","metadata":{}},{"cell_type":"markdown","source":"Dans ce notebook, nous allons analyser la signification et l'intuition derrière chaque composante du jeu de données, y compris les images, le LiDAR(aser imaging detection and ranging : La télédétection par laser ou lidar) et les nuages de points. Après avoir plongé dans la théorie qui sous-tend ces concepts, je montrerai comment cet ensemble de données peut être conditionné dans un format compact qui facilite l'interrogation des informations de l'ensemble de données. Enfin, je montrerai comment visualiser et explorer ces données à l'aide la visualization *matplotlib*. ","metadata":{}},{"cell_type":"markdown","source":"# Acknowledgements","metadata":{}},{"cell_type":"markdown","source":"* [NuScences DevKit ~ by Lyft](https://github.com/lyft/nuscenes-devkit)\n* [EDA - 3D Object Detection Challenge ~ by beluga](https://www.kaggle.com/gaborfodor/eda-3d-object-detection-challenge)\n* [Lyft: EDA, Animations, generating CSVs ~ by xhulu](https://www.kaggle.com/xhlulu/lyft-eda-animations-generating-csvs)\n* [Lidar - Wikipedia](https://en.wikipedia.org/wiki/Lidar)","metadata":{}},{"cell_type":"markdown","source":"If you find this kernel interesting, please drop an upvote. It motivates me to produce more quality content :)","metadata":{}},{"cell_type":"markdown","source":"### Une voiture conduite par l'intelligence artificielle !","metadata":{}},{"cell_type":"code","source":"## Importer la librairie HTML pour lire la vidéo\nfrom IPython.display import HTML\nHTML('
')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T10:20:46.175446Z","iopub.execute_input":"2021-05-22T10:20:46.175724Z","iopub.status.idle":"2021-05-22T10:20:46.185114Z","shell.execute_reply.started":"2021-05-22T10:20:46.175679Z","shell.execute_reply":"2021-05-22T10:20:46.184136Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"On peut voir dans la vidéo que la voiture est capable de prendre des virages, de changer de voie, de s'arrêter aux feux rouges, etc. sans effort. Cela est possible parce que la voiture est capable de reconnaître avec précision les objets dans l'espace 3D en utilisant les informations de ses capteurs, comme les données d'image et LiDAR. Je vais maintenant examiner la signification théorique de ces formes de données, puis je visualiserai ces informations plus tard dans le noyau.","metadata":{}},{"cell_type":"markdown","source":"# Structure du dataset ","metadata":{}},{"cell_type":"markdown","source":"1. `scene` - Consiste en 25 à 45 secondes de trajet d'une voiture dans un environnement donné. Chaque scence est composée de plusieurs échantillons.\n2. `sample` - Un instantané d'une scène à un moment précis dans le temps. Chaque échantillon est annoté avec les objets présents.\n3. `sample_data` - Contient les données collectées à partir d'un capteur particulier de la voiture.\n4. `sample_annotation` - Une instance annotée d'un objet qui nous intéresse.\n5. `instance` - Une énumération de toutes les instances d'objets que nous avons observées.\n6. `category` - Plusieurs catégories d'objets (e.g. véhicule, humain). \n7. `attribute` - Propriété d'une instance qui peut changer alors que la catégorie reste la même.\n8. `visibility` - \n9. `sensor` - Un type de capteur spécifique.\n10. `calibrated sensor` - Définition d'un capteur particulier tel qu'étalonné sur un véhicule particulier.\n11. `ego_pose` - Le véhicule Ego pose à un moment précis.\n12. `log` - Informations sur le journal à partir duquel les données ont été extraites.\n13. `map` - Cartographier les données stockées sous forme de masques sémantiques binaires à partir d'une vue de haut en bas.","metadata":{}},{"cell_type":"markdown","source":"Nous distinguons deux types d'informations: **image data and LiDAR data**.","metadata":{}},{"cell_type":"markdown","source":"Les données de l'image sont dans le format habituel *.jpeg*, qui est assez simple à comprendre. Chaque image se compose simplement de trois canaux de couleur : Rouge (R), Bleu (B) et Vert (G) qui forment le format d'image couleur RVB. Ces canaux de couleur se superposent pour former l'image colorée finale. Ces images peuvent donc être stockées dans un tenseur quadridimensionnel dont les dimensions sont les suivantes: **(batch_size, channels, width, height)**.","metadata":{}},{"cell_type":"markdown","source":"# LiDAR ?","metadata":{}},{"cell_type":"markdown","source":"Le LiDAR (Light Detection and Ranging) est une méthode utilisée pour générer des représentations 3D précises de l'environnement, et il utilise la lumière laser pour y parvenir. En gros, la cible 3D est éclairée par une lumière laser (un faisceau de lumière focalisé et dirigé) et la lumière afléchié est collectée par des capteurs. Le temps nécessaire pour que la lumière soit affléchie vers le capteur est calculé. \n\n**Des capteurs différents collectent la lumière de différentes parties de l'objet, et les temps enregistrés par les capteurs seront différents. Cette différence de temps calculée par les capteurs peut être utilisée pour calculer la profondeur de l'objet. Cette information de profondeur, combinée à la représentation 2D de l'image, fournit une représentation 3D précise de l'objet. Ce processus est similaire à la vision humaine réelle. Deux yeux font des observations en 2D et ces deux informations sont combinées pour former une carte 3D (perception de la profondeur). C'est ainsi que les humains perçoivent le monde qui les entoure**.\n\nCette technologie est utilisée pour créer des représentations 3D dans de nombreux scénarios du monde réel. Par exemple, elle est utilisée dans les fermes pour aider à semer les graines et à enlever les mauvaises herbes. Un robot en mouvement utilise le LiDAR pour créer une carte en 3D de son environnement. Grâce à cette carte, il évite les obstacles et accomplit ses tâches. Cette technologie est également utilisée en archéologie. Le LiDAR est utilisé pour créer des rendus 3D à partir de scans 2D d'artefacts. Cela donne une idée précise de la forme 3D de l'artefact lorsque celui-ci ne peut être fouillé pour une raison quelconque. Enfin, le LiDAR peut également être utilisé pour produire des cartes 3D de haute qualité des fonds marins et d'autres terrains inaccessibles, ce qui le rend très utile aux géologues et aux océanographes. Ci-dessous, la carte 3D d'un plancher océanique générée à l'aide du LiDAR :","metadata":{}},{"cell_type":"markdown","source":"
","metadata":{}},{"cell_type":"markdown","source":"Et, bien sûr, les voitures à conduite autonome utilisent cette technologie pour identifier les objets qui les entourent en 3D, ainsi que pour estimer la vitesse et l'orientation de ces objets. Cette carte 3D complète fournit à la voiture des informations détaillées qui lui permettent de naviguer même dans des environnements complexes. Vous trouverez ci-dessous une vidéo présentant un drone équipé d'un LiDAR. Il crée automatiquement une carte 3D du monde qui l'entoure en utilisant le processus mentionné ci-dessus.","metadata":{}},{"cell_type":"code","source":"HTML('
')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T10:48:18.535300Z","iopub.execute_input":"2021-05-22T10:48:18.535585Z","iopub.status.idle":"2021-05-22T10:48:18.541037Z","shell.execute_reply.started":"2021-05-22T10:48:18.535539Z","shell.execute_reply":"2021-05-22T10:48:18.540117Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Démonstration de fonctionnement de LiDAR ","metadata":{}},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"des faisceaux laser sont tirés dans tous les sens par un laser. Les faisceaux laser se réfléchissent sur les objets qui se trouvent sur leur chemin et les faisceaux réfléchis sont collectés par un capteur. Maintenant, un dispositif spécial appelé **caméra flash LiDAR** est utilisé pour créer des cartes en 3D en utilisant les informations de ces capteurs.","metadata":{}},{"cell_type":"markdown","source":"### Flash LiDAR Camera","metadata":{}},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"L'appareil présenté dans l'image ci-dessus s'appelle une caméra Flash LiDAR. Le plan focal d'une caméra Flash LiDAR comporte des rangées et des colonnes de pixels ayant une \"profondeur\" et une \"intensité\" suffisantes pour créer des modèles de paysage en 3D. Chaque pixel enregistre le temps que met chaque impulsion laser à atteindre la cible et à revenir au capteur, ainsi que la profondeur, l'emplacement et l'intensité de réflexion de l'objet touché par l'impulsion laser.\n\nLe Flash LiDAR utilise une seule source lumineuse qui illumine le champ de vision en une seule impulsion. Tout comme un appareil photo qui prend des photos de la distance, au lieu des couleurs.\n\nLa source d'illumination embarquée fait du Flash LiDAR un capteur actif. Le signal renvoyé est traité par des algorithmes intégrés pour produire un rendu 3D quasi instantané des objets et des caractéristiques du terrain dans le champ de vision du capteur. La fréquence de répétition des impulsions laser est suffisante pour générer des vidéos 3D avec une résolution et une précision élevées. La fréquence d'images élevée du capteur en fait un outil utile pour une variété d'applications qui bénéficient d'une visualisation en temps réel, comme la conduite autonome des véhicules. En renvoyant immédiatement un maillage d'élévation 3D des paysages cibles, un capteur flash peut être utilisé par un véhicule autonome pour prendre des décisions concernant le réglage de la vitesse, le freinage, la direction, etc.\n\nCe type de caméra est fixé au sommet des voitures autonomes, et ces voitures l'utilisent pour naviguer tout en conduisant.","metadata":{}},{"cell_type":"markdown","source":"# Visualisation de données ","metadata":{}},{"cell_type":"markdown","source":"### Install *lyft_dataset_sdk* and import the necessary libraries","metadata":{}},{"cell_type":"markdown","source":"Nous aurons besoin de la bibliothèque *lyft_dataset_sdk* car elle nous aidera à visualiser facilement l'image et les données LiDAR. Une simple commande *pip install* est nécessaire. J'utiliserai également l'installation de la bibliothèque *chart_studio* pour générer des graphiques interactifs.","metadata":{}},{"cell_type":"code","source":"!pip install lyft_dataset_sdk","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2021-05-22T10:57:22.290660Z","iopub.execute_input":"2021-05-22T10:57:22.291008Z","iopub.status.idle":"2021-05-22T10:57:46.344443Z","shell.execute_reply.started":"2021-05-22T10:57:22.290962Z","shell.execute_reply":"2021-05-22T10:57:46.343350Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport gc\nimport numpy as np\nimport pandas as pd\n\nimport json\nimport math\nimport sys\nimport time\nfrom datetime import datetime\nfrom typing import Tuple, List\n\nimport cv2\nimport matplotlib.pyplot as plt\nimport sklearn.metrics\nfrom PIL import Image\n\nfrom matplotlib.axes import Axes\nfrom matplotlib import animation, rc\nimport plotly.graph_objs as go\nimport plotly.tools as tls\nfrom plotly.offline import plot, init_notebook_mode\nimport plotly.figure_factory as ff\n\ninit_notebook_mode(connected=True)\n\nimport seaborn as sns\nfrom pyquaternion import Quaternion\nfrom tqdm import tqdm\n\nfrom lyft_dataset_sdk.utils.map_mask import MapMask\nfrom lyft_dataset_sdk.lyftdataset import LyftDataset\nfrom lyft_dataset_sdk.utils.geometry_utils import view_points, box_in_image, BoxVisibility\nfrom lyft_dataset_sdk.utils.geometry_utils import view_points, transform_matrix\nfrom pathlib import Path\n\nimport struct\nfrom abc import ABC, abstractmethod\nfrom functools import reduce\nfrom typing import Tuple, List, Dict\nimport copy","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-05-22T10:59:35.829643Z","iopub.execute_input":"2021-05-22T10:59:35.829938Z","iopub.status.idle":"2021-05-22T10:59:39.703471Z","shell.execute_reply.started":"2021-05-22T10:59:35.829884Z","shell.execute_reply":"2021-05-22T10:59:39.702710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### le chemin de données","metadata":{}},{"cell_type":"code","source":"## créér le chémin où les donnée\nDATA_PATH = '/kaggle/input/3d-object-detection-for-autonomous-vehicles/'","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:00:32.237983Z","iopub.execute_input":"2021-05-22T11:00:32.238299Z","iopub.status.idle":"2021-05-22T11:00:32.244534Z","shell.execute_reply.started":"2021-05-22T11:00:32.238242Z","shell.execute_reply":"2021-05-22T11:00:32.243764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Importer les données de training","metadata":{}},{"cell_type":"code","source":"## importer le dataset train \ntrain = pd.read_csv(DATA_PATH + 'train.csv')\nsample_submission = pd.read_csv(DATA_PATH + 'sample_submission.csv')","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:03:47.370905Z","iopub.execute_input":"2021-05-22T11:03:47.371425Z","iopub.status.idle":"2021-05-22T11:03:48.538886Z","shell.execute_reply.started":"2021-05-22T11:03:47.371224Z","shell.execute_reply":"2021-05-22T11:03:48.538166Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:04:14.634693Z","iopub.execute_input":"2021-05-22T11:04:14.634980Z","iopub.status.idle":"2021-05-22T11:04:14.655211Z","shell.execute_reply.started":"2021-05-22T11:04:14.634932Z","shell.execute_reply":"2021-05-22T11:04:14.654140Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n### Regrouper les données par catégorie d'objet","metadata":{}},{"cell_type":"code","source":"# Taken from https://www.kaggle.com/gaborfodor/eda-3d-object-detection-challenge\n\nobject_columns = ['sample_id', 'object_id', 'center_x', 'center_y', 'center_z',\n 'width', 'length', 'height', 'yaw', 'class_name']\nobjects = []\nfor sample_id, ps in tqdm(train.values[:]):\n object_params = ps.split()\n n_objects = len(object_params)\n for i in range(n_objects // 8):\n x, y, z, w, l, h, yaw, c = tuple(object_params[i * 8: (i + 1) * 8])\n objects.append([sample_id, i, x, y, z, w, l, h, yaw, c])\ntrain_objects = pd.DataFrame(\n objects,\n columns = object_columns\n)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:07:16.867644Z","iopub.execute_input":"2021-05-22T11:07:16.867933Z","iopub.status.idle":"2021-05-22T11:07:19.749912Z","shell.execute_reply.started":"2021-05-22T11:07:16.867883Z","shell.execute_reply":"2021-05-22T11:07:19.749163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Convertir les colonnes de type string en numérique (float32)","metadata":{}},{"cell_type":"code","source":"train_objects.head()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:08:03.199957Z","iopub.execute_input":"2021-05-22T11:08:03.200239Z","iopub.status.idle":"2021-05-22T11:08:03.217047Z","shell.execute_reply.started":"2021-05-22T11:08:03.200191Z","shell.execute_reply":"2021-05-22T11:08:03.215897Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"numerical_cols = ['object_id', 'center_x', 'center_y', 'center_z', 'width', 'length', 'height', 'yaw']\ntrain_objects[numerical_cols] = np.float32(train_objects[numerical_cols].values)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:08:06.391039Z","iopub.execute_input":"2021-05-22T11:08:06.391369Z","iopub.status.idle":"2021-05-22T11:08:07.802498Z","shell.execute_reply.started":"2021-05-22T11:08:06.391311Z","shell.execute_reply":"2021-05-22T11:08:07.801553Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_objects.head()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:08:07.804198Z","iopub.execute_input":"2021-05-22T11:08:07.804503Z","iopub.status.idle":"2021-05-22T11:08:07.823240Z","shell.execute_reply.started":"2021-05-22T11:08:07.804460Z","shell.execute_reply":"2021-05-22T11:08:07.822651Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_objects.info()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:09:31.494919Z","iopub.execute_input":"2021-05-22T11:09:31.495206Z","iopub.status.idle":"2021-05-22T11:09:31.621163Z","shell.execute_reply.started":"2021-05-22T11:09:31.495159Z","shell.execute_reply":"2021-05-22T11:09:31.620058Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Analyse exploratoire de données ","metadata":{}},{"cell_type":"markdown","source":"### center_x and center_y","metadata":{}},{"cell_type":"markdown","source":"**center_x** et **center_y** correspondent aux coordonnées *x* et *y* du centre de l'emplacement d'un objet (volume limite). Ces coordonnées représentent l'emplacement d'un objet sur le plan *x-y*.","metadata":{}},{"cell_type":"markdown","source":"### Distributions *center_x* and *center_y*","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['center_x'], color='darkorange', ax=ax).set_title('center_x and center_y', fontsize=16)\nsns.distplot(train_objects['center_y'], color='purple', ax=ax).set_title('center_x and center_y', fontsize=16)\nplt.xlabel('center_x and center_y', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:11:23.794328Z","iopub.execute_input":"2021-05-22T11:11:23.794619Z","iopub.status.idle":"2021-05-22T11:11:24.671813Z","shell.execute_reply.started":"2021-05-22T11:11:23.794573Z","shell.execute_reply":"2021-05-22T11:11:24.670889Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Sur ce graphique ci-dessus, la distribution violette est celle de *center_y* et la distribution orange est celle de *center_x*. Le diagramme ci-dessus montre que les distributions de *centre_x* et de *centre_y* ont plusieurs pics et sont donc multimodales. Les deux distributions présentent également une nette inclinaison vers la droite ou une inclinaison positive. Mais, la distribution de *center_y* (violet) a un biais significativement plus élevé que la distribution de *center_x* (orange). La distribution *center_x* est plus uniformément répartie. \n\nCela indique que les objets sont répartis très uniformément le long de l'axe *x*, mais pas de la même manière le long de l'axe *y*. Cela est probablement dû au fait que la caméra de la voiture peut facilement détecter des objets à gauche ou à droite (le long de l'axe *x*) en raison de la faible largeur de la route. Mais, comme la longueur de la route est beaucoup plus grande que sa largeur, et qu'il y a plus de chances que la vue de la caméra soit bloquée depuis cet angle, la caméra ne peut trouver que des objets situés juste devant ou juste derrière (et pas plus loin).","metadata":{}},{"cell_type":"markdown","source":"### Relation entre *center_x* and *center_y*","metadata":{}},{"cell_type":"markdown","source":"### KDE Plot","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"new_train_objects = train_objects.query('class_name == \"car\"')\nplot = sns.jointplot(x=new_train_objects['center_x'][:1000], y=new_train_objects['center_y'][:1000], kind='kde', color='blueviolet')\nplot.set_axis_labels('center_x', 'center_y', fontsize=16)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:15:31.678101Z","iopub.execute_input":"2021-05-22T11:15:31.678443Z","iopub.status.idle":"2021-05-22T11:15:33.408915Z","shell.execute_reply.started":"2021-05-22T11:15:31.678386Z","shell.execute_reply":"2021-05-22T11:15:33.407925Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le graphique KDE ci-dessus, nous pouvons voir que *center_x* et *center_y* semblent avoir une corrélation quelque peu négative. Cela est probablement dû, une fois de plus, aux limites du système de caméra. La caméra peut détecter des objets qui sont loin devant, mais pas trop loin sur le côté. Et elle peut également détecter des objets qui sont loin sur le côté, mais pas trop loin devant. Mais **la caméra ne peut pas détecter les objets qui sont à la fois loin devant et loin sur le côté**. Pour cette raison, les objets situés loin devant et loin sur le côté ne sont pas du tout détectés, et seuls les objets qui remplissent une (ou aucune) de ces conditions sont détectés. Il en résulte une relation négative entre *center_x* et *center_y*.","metadata":{}},{"cell_type":"markdown","source":"### center_z","metadata":{}},{"cell_type":"markdown","source":"**center_z** correspond à la coordonnée *xz* du centre de l'emplacement d'un objet (volume limite). Cette coordonnée représente la hauteur de l'objet au-dessus du plan *x-y*.","metadata":{}},{"cell_type":"markdown","source":"### Distribution *center_z*","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['center_z'], color='navy', ax=ax).set_title('center_z', fontsize=16)\nplt.xlabel('center_z', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:18:37.705377Z","iopub.execute_input":"2021-05-22T11:18:37.705889Z","iopub.status.idle":"2021-05-22T11:18:38.473961Z","shell.execute_reply.started":"2021-05-22T11:18:37.705703Z","shell.execute_reply":"2021-05-22T11:18:38.473111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la distribution de *center_z* a une asymétrie positive (vers la droite) extrêmement élevée et qu'elle est regroupée autour de la marque -20 (qui est proche de sa valeur moyenne). La variation (dispersion) de *center_z* est nettement plus faible que celle de *center_x* et *center_y*. Cela s'explique probablement par le fait que la plupart des objets sont très proches du plan plat de la route et qu'il n'y a donc pas de grande variation de la hauteur des objets au-dessus (ou au-dessous) de la caméra. Il y a naturellement une variation beaucoup plus grande dans les coordonnées *x* et *y* de l'objet.\n\nDe plus, la plupart des coordonnées *z* sont négatives car la caméra est fixée au sommet de la voiture. Ainsi, la plupart du temps, la caméra doit \"regarder vers le bas\" pour voir les objets. Par conséquent, la hauteur ou les coordonnées *z* des objets par rapport à la caméra sont généralement négatives.","metadata":{}},{"cell_type":"markdown","source":"### yaw","metadata":{}},{"cell_type":"markdown","source":"**yaw** est l'angle du volume autour de l'axe *z*, ce qui fait que le \"lacet\" est la direction vers laquelle l'avant du véhicule/boîte englobante est dirigé lorsqu'il est au sol.","metadata":{}},{"cell_type":"markdown","source":"### Distribution de *yaw*","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['yaw'], color='darkgreen', ax=ax).set_title('yaw', fontsize=16)\nplt.xlabel('yaw', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:38:06.489867Z","iopub.execute_input":"2021-05-22T11:38:06.490478Z","iopub.status.idle":"2021-05-22T11:38:07.044164Z","shell.execute_reply.started":"2021-05-22T11:38:06.490164Z","shell.execute_reply":"2021-05-22T11:38:07.043409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la distribution de *yaw* est grossièrement bimodale, *c'est-à-dire qu'il y a deux pics majeurs dans la distribution. L'un des pics se situe autour de 0,5 et l'autre autour de 2,5. On peut estimer que la moyenne se situe entre 1 et 2 (autour de 1,5). La distribution ne présente pas d'asymétrie nette. La présence des deux pics à des positions symétriques réduit l'asymétrie dans les deux directions (et ils s'annulent), ce qui rend la distribution plus équilibrée que les distributions de *centre_x*, *centre_y* et *centre_z*.","metadata":{}},{"cell_type":"markdown","source":"### width","metadata":{}},{"cell_type":"markdown","source":"**width** est simplement la largeur du volume délimité dans lequel se trouve l'objet.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['width'], color='magenta', ax=ax).set_title('width', fontsize=16)\nplt.xlabel('width', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:39:50.933860Z","iopub.execute_input":"2021-05-22T11:39:50.934172Z","iopub.status.idle":"2021-05-22T11:39:51.456382Z","shell.execute_reply.started":"2021-05-22T11:39:50.934123Z","shell.execute_reply":"2021-05-22T11:39:51.455564Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la *largeur* est distribuée à peu près normalement avec une moyenne d'environ 2, avec quelques valeurs aberrantes de chaque côté. La majorité des objets sont des voitures (comme nous le verrons plus tard), et celles-ci constituent une largeur d'environ 2 (au sommet). Les valeurs aberrantes à droite représentent des objets plus grands comme les camions et les camionnettes, et les valeurs aberrantes à gauche représentent des objets plus petits comme les piétons et les bicyclettes.","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### length","metadata":{}},{"cell_type":"markdown","source":"**length** est simplement la longueur du volume délimité dans lequel se trouve l'objet.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['length'], color='crimson', ax=ax).set_title('length', fontsize=16)\nplt.xlabel('length', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:41:26.875518Z","iopub.execute_input":"2021-05-22T11:41:26.875837Z","iopub.status.idle":"2021-05-22T11:41:27.383567Z","shell.execute_reply.started":"2021-05-22T11:41:26.875787Z","shell.execute_reply":"2021-05-22T11:41:27.382619Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la *longueur* a une distribution fortement positive (skew vers la droite) avec une moyenne d'environ 5, avec quelques valeurs aberrantes de chaque côté. La majorité des objets sont des voitures (comme nous le verrons plus tard), et celles-ci constituent une longueur d'environ 5 (au sommet). Les valeurs aberrantes sur la droite représentent des objets plus grands comme les camions et les camionnettes, et les valeurs aberrantes sur la gauche représentent des objets plus petits comme les piétons et les bicyclettes.","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### height","metadata":{}},{"cell_type":"markdown","source":"**height** est simplement la hauteur du volume délimité dans lequel se trouve l'objet.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['height'], color='indigo', ax=ax).set_title('height', fontsize=16)\nplt.xlabel('height', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:42:31.953641Z","iopub.execute_input":"2021-05-22T11:42:31.953937Z","iopub.status.idle":"2021-05-22T11:42:32.464587Z","shell.execute_reply.started":"2021-05-22T11:42:31.953888Z","shell.execute_reply":"2021-05-22T11:42:32.463710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la *hauteur* a une distribution fortement positive (skew vers la droite) avec une moyenne d'environ 2, avec quelques aberrations de part et d'autre. La majorité des objets sont des voitures (comme nous le verrons plus tard), et celles-ci constituent une longueur d'environ 2 (au sommet). Les valeurs aberrantes sur la droite représentent des objets plus grands comme les camions et les camionnettes, et les valeurs aberrantes sur la gauche représentent des objets plus petits comme les piétons et les bicyclettes.","metadata":{}},{"cell_type":"markdown","source":"### Fréquence des objets","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nplot = sns.countplot(y=\"class_name\", data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette=['navy', 'darkblue', 'blue', 'dodgerblue', 'skyblue', 'lightblue']).set_title('Object Frequencies', fontsize=16)\nplt.yticks(fontsize=14)\nplt.xlabel(\"Count\", fontsize=15)\nplt.ylabel(\"Class Name\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:44:05.860924Z","iopub.execute_input":"2021-05-22T11:44:05.861213Z","iopub.status.idle":"2021-05-22T11:44:06.595027Z","shell.execute_reply.started":"2021-05-22T11:44:05.861164Z","shell.execute_reply":"2021-05-22T11:44:06.594250Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Le diagramme ci-dessus montre que la classe d'objets la plus courante dans l'ensemble de données est la \"voiture\". Cela n'est pas surprenant car les images sont prises dans les rues de Palo Alto, dans la Silicon Valley, en Californie. Et le véhicule (ou l'entité, d'ailleurs) le plus communément visible sur ces routes est la voiture. Toutes les autres classes d'objets sont loin d'être proches des voitures en termes de fréquence.","metadata":{}},{"cell_type":"code","source":"## Analyse multivariée ","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:45:46.470002Z","iopub.execute_input":"2021-05-22T11:45:46.470326Z","iopub.status.idle":"2021-05-22T11:45:46.474036Z","shell.execute_reply.started":"2021-05-22T11:45:46.470255Z","shell.execute_reply":"2021-05-22T11:45:46.473218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### center_x *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de **center_x** change pour différents **nom de classe_des objets.**.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"center_x\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGnBu',\n split=True, ax=ax).set_title('center_x (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_x\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:46:40.544552Z","iopub.execute_input":"2021-05-22T11:46:40.544841Z","iopub.status.idle":"2021-05-22T11:46:43.411018Z","shell.execute_reply.started":"2021-05-22T11:46:40.544795Z","shell.execute_reply":"2021-05-22T11:46:43.410171Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon ci-dessus, nous pouvons voir que les distributions de *center_x* pour les grands véhicules, y compris les camions, les bus et autres véhicules, sont bien réparties. Elles ne présentent pratiquement pas d'asymétrie et ont des moyennes plus élevées que les distributions des piétons et des bicyclettes. Cela s'explique probablement par le fait que ces gros véhicules ont tendance à garder une plus grande distance avec les autres véhicules, et que les petits véhicules ne restent pas trop près de ces gros véhicules afin d'éviter les accidents. Par conséquent, la moyenne *center_x* est nettement supérieure pour les gros véhicules comme les bus et les camions.\n\nEn revanche, les objets plus petits comme les piétons et les bicyclettes ont des distributions *center_x* fortement inclinées vers la droite. Ces distributions ont également des moyennes nettement plus faibles que celles des véhicules plus grands. Cela est probablement dû au fait que les piétons (qui traversent la route) et les cyclistes n'ont pas besoin de maintenir de grandes distances avec les voitures et les camions pour éviter les accidents. Ils traversent généralement la route pendant un feu rouge, lorsque le trafic s'arrête.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"center_x\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGnBu', ax=ax).set_title('center_x (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_x\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:49:25.633246Z","iopub.execute_input":"2021-05-22T11:49:25.633624Z","iopub.status.idle":"2021-05-22T11:49:26.640091Z","shell.execute_reply.started":"2021-05-22T11:49:25.633577Z","shell.execute_reply":"2021-05-22T11:49:26.639183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In the box plots above, we can notice the same observation as in the violin plot above. The *center_x* distributions for smaller objects like pedestrians and bicycles have very low mean and quartile values as compared to larger objects like cars, trucks, and buses.","metadata":{}},{"cell_type":"markdown","source":"### center_y *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, nous allons explorer comment la distribution de **center_y** change pour différents **classes_noms** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"center_y\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlOrRd',\n split=True, ax=ax).set_title('center_y (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_y\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:50:52.650733Z","iopub.execute_input":"2021-05-22T11:50:52.651072Z","iopub.status.idle":"2021-05-22T11:50:55.421171Z","shell.execute_reply.started":"2021-05-22T11:50:52.651021Z","shell.execute_reply":"2021-05-22T11:50:55.420362Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon ci-dessus, nous pouvons voir que les distributions de *centre_y* pour les petits objets, y compris les piétons et les bicyclettes, ont une valeur moyenne plus grande que les grands objets comme les camions et les bus. Les distributions pour les petits objets ont une densité de probabilité beaucoup plus grande concentrée à des valeurs plus élevées de *centre_y* par rapport aux grands objets. Cela signifie que les petits objets, en général, ont des valeurs de *center_y* plus élevées que les grands objets. \n\nCela est probablement dû au fait que les grands véhicules ont tendance à se trouver dans le champ de vision de la caméra en raison de leur grande taille. Mais les objets plus petits, comme les bicyclettes et les piétons, ne peuvent pas rester dans le champ de vision de la caméra lorsqu'ils sont trop proches. Par conséquent, la plupart des piétons et des vélos qui sont détectés ont tendance à être éloignés. Le *centre_y* est donc plus grand (en moyenne) pour les petits objets que pour les grands.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"center_y\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlOrRd', ax=ax).set_title('center_y (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_y\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:52:41.066865Z","iopub.execute_input":"2021-05-22T11:52:41.067197Z","iopub.status.idle":"2021-05-22T11:52:41.940086Z","shell.execute_reply.started":"2021-05-22T11:52:41.067155Z","shell.execute_reply":"2021-05-22T11:52:41.939249Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions *center_y* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus grandes que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### center_z *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de **center_z** change pour différents **classes_noms** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"center_z\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"').query('center_z <= -5'),\n palette='RdPu',\n split=True, ax=ax).set_title('center_z (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_z\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:53:46.757168Z","iopub.execute_input":"2021-05-22T11:53:46.757484Z","iopub.status.idle":"2021-05-22T11:53:49.337041Z","shell.execute_reply.started":"2021-05-22T11:53:46.757433Z","shell.execute_reply":"2021-05-22T11:53:49.336084Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon ci-dessus, nous pouvons voir que les distributions de *center_z* pour les petits objets, y compris les piétons et les bicyclettes, ont une valeur moyenne nettement inférieure à celle des grands objets comme les camions et les bus. Les distributions pour les petits objets ont une densité de probabilité beaucoup plus importante concentrée à des valeurs plus faibles de *centre_z* par rapport aux grands objets. Cela signifie que les petits objets, en général, ont des valeurs de *center_y* plus petites que les grands objets. \n\nCela est probablement dû au fait que les petits objets comme les piétons et les vélos ont tendance à avoir une hauteur plus faible par rapport à la caméra. Et, d'autre part, les objets plus grands comme les voitures, les camions et les bus ont tendance à avoir une plus grande hauteur par rapport à la caméra.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"center_z\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"').query('center_z <= -5'),\n palette='RdPu', ax=ax).set_title('center_z (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_z\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:55:10.581600Z","iopub.execute_input":"2021-05-22T11:55:10.581888Z","iopub.status.idle":"2021-05-22T11:55:11.403009Z","shell.execute_reply.started":"2021-05-22T11:55:10.581839Z","shell.execute_reply":"2021-05-22T11:55:11.402155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions *center_z* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### width *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de **largeur** change pour différents **noms de classe** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"width\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGn',\n split=True, ax=ax).set_title('width (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"width\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:56:24.885126Z","iopub.execute_input":"2021-05-22T11:56:24.885457Z","iopub.status.idle":"2021-05-22T11:56:27.716860Z","shell.execute_reply.started":"2021-05-22T11:56:24.885400Z","shell.execute_reply":"2021-05-22T11:56:27.715945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon, nous pouvons clairement voir que les distributions de *largeur* pour les grands véhicules comme les voitures, les bus et les camions ont des moyennes beaucoup plus grandes que celles des petits objets comme les piétons et les bicyclettes. Cela n'est pas surprenant car les camions, les bus et les voitures ont presque toujours une largeur beaucoup plus grande que les piétons et les vélos.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"width\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGn', ax=ax).set_title('width (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"width\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:57:25.796188Z","iopub.execute_input":"2021-05-22T11:57:25.796530Z","iopub.status.idle":"2021-05-22T11:57:26.591057Z","shell.execute_reply.started":"2021-05-22T11:57:25.796480Z","shell.execute_reply":"2021-05-22T11:57:26.590298Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions de *largeur* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### length *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"In the plots below, I will explore how the distribution of **length** changes for different object **class_names**.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"length\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and length < 15'),\n palette='Purples',\n split=True, ax=ax).set_title('length (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"length\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:57:56.182637Z","iopub.execute_input":"2021-05-22T11:57:56.182990Z","iopub.status.idle":"2021-05-22T11:57:58.648718Z","shell.execute_reply.started":"2021-05-22T11:57:56.182927Z","shell.execute_reply":"2021-05-22T11:57:58.647862Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon, nous pouvons clairement voir que les distributions de *longueur* pour les grands véhicules comme les voitures, les bus et les camions ont des moyennes beaucoup plus grandes que celles des petits objets comme les piétons et les bicyclettes. Ce n'est pas surprenant car les camions, les bus et les voitures ont presque toujours une longueur beaucoup plus grande que les piétons et les vélos.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"length\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and length < 15'),\n palette='Purples', ax=ax).set_title('length (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"length\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:58:38.336924Z","iopub.execute_input":"2021-05-22T11:58:38.337213Z","iopub.status.idle":"2021-05-22T11:58:39.195024Z","shell.execute_reply.started":"2021-05-22T11:58:38.337163Z","shell.execute_reply":"2021-05-22T11:58:39.194247Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions de *longueur* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### height *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de la **hauteur** change pour différents **noms de classe** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"height\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and height < 6'),\n palette='Reds',\n split=True, ax=ax).set_title('height (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"height\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:59:04.044292Z","iopub.execute_input":"2021-05-22T11:59:04.044626Z","iopub.status.idle":"2021-05-22T11:59:06.561721Z","shell.execute_reply.started":"2021-05-22T11:59:04.044577Z","shell.execute_reply":"2021-05-22T11:59:06.560862Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon, nous pouvons clairement voir que les distributions de *longueur* pour les grands véhicules comme les bus et les camions ont des moyennes beaucoup plus grandes que celles des petits objets comme les piétons et les bicyclettes. Ce n'est pas surprenant car les camions et les bus ont presque toujours une longueur beaucoup plus grande que les piétons et les vélos.\n\nLes voitures constituent la seule exception à cette tendance. Elles ont tendance à avoir une hauteur similaire à celle des piétons.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"height\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and height < 6'),\n palette='Reds', ax=ax).set_title('height (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"height\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:59:35.905404Z","iopub.execute_input":"2021-05-22T11:59:35.905692Z","iopub.status.idle":"2021-05-22T11:59:36.697307Z","shell.execute_reply.started":"2021-05-22T11:59:35.905643Z","shell.execute_reply":"2021-05-22T11:59:36.696577Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions de *hauteur* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.\n\nUne fois encore, les voitures constituent la seule exception à cette tendance. Elles ont tendance à avoir une hauteur similaire à celle des piétons.","metadata":{}},{"cell_type":"markdown","source":"# analyse les images et les données LiDAR","metadata":{}},{"cell_type":"markdown","source":"### Define some functions to help create the *LyftDataset* class\n#### (click CODE on the right side)","metadata":{}},{"cell_type":"code","source":"# Lyft Dataset SDK dev-kit.\n# Code written by Oscar Beijbom, 2018.\n# Licensed under the Creative Commons [see licence.txt]\n# Modified by Vladimir Iglovikov 2019.\n\nclass PointCloud(ABC):\n \"\"\"\n Abstract class for manipulating and viewing point clouds.\n Every point cloud (lidar and radar) consists of points where:\n - Dimensions 0, 1, 2 represent x, y, z coordinates.\n These are modified when the point cloud is rotated or translated.\n - All other dimensions are optional. Hence these have to be manually modified if the reference frame changes.\n \"\"\"\n\n def __init__(self, points: np.ndarray):\n \"\"\"\n Initialize a point cloud and check it has the correct dimensions.\n :param points: . d-dimensional input point cloud matrix.\n \"\"\"\n assert points.shape[0] == self.nbr_dims(), (\n \"Error: Pointcloud points must have format: %d x n\" % self.nbr_dims()\n )\n self.points = points\n\n @staticmethod\n @abstractmethod\n def nbr_dims() -> int:\n \"\"\"Returns the number of dimensions.\n Returns: Number of dimensions.\n \"\"\"\n pass\n\n @classmethod\n @abstractmethod\n def from_file(cls, file_name: str) -> \"PointCloud\":\n \"\"\"Loads point cloud from disk.\n Args:\n file_name: Path of the pointcloud file on disk.\n Returns: PointCloud instance.\n \"\"\"\n pass\n\n @classmethod\n def from_file_multisweep(\n cls, lyftd, sample_rec: Dict, chan: str, ref_chan: str, num_sweeps: int = 26, min_distance: float = 1.0\n ) -> Tuple[\"PointCloud\", np.ndarray]:\n \"\"\"Return a point cloud that aggregates multiple sweeps.\n As every sweep is in a different coordinate frame, we need to map the coordinates to a single reference frame.\n As every sweep has a different timestamp, we need to account for that in the transformations and timestamps.\n Args:\n lyftd: A LyftDataset instance.\n sample_rec: The current sample.\n chan: The radar channel from which we track back n sweeps to aggregate the point cloud.\n ref_chan: The reference channel of the current sample_rec that the point clouds are mapped to.\n num_sweeps: Number of sweeps to aggregated.\n min_distance: Distance below which points are discarded.\n Returns: (all_pc, all_times). The aggregated point cloud and timestamps.\n \"\"\"\n\n # Init\n points = np.zeros((cls.nbr_dims(), 0))\n all_pc = cls(points)\n all_times = np.zeros((1, 0))\n\n # Get reference pose and timestamp\n ref_sd_token = sample_rec[\"data\"][ref_chan]\n ref_sd_rec = lyftd.get(\"sample_data\", ref_sd_token)\n ref_pose_rec = lyftd.get(\"ego_pose\", ref_sd_rec[\"ego_pose_token\"])\n ref_cs_rec = lyftd.get(\"calibrated_sensor\", ref_sd_rec[\"calibrated_sensor_token\"])\n ref_time = 1e-6 * ref_sd_rec[\"timestamp\"]\n\n # Homogeneous transform from ego car frame to reference frame\n ref_from_car = transform_matrix(ref_cs_rec[\"translation\"], Quaternion(ref_cs_rec[\"rotation\"]), inverse=True)\n\n # Homogeneous transformation matrix from global to _current_ ego car frame\n car_from_global = transform_matrix(\n ref_pose_rec[\"translation\"], Quaternion(ref_pose_rec[\"rotation\"]), inverse=True\n )\n\n # Aggregate current and previous sweeps.\n sample_data_token = sample_rec[\"data\"][chan]\n current_sd_rec = lyftd.get(\"sample_data\", sample_data_token)\n for _ in range(num_sweeps):\n # Load up the pointcloud.\n current_pc = cls.from_file(lyftd.data_path / ('train_' + current_sd_rec[\"filename\"]))\n\n # Get past pose.\n current_pose_rec = lyftd.get(\"ego_pose\", current_sd_rec[\"ego_pose_token\"])\n global_from_car = transform_matrix(\n current_pose_rec[\"translation\"], Quaternion(current_pose_rec[\"rotation\"]), inverse=False\n )\n\n # Homogeneous transformation matrix from sensor coordinate frame to ego car frame.\n current_cs_rec = lyftd.get(\"calibrated_sensor\", current_sd_rec[\"calibrated_sensor_token\"])\n car_from_current = transform_matrix(\n current_cs_rec[\"translation\"], Quaternion(current_cs_rec[\"rotation\"]), inverse=False\n )\n\n # Fuse four transformation matrices into one and perform transform.\n trans_matrix = reduce(np.dot, [ref_from_car, car_from_global, global_from_car, car_from_current])\n current_pc.transform(trans_matrix)\n\n # Remove close points and add timevector.\n current_pc.remove_close(min_distance)\n time_lag = ref_time - 1e-6 * current_sd_rec[\"timestamp\"] # positive difference\n times = time_lag * np.ones((1, current_pc.nbr_points()))\n all_times = np.hstack((all_times, times))\n\n # Merge with key pc.\n all_pc.points = np.hstack((all_pc.points, current_pc.points))\n\n # Abort if there are no previous sweeps.\n if current_sd_rec[\"prev\"] == \"\":\n break\n else:\n current_sd_rec = lyftd.get(\"sample_data\", current_sd_rec[\"prev\"])\n\n return all_pc, all_times\n\n def nbr_points(self) -> int:\n \"\"\"Returns the number of points.\"\"\"\n return self.points.shape[1]\n\n def subsample(self, ratio: float) -> None:\n \"\"\"Sub-samples the pointcloud.\n Args:\n ratio: Fraction to keep.\n \"\"\"\n selected_ind = np.random.choice(np.arange(0, self.nbr_points()), size=int(self.nbr_points() * ratio))\n self.points = self.points[:, selected_ind]\n\n def remove_close(self, radius: float) -> None:\n \"\"\"Removes point too close within a certain radius from origin.\n Args:\n radius: Radius below which points are removed.\n Returns:\n \"\"\"\n x_filt = np.abs(self.points[0, :]) < radius\n y_filt = np.abs(self.points[1, :]) < radius\n not_close = np.logical_not(np.logical_and(x_filt, y_filt))\n self.points = self.points[:, not_close]\n\n def translate(self, x: np.ndarray) -> None:\n \"\"\"Applies a translation to the point cloud.\n Args:\n x: . Translation in x, y, z.\n \"\"\"\n for i in range(3):\n self.points[i, :] = self.points[i, :] + x[i]\n\n def rotate(self, rot_matrix: np.ndarray) -> None:\n \"\"\"Applies a rotation.\n Args:\n rot_matrix: . Rotation matrix.\n Returns:\n \"\"\"\n self.points[:3, :] = np.dot(rot_matrix, self.points[:3, :])\n\n def transform(self, transf_matrix: np.ndarray) -> None:\n \"\"\"Applies a homogeneous transform.\n Args:\n transf_matrix: transf_matrix: . Homogenous transformation matrix.\n \"\"\"\n self.points[:3, :] = transf_matrix.dot(np.vstack((self.points[:3, :], np.ones(self.nbr_points()))))[:3, :]\n\n def render_height(\n self,\n ax: Axes,\n view: np.ndarray = np.eye(4),\n x_lim: Tuple = (-20, 20),\n y_lim: Tuple = (-20, 20),\n marker_size: float = 1,\n ) -> None:\n \"\"\"Simple method that applies a transformation and then scatter plots the points colored by height (z-value).\n Args:\n ax: Axes on which to render the points.\n view: . Defines an arbitrary projection (n <= 4).\n x_lim: (min , max ). x range for plotting.\n y_lim: (min , max ). y range for plotting.\n marker_size: Marker size.\n \"\"\"\n self._render_helper(2, ax, view, x_lim, y_lim, marker_size)\n\n def render_intensity(\n self,\n ax: Axes,\n view: np.ndarray = np.eye(4),\n x_lim: Tuple = (-20, 20),\n y_lim: Tuple = (-20, 20),\n marker_size: float = 1,\n ) -> None:\n \"\"\"Very simple method that applies a transformation and then scatter plots the points colored by intensity.\n Args:\n ax: Axes on which to render the points.\n view: . Defines an arbitrary projection (n <= 4).\n x_lim: (min , max ).\n y_lim: (min , max ).\n marker_size: Marker size.\n Returns:\n \"\"\"\n self._render_helper(3, ax, view, x_lim, y_lim, marker_size)\n\n def _render_helper(\n self, color_channel: int, ax: Axes, view: np.ndarray, x_lim: Tuple, y_lim: Tuple, marker_size: float\n ) -> None:\n \"\"\"Helper function for rendering.\n Args:\n color_channel: Point channel to use as color.\n ax: Axes on which to render the points.\n view: . Defines an arbitrary projection (n <= 4).\n x_lim: (min , max ).\n y_lim: (min , max ).\n marker_size: Marker size.\n \"\"\"\n points = view_points(self.points[:3, :], view, normalize=False)\n ax.scatter(points[0, :], points[1, :], c=self.points[color_channel, :], s=marker_size)\n ax.set_xlim(x_lim[0], x_lim[1])\n ax.set_ylim(y_lim[0], y_lim[1])\n\n\nclass LidarPointCloud(PointCloud):\n @staticmethod\n def nbr_dims() -> int:\n \"\"\"Returns the number of dimensions.\n Returns: Number of dimensions.\n \"\"\"\n return 4\n\n @classmethod\n def from_file(cls, file_name: Path) -> \"LidarPointCloud\":\n \"\"\"Loads LIDAR data from binary numpy format. Data is stored as (x, y, z, intensity, ring index).\n Args:\n file_name: Path of the pointcloud file on disk.\n Returns: LidarPointCloud instance (x, y, z, intensity).\n \"\"\"\n\n assert file_name.suffix == \".bin\", \"Unsupported filetype {}\".format(file_name)\n\n scan = np.fromfile(str(file_name), dtype=np.float32)\n points = scan.reshape((-1, 5))[:, : cls.nbr_dims()]\n return cls(points.T)\n\n\nclass RadarPointCloud(PointCloud):\n\n # Class-level settings for radar pointclouds, see from_file().\n invalid_states = [0] # type: List[int]\n dynprop_states = range(7) # type: List[int] # Use [0, 2, 6] for moving objects only.\n ambig_states = [3] # type: List[int]\n\n @staticmethod\n def nbr_dims() -> int:\n \"\"\"Returns the number of dimensions.\n Returns: Number of dimensions.\n \"\"\"\n return 18\n\n @classmethod\n def from_file(\n cls,\n file_name: Path,\n invalid_states: List[int] = None,\n dynprop_states: List[int] = None,\n ambig_states: List[int] = None,\n ) -> \"RadarPointCloud\":\n \"\"\"Loads RADAR data from a Point Cloud Data file. See details below.\n Args:\n file_name: The path of the pointcloud file.\n invalid_states: Radar states to be kept. See details below.\n dynprop_states: Radar states to be kept. Use [0, 2, 6] for moving objects only. See details below.\n ambig_states: Radar states to be kept. See details below. To keep all radar returns,\n set each state filter to range(18).\n Returns: . Point cloud matrix with d dimensions and n points.\n Example of the header fields:\n # .PCD v0.7 - Point Cloud Data file format\n VERSION 0.7\n FIELDS x y z dyn_prop id rcs vx vy vx_comp vy_comp is_quality_valid ambig_\n state x_rms y_rms invalid_state pdh0 vx_rms vy_rms\n SIZE 4 4 4 1 2 4 4 4 4 4 1 1 1 1 1 1 1 1\n TYPE F F F I I F F F F F I I I I I I I I\n COUNT 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n WIDTH 125\n HEIGHT 1\n VIEWPOINT 0 0 0 1 0 0 0\n POINTS 125\n DATA binary\n Below some of the fields are explained in more detail:\n x is front, y is left\n vx, vy are the velocities in m/s.\n vx_comp, vy_comp are the velocities in m/s compensated by the ego motion.\n We recommend using the compensated velocities.\n invalid_state: state of Cluster validity state.\n (Invalid states)\n 0x01\tinvalid due to low RCS\n 0x02\tinvalid due to near-field artefact\n 0x03\tinvalid far range cluster because not confirmed in near range\n 0x05\treserved\n 0x06\tinvalid cluster due to high mirror probability\n 0x07\tInvalid cluster because outside sensor field of view\n 0x0d\treserved\n 0x0e\tinvalid cluster because it is a harmonics\n (Valid states)\n 0x00\tvalid\n 0x04\tvalid cluster with low RCS\n 0x08\tvalid cluster with azimuth correction due to elevation\n 0x09\tvalid cluster with high child probability\n 0x0a\tvalid cluster with high probability of being a 50 deg artefact\n 0x0b\tvalid cluster but no local maximum\n 0x0c\tvalid cluster with high artefact probability\n 0x0f\tvalid cluster with above 95m in near range\n 0x10\tvalid cluster with high multi-target probability\n 0x11\tvalid cluster with suspicious angle\n dynProp: Dynamic property of cluster to indicate if is moving or not.\n 0: moving\n 1: stationary\n 2: oncoming\n 3: stationary candidate\n 4: unknown\n 5: crossing stationary\n 6: crossing moving\n 7: stopped\n ambig_state: State of Doppler (radial velocity) ambiguity solution.\n 0: invalid\n 1: ambiguous\n 2: staggered ramp\n 3: unambiguous\n 4: stationary candidates\n pdh0: False alarm probability of cluster (i.e. probability of being an artefact caused\n by multipath or similar).\n 0: invalid\n 1: <25%\n 2: 50%\n 3: 75%\n 4: 90%\n 5: 99%\n 6: 99.9%\n 7: <=100%\n \"\"\"\n\n assert file_name.suffix == \".pcd\", \"Unsupported filetype {}\".format(file_name)\n\n meta = []\n with open(str(file_name), \"rb\") as f:\n for line in f:\n line = line.strip().decode(\"utf-8\")\n meta.append(line)\n if line.startswith(\"DATA\"):\n break\n\n data_binary = f.read()\n\n # Get the header rows and check if they appear as expected.\n assert meta[0].startswith(\"#\"), \"First line must be comment\"\n assert meta[1].startswith(\"VERSION\"), \"Second line must be VERSION\"\n sizes = meta[3].split(\" \")[1:]\n types = meta[4].split(\" \")[1:]\n counts = meta[5].split(\" \")[1:]\n width = int(meta[6].split(\" \")[1])\n height = int(meta[7].split(\" \")[1])\n data = meta[10].split(\" \")[1]\n feature_count = len(types)\n assert width > 0\n assert len([c for c in counts if c != c]) == 0, \"Error: COUNT not supported!\"\n assert height == 1, \"Error: height != 0 not supported!\"\n assert data == \"binary\"\n\n # Lookup table for how to decode the binaries.\n unpacking_lut = {\n \"F\": {2: \"e\", 4: \"f\", 8: \"d\"},\n \"I\": {1: \"b\", 2: \"h\", 4: \"i\", 8: \"q\"},\n \"U\": {1: \"B\", 2: \"H\", 4: \"I\", 8: \"Q\"},\n }\n types_str = \"\".join([unpacking_lut[t][int(s)] for t, s in zip(types, sizes)])\n\n # Decode each point.\n offset = 0\n point_count = width\n points = []\n for i in range(point_count):\n point = []\n for p in range(feature_count):\n start_p = offset\n end_p = start_p + int(sizes[p])\n assert end_p < len(data_binary)\n point_p = struct.unpack(types_str[p], data_binary[start_p:end_p])[0]\n point.append(point_p)\n offset = end_p\n points.append(point)\n\n # A NaN in the first point indicates an empty pointcloud.\n point = np.array(points[0])\n if np.any(np.isnan(point)):\n return cls(np.zeros((feature_count, 0)))\n\n # Convert to numpy matrix.\n points = np.array(points).transpose()\n\n # If no parameters are provided, use default settings.\n invalid_states = cls.invalid_states if invalid_states is None else invalid_states\n dynprop_states = cls.dynprop_states if dynprop_states is None else dynprop_states\n ambig_states = cls.ambig_states if ambig_states is None else ambig_states\n\n # Filter points with an invalid state.\n valid = [p in invalid_states for p in points[-4, :]]\n points = points[:, valid]\n\n # Filter by dynProp.\n valid = [p in dynprop_states for p in points[3, :]]\n points = points[:, valid]\n\n # Filter by ambig_state.\n valid = [p in ambig_states for p in points[11, :]]\n points = points[:, valid]\n\n return cls(points)\n\n\nclass Box:\n \"\"\" Simple data class representing a 3d box including, label, score and velocity. \"\"\"\n\n def __init__(\n self,\n center: List[float],\n size: List[float],\n orientation: Quaternion,\n label: int = np.nan,\n score: float = np.nan,\n velocity: Tuple = (np.nan, np.nan, np.nan),\n name: str = None,\n token: str = None,\n ):\n \"\"\"\n Args:\n center: Center of box given as x, y, z.\n size: Size of box in width, length, height.\n orientation: Box orientation.\n label: Integer label, optional.\n score: Classification score, optional.\n velocity: Box velocity in x, y, z direction.\n name: Box name, optional. Can be used e.g. for denote category name.\n token: Unique string identifier from DB.\n \"\"\"\n assert not np.any(np.isnan(center))\n assert not np.any(np.isnan(size))\n assert len(center) == 3\n assert len(size) == 3\n assert type(orientation) == Quaternion\n\n self.center = np.array(center)\n self.wlh = np.array(size)\n self.orientation = orientation\n self.label = int(label) if not np.isnan(label) else label\n self.score = float(score) if not np.isnan(score) else score\n self.velocity = np.array(velocity)\n self.name = name\n self.token = token\n\n def __eq__(self, other):\n center = np.allclose(self.center, other.center)\n wlh = np.allclose(self.wlh, other.wlh)\n orientation = np.allclose(self.orientation.elements, other.orientation.elements)\n label = (self.label == other.label) or (np.isnan(self.label) and np.isnan(other.label))\n score = (self.score == other.score) or (np.isnan(self.score) and np.isnan(other.score))\n vel = np.allclose(self.velocity, other.velocity) or (\n np.all(np.isnan(self.velocity)) and np.all(np.isnan(other.velocity))\n )\n\n return center and wlh and orientation and label and score and vel\n\n def __repr__(self):\n repr_str = (\n \"label: {}, score: {:.2f}, xyz: [{:.2f}, {:.2f}, {:.2f}], wlh: [{:.2f}, {:.2f}, {:.2f}], \"\n \"rot axis: [{:.2f}, {:.2f}, {:.2f}], ang(degrees): {:.2f}, ang(rad): {:.2f}, \"\n \"vel: {:.2f}, {:.2f}, {:.2f}, name: {}, token: {}\"\n )\n\n return repr_str.format(\n self.label,\n self.score,\n self.center[0],\n self.center[1],\n self.center[2],\n self.wlh[0],\n self.wlh[1],\n self.wlh[2],\n self.orientation.axis[0],\n self.orientation.axis[1],\n self.orientation.axis[2],\n self.orientation.degrees,\n self.orientation.radians,\n self.velocity[0],\n self.velocity[1],\n self.velocity[2],\n self.name,\n self.token,\n )\n\n @property\n def rotation_matrix(self) -> np.ndarray:\n \"\"\"Return a rotation matrix.\n Returns: . The box's rotation matrix.\n \"\"\"\n return self.orientation.rotation_matrix\n\n def translate(self, x: np.ndarray) -> None:\n \"\"\"Applies a translation.\n Args:\n x: . Translation in x, y, z direction.\n \"\"\"\n self.center += x\n\n def rotate(self, quaternion: Quaternion) -> None:\n \"\"\"Rotates box.\n Args:\n quaternion: Rotation to apply.\n \"\"\"\n self.center = np.dot(quaternion.rotation_matrix, self.center)\n self.orientation = quaternion * self.orientation\n self.velocity = np.dot(quaternion.rotation_matrix, self.velocity)\n\n def corners(self, wlh_factor: float = 1.0) -> np.ndarray:\n \"\"\"Returns the bounding box corners.\n Args:\n wlh_factor: Multiply width, length, height by a factor to scale the box.\n Returns: First four corners are the ones facing forward.\n The last four are the ones facing backwards.\n \"\"\"\n\n width, length, height = self.wlh * wlh_factor\n\n # 3D bounding box corners. (Convention: x points forward, y to the left, z up.)\n x_corners = length / 2 * np.array([1, 1, 1, 1, -1, -1, -1, -1])\n y_corners = width / 2 * np.array([1, -1, -1, 1, 1, -1, -1, 1])\n z_corners = height / 2 * np.array([1, 1, -1, -1, 1, 1, -1, -1])\n corners = np.vstack((x_corners, y_corners, z_corners))\n\n # Rotate\n corners = np.dot(self.orientation.rotation_matrix, corners)\n\n # Translate\n x, y, z = self.center\n corners[0, :] = corners[0, :] + x\n corners[1, :] = corners[1, :] + y\n corners[2, :] = corners[2, :] + z\n\n return corners\n\n def bottom_corners(self) -> np.ndarray:\n \"\"\"Returns the four bottom corners.\n Returns: . Bottom corners. First two face forward, last two face backwards.\n \"\"\"\n return self.corners()[:, [2, 3, 7, 6]]\n\n def render(\n self,\n axis: Axes,\n view: np.ndarray = np.eye(3),\n normalize: bool = False,\n colors: Tuple = (\"b\", \"r\", \"k\"),\n linewidth: float = 2,\n ):\n \"\"\"Renders the box in the provided Matplotlib axis.\n Args:\n axis: Axis onto which the box should be drawn.\n view: . Define a projection in needed (e.g. for drawing projection in an image).\n normalize: Whether to normalize the remaining coordinate.\n colors: (: 3). Valid Matplotlib colors ( or normalized RGB tuple) for front,\n back and sides.\n linewidth: Width in pixel of the box sides.\n \"\"\"\n corners = view_points(self.corners(), view, normalize=normalize)[:2, :]\n\n def draw_rect(selected_corners, color):\n prev = selected_corners[-1]\n for corner in selected_corners:\n axis.plot([prev[0], corner[0]], [prev[1], corner[1]], color=color, linewidth=linewidth)\n prev = corner\n\n # Draw the sides\n for i in range(4):\n axis.plot(\n [corners.T[i][0], corners.T[i + 4][0]],\n [corners.T[i][1], corners.T[i + 4][1]],\n color=colors[2],\n linewidth=linewidth,\n )\n\n # Draw front (first 4 corners) and rear (last 4 corners) rectangles(3d)/lines(2d)\n draw_rect(corners.T[:4], colors[0])\n draw_rect(corners.T[4:], colors[1])\n\n # Draw line indicating the front\n center_bottom_forward = np.mean(corners.T[2:4], axis=0)\n center_bottom = np.mean(corners.T[[2, 3, 7, 6]], axis=0)\n axis.plot(\n [center_bottom[0], center_bottom_forward[0]],\n [center_bottom[1], center_bottom_forward[1]],\n color=colors[0],\n linewidth=linewidth,\n )\n\n def render_cv2(\n self,\n image: np.ndarray,\n view: np.ndarray = np.eye(3),\n normalize: bool = False,\n colors: Tuple = ((0, 0, 255), (255, 0, 0), (155, 155, 155)),\n linewidth: int = 2,\n ) -> None:\n \"\"\"Renders box using OpenCV2.\n Args:\n image: . Image array. Channels are in BGR order.\n view: . Define a projection if needed (e.g. for drawing projection in an image).\n normalize: Whether to normalize the remaining coordinate.\n colors: ((R, G, B), (R, G, B), (R, G, B)). Colors for front, side & rear.\n linewidth: Linewidth for plot.\n Returns:\n \"\"\"\n corners = view_points(self.corners(), view, normalize=normalize)[:2, :]\n\n def draw_rect(selected_corners, color):\n prev = selected_corners[-1]\n for corner in selected_corners:\n cv2.line(image, (int(prev[0]), int(prev[1])), (int(corner[0]), int(corner[1])), color, linewidth)\n prev = corner\n\n # Draw the sides\n for i in range(4):\n cv2.line(\n image,\n (int(corners.T[i][0]), int(corners.T[i][1])),\n (int(corners.T[i + 4][0]), int(corners.T[i + 4][1])),\n colors[2][::-1],\n linewidth,\n )\n\n # Draw front (first 4 corners) and rear (last 4 corners) rectangles(3d)/lines(2d)\n draw_rect(corners.T[:4], colors[0][::-1])\n draw_rect(corners.T[4:], colors[1][::-1])\n\n # Draw line indicating the front\n center_bottom_forward = np.mean(corners.T[2:4], axis=0)\n center_bottom = np.mean(corners.T[[2, 3, 7, 6]], axis=0)\n cv2.line(\n image,\n (int(center_bottom[0]), int(center_bottom[1])),\n (int(center_bottom_forward[0]), int(center_bottom_forward[1])),\n colors[0][::-1],\n linewidth,\n )\n\n def copy(self) -> \"Box\":\n \"\"\" Create a copy of self.\n Returns: A copy.\n \"\"\"\n return copy.deepcopy(self)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:01:03.804593Z","iopub.execute_input":"2021-05-22T12:01:03.804900Z","iopub.status.idle":"2021-05-22T12:01:03.913070Z","shell.execute_reply.started":"2021-05-22T12:01:03.804849Z","shell.execute_reply":"2021-05-22T12:01:03.912084Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Créez une classe appelée *LyftDataset* pour conditionner le jeu de données sous une forme pratique.\n#### (click CODE )","metadata":{}},{"cell_type":"code","source":"# Lyft Dataset SDK dev-kit.\n# Code written by Oscar Beijbom, 2018.\n# Licensed under the Creative Commons [see licence.txt]\n# Modified by Vladimir Iglovikov 2019.\n\nPYTHON_VERSION = sys.version_info[0]\n\nif not PYTHON_VERSION == 3:\n raise ValueError(\"LyftDataset sdk only supports Python version 3.\")\n\n\nclass LyftDataset:\n \"\"\"Database class for Lyft Dataset to help query and retrieve information from the database.\"\"\"\n\n def __init__(self, data_path: str, json_path: str, verbose: bool = True, map_resolution: float = 0.1):\n \"\"\"Loads database and creates reverse indexes and shortcuts.\n Args:\n data_path: Path to the tables and data.\n json_path: Path to the folder with json files\n verbose: Whether to print status messages during load.\n map_resolution: Resolution of maps (meters).\n \"\"\"\n\n self.data_path = Path(data_path).expanduser().absolute()\n self.json_path = Path(json_path)\n\n self.table_names = [\n \"category\",\n \"attribute\",\n \"visibility\",\n \"instance\",\n \"sensor\",\n \"calibrated_sensor\",\n \"ego_pose\",\n \"log\",\n \"scene\",\n \"sample\",\n \"sample_data\",\n \"sample_annotation\",\n \"map\",\n ]\n\n start_time = time.time()\n\n # Explicitly assign tables to help the IDE determine valid class members.\n self.category = self.__load_table__(\"category\")\n self.attribute = self.__load_table__(\"attribute\")\n self.visibility = self.__load_table__(\"visibility\")\n self.instance = self.__load_table__(\"instance\")\n self.sensor = self.__load_table__(\"sensor\")\n self.calibrated_sensor = self.__load_table__(\"calibrated_sensor\")\n self.ego_pose = self.__load_table__(\"ego_pose\")\n self.log = self.__load_table__(\"log\")\n self.scene = self.__load_table__(\"scene\")\n self.sample = self.__load_table__(\"sample\")\n self.sample_data = self.__load_table__(\"sample_data\")\n self.sample_annotation = self.__load_table__(\"sample_annotation\")\n self.map = self.__load_table__(\"map\")\n\n # Initialize map mask for each map record.\n for map_record in self.map:\n map_record[\"mask\"] = MapMask(self.data_path / 'train_maps/map_raster_palo_alto.png', resolution=map_resolution)\n\n if verbose:\n for table in self.table_names:\n print(\"{} {},\".format(len(getattr(self, table)), table))\n print(\"Done loading in {:.1f} seconds.\\n======\".format(time.time() - start_time))\n\n # Make reverse indexes for common lookups.\n self.__make_reverse_index__(verbose)\n\n # Initialize LyftDatasetExplorer class\n self.explorer = LyftDatasetExplorer(self)\n\n def __load_table__(self, table_name) -> dict:\n \"\"\"Loads a table.\"\"\"\n with open(str(self.json_path.joinpath(\"{}.json\".format(table_name)))) as f:\n table = json.load(f)\n return table\n\n def __make_reverse_index__(self, verbose: bool) -> None:\n \"\"\"De-normalizes database to create reverse indices for common cases.\n Args:\n verbose: Whether to print outputs.\n \"\"\"\n\n start_time = time.time()\n if verbose:\n print(\"Reverse indexing ...\")\n\n # Store the mapping from token to table index for each table.\n self._token2ind = dict()\n for table in self.table_names:\n self._token2ind[table] = dict()\n\n for ind, member in enumerate(getattr(self, table)):\n self._token2ind[table][member[\"token\"]] = ind\n\n # Decorate (adds short-cut) sample_annotation table with for category name.\n for record in self.sample_annotation:\n inst = self.get(\"instance\", record[\"instance_token\"])\n record[\"category_name\"] = self.get(\"category\", inst[\"category_token\"])[\"name\"]\n\n # Decorate (adds short-cut) sample_data with sensor information.\n for record in self.sample_data:\n cs_record = self.get(\"calibrated_sensor\", record[\"calibrated_sensor_token\"])\n sensor_record = self.get(\"sensor\", cs_record[\"sensor_token\"])\n record[\"sensor_modality\"] = sensor_record[\"modality\"]\n record[\"channel\"] = sensor_record[\"channel\"]\n\n # Reverse-index samples with sample_data and annotations.\n for record in self.sample:\n record[\"data\"] = {}\n record[\"anns\"] = []\n\n for record in self.sample_data:\n if record[\"is_key_frame\"]:\n sample_record = self.get(\"sample\", record[\"sample_token\"])\n sample_record[\"data\"][record[\"channel\"]] = record[\"token\"]\n\n for ann_record in self.sample_annotation:\n sample_record = self.get(\"sample\", ann_record[\"sample_token\"])\n sample_record[\"anns\"].append(ann_record[\"token\"])\n\n # Add reverse indices from log records to map records.\n if \"log_tokens\" not in self.map[0].keys():\n raise Exception(\"Error: log_tokens not in map table. This code is not compatible with the teaser dataset.\")\n log_to_map = dict()\n for map_record in self.map:\n for log_token in map_record[\"log_tokens\"]:\n log_to_map[log_token] = map_record[\"token\"]\n for log_record in self.log:\n log_record[\"map_token\"] = log_to_map[log_record[\"token\"]]\n\n if verbose:\n print(\"Done reverse indexing in {:.1f} seconds.\\n======\".format(time.time() - start_time))\n\n def get(self, table_name: str, token: str) -> dict:\n \"\"\"Returns a record from table in constant runtime.\n Args:\n table_name: Table name.\n token: Token of the record.\n Returns: Table record.\n \"\"\"\n\n assert table_name in self.table_names, \"Table {} not found\".format(table_name)\n\n return getattr(self, table_name)[self.getind(table_name, token)]\n\n def getind(self, table_name: str, token: str) -> int:\n \"\"\"Returns the index of the record in a table in constant runtime.\n Args:\n table_name: Table name.\n token: The index of the record in table, table is an array.\n Returns:\n \"\"\"\n return self._token2ind[table_name][token]\n\n def field2token(self, table_name: str, field: str, query) -> List[str]:\n \"\"\"Query all records for a certain field value, and returns the tokens for the matching records.\n Runs in linear time.\n Args:\n table_name: Table name.\n field: Field name.\n query: Query to match against. Needs to type match the content of the query field.\n Returns: List of tokens for the matching records.\n \"\"\"\n matches = []\n for member in getattr(self, table_name):\n if member[field] == query:\n matches.append(member[\"token\"])\n return matches\n\n def get_sample_data_path(self, sample_data_token: str) -> Path:\n \"\"\"Returns the path to a sample_data.\n Args:\n sample_data_token:\n Returns:\n \"\"\"\n\n sd_record = self.get(\"sample_data\", sample_data_token)\n return self.data_path / sd_record[\"filename\"]\n\n def get_sample_data(\n self,\n sample_data_token: str,\n box_vis_level: BoxVisibility = BoxVisibility.ANY,\n selected_anntokens: List[str] = None,\n flat_vehicle_coordinates: bool = False,\n ) -> Tuple[Path, List[Box], np.array]:\n \"\"\"Returns the data path as well as all annotations related to that sample_data.\n The boxes are transformed into the current sensor's coordinate frame.\n Args:\n sample_data_token: Sample_data token.\n box_vis_level: If sample_data is an image, this sets required visibility for boxes.\n selected_anntokens: If provided only return the selected annotation.\n flat_vehicle_coordinates: Instead of current sensor's coordinate frame, use vehicle frame which is\n aligned to z-plane in world\n Returns: (data_path, boxes, camera_intrinsic )\n \"\"\"\n\n # Retrieve sensor & pose records\n sd_record = self.get(\"sample_data\", sample_data_token)\n cs_record = self.get(\"calibrated_sensor\", sd_record[\"calibrated_sensor_token\"])\n sensor_record = self.get(\"sensor\", cs_record[\"sensor_token\"])\n pose_record = self.get(\"ego_pose\", sd_record[\"ego_pose_token\"])\n\n data_path = self.get_sample_data_path(sample_data_token)\n\n if sensor_record[\"modality\"] == \"camera\":\n cam_intrinsic = np.array(cs_record[\"camera_intrinsic\"])\n imsize = (sd_record[\"width\"], sd_record[\"height\"])\n else:\n cam_intrinsic = None\n imsize = None\n\n # Retrieve all sample annotations and map to sensor coordinate system.\n if selected_anntokens is not None:\n boxes = list(map(self.get_box, selected_anntokens))\n else:\n boxes = self.get_boxes(sample_data_token)\n\n # Make list of Box objects including coord system transforms.\n box_list = []\n for box in boxes:\n if flat_vehicle_coordinates:\n # Move box to ego vehicle coord system parallel to world z plane\n ypr = Quaternion(pose_record[\"rotation\"]).yaw_pitch_roll\n yaw = ypr[0]\n\n box.translate(-np.array(pose_record[\"translation\"]))\n box.rotate(Quaternion(scalar=np.cos(yaw / 2), vector=[0, 0, np.sin(yaw / 2)]).inverse)\n\n else:\n # Move box to ego vehicle coord system\n box.translate(-np.array(pose_record[\"translation\"]))\n box.rotate(Quaternion(pose_record[\"rotation\"]).inverse)\n\n # Move box to sensor coord system\n box.translate(-np.array(cs_record[\"translation\"]))\n box.rotate(Quaternion(cs_record[\"rotation\"]).inverse)\n\n if sensor_record[\"modality\"] == \"camera\" and not box_in_image(\n box, cam_intrinsic, imsize, vis_level=box_vis_level\n ):\n continue\n\n box_list.append(box)\n\n return data_path, box_list, cam_intrinsic\n\n def get_box(self, sample_annotation_token: str) -> Box:\n \"\"\"Instantiates a Box class from a sample annotation record.\n Args:\n sample_annotation_token: Unique sample_annotation identifier.\n Returns:\n \"\"\"\n record = self.get(\"sample_annotation\", sample_annotation_token)\n return Box(\n record[\"translation\"],\n record[\"size\"],\n Quaternion(record[\"rotation\"]),\n name=record[\"category_name\"],\n token=record[\"token\"],\n )\n\n def get_boxes(self, sample_data_token: str) -> List[Box]:\n \"\"\"Instantiates Boxes for all annotation for a particular sample_data record. If the sample_data is a\n keyframe, this returns the annotations for that sample. But if the sample_data is an intermediate\n sample_data, a linear interpolation is applied to estimate the location of the boxes at the time the\n sample_data was captured.\n Args:\n sample_data_token: Unique sample_data identifier.\n Returns:\n \"\"\"\n\n # Retrieve sensor & pose records\n sd_record = self.get(\"sample_data\", sample_data_token)\n curr_sample_record = self.get(\"sample\", sd_record[\"sample_token\"])\n\n if curr_sample_record[\"prev\"] == \"\" or sd_record[\"is_key_frame\"]:\n # If no previous annotations available, or if sample_data is keyframe just return the current ones.\n boxes = list(map(self.get_box, curr_sample_record[\"anns\"]))\n\n else:\n prev_sample_record = self.get(\"sample\", curr_sample_record[\"prev\"])\n\n curr_ann_recs = [self.get(\"sample_annotation\", token) for token in curr_sample_record[\"anns\"]]\n prev_ann_recs = [self.get(\"sample_annotation\", token) for token in prev_sample_record[\"anns\"]]\n\n # Maps instance tokens to prev_ann records\n prev_inst_map = {entry[\"instance_token\"]: entry for entry in prev_ann_recs}\n\n t0 = prev_sample_record[\"timestamp\"]\n t1 = curr_sample_record[\"timestamp\"]\n t = sd_record[\"timestamp\"]\n\n # There are rare situations where the timestamps in the DB are off so ensure that t0 < t < t1.\n t = max(t0, min(t1, t))\n\n boxes = []\n for curr_ann_rec in curr_ann_recs:\n\n if curr_ann_rec[\"instance_token\"] in prev_inst_map:\n # If the annotated instance existed in the previous frame, interpolate center & orientation.\n prev_ann_rec = prev_inst_map[curr_ann_rec[\"instance_token\"]]\n\n # Interpolate center.\n center = [\n np.interp(t, [t0, t1], [c0, c1])\n for c0, c1 in zip(prev_ann_rec[\"translation\"], curr_ann_rec[\"translation\"])\n ]\n\n # Interpolate orientation.\n rotation = Quaternion.slerp(\n q0=Quaternion(prev_ann_rec[\"rotation\"]),\n q1=Quaternion(curr_ann_rec[\"rotation\"]),\n amount=(t - t0) / (t1 - t0),\n )\n\n box = Box(\n center,\n curr_ann_rec[\"size\"],\n rotation,\n name=curr_ann_rec[\"category_name\"],\n token=curr_ann_rec[\"token\"],\n )\n else:\n # If not, simply grab the current annotation.\n box = self.get_box(curr_ann_rec[\"token\"])\n\n boxes.append(box)\n return boxes\n\n def box_velocity(self, sample_annotation_token: str, max_time_diff: float = 1.5) -> np.ndarray:\n \"\"\"Estimate the velocity for an annotation.\n If possible, we compute the centered difference between the previous and next frame.\n Otherwise we use the difference between the current and previous/next frame.\n If the velocity cannot be estimated, values are set to np.nan.\n Args:\n sample_annotation_token: Unique sample_annotation identifier.\n max_time_diff: Max allowed time diff between consecutive samples that are used to estimate velocities.\n Returns: . Velocity in x/y/z direction in m/s.\n \"\"\"\n\n current = self.get(\"sample_annotation\", sample_annotation_token)\n has_prev = current[\"prev\"] != \"\"\n has_next = current[\"next\"] != \"\"\n\n # Cannot estimate velocity for a single annotation.\n if not has_prev and not has_next:\n return np.array([np.nan, np.nan, np.nan])\n\n if has_prev:\n first = self.get(\"sample_annotation\", current[\"prev\"])\n else:\n first = current\n\n if has_next:\n last = self.get(\"sample_annotation\", current[\"next\"])\n else:\n last = current\n\n pos_last = np.array(last[\"translation\"])\n pos_first = np.array(first[\"translation\"])\n pos_diff = pos_last - pos_first\n\n time_last = 1e-6 * self.get(\"sample\", last[\"sample_token\"])[\"timestamp\"]\n time_first = 1e-6 * self.get(\"sample\", first[\"sample_token\"])[\"timestamp\"]\n time_diff = time_last - time_first\n\n if has_next and has_prev:\n # If doing centered difference, allow for up to double the max_time_diff.\n max_time_diff *= 2\n\n if time_diff > max_time_diff:\n # If time_diff is too big, don't return an estimate.\n return np.array([np.nan, np.nan, np.nan])\n else:\n return pos_diff / time_diff\n\n def list_categories(self) -> None:\n self.explorer.list_categories()\n\n def list_attributes(self) -> None:\n self.explorer.list_attributes()\n\n def list_scenes(self) -> None:\n self.explorer.list_scenes()\n\n def list_sample(self, sample_token: str) -> None:\n self.explorer.list_sample(sample_token)\n\n def render_pointcloud_in_image(\n self,\n sample_token: str,\n dot_size: int = 5,\n pointsensor_channel: str = \"LIDAR_TOP\",\n camera_channel: str = \"CAM_FRONT\",\n out_path: str = None,\n ) -> None:\n self.explorer.render_pointcloud_in_image(\n sample_token,\n dot_size,\n pointsensor_channel=pointsensor_channel,\n camera_channel=camera_channel,\n out_path=out_path,\n )\n\n def render_sample(\n self,\n sample_token: str,\n box_vis_level: BoxVisibility = BoxVisibility.ANY,\n nsweeps: int = 1,\n out_path: str = None,\n ) -> None:\n self.explorer.render_sample(sample_token, box_vis_level, nsweeps=nsweeps, out_path=out_path)\n\n def render_sample_data(\n self,\n sample_data_token: str,\n with_anns: bool = True,\n box_vis_level: BoxVisibility = BoxVisibility.ANY,\n axes_limit: float = 40,\n ax: Axes = None,\n nsweeps: int = 1,\n out_path: str = None,\n underlay_map: bool = False,\n ) -> None:\n return self.explorer.render_sample_data(\n sample_data_token,\n with_anns,\n box_vis_level,\n axes_limit,\n ax,\n num_sweeps=nsweeps,\n out_path=out_path,\n underlay_map=underlay_map,\n )\n\n def render_annotation(\n self,\n sample_annotation_token: str,\n margin: float = 10,\n view: np.ndarray = np.eye(4),\n box_vis_level: BoxVisibility = BoxVisibility.ANY,\n out_path: str = None,\n ) -> None:\n self.explorer.render_annotation(sample_annotation_token, margin, view, box_vis_level, out_path)\n\n def render_instance(self, instance_token: str, out_path: str = None) -> None:\n self.explorer.render_instance(instance_token, out_path=out_path)\n\n def render_scene(self, scene_token: str, freq: float = 10, imwidth: int = 640, out_path: str = None) -> None:\n self.explorer.render_scene(scene_token, freq, image_width=imwidth, out_path=out_path)\n\n def render_scene_channel(\n self,\n scene_token: str,\n channel: str = \"CAM_FRONT\",\n freq: float = 10,\n imsize: Tuple[float, float] = (640, 360),\n out_path: str = None,\n ) -> None:\n self.explorer.render_scene_channel(\n scene_token=scene_token, channel=channel, freq=freq, image_size=imsize, out_path=out_path\n )\n\n def render_egoposes_on_map(self, log_location: str, scene_tokens: List = None, out_path: str = None) -> None:\n self.explorer.render_egoposes_on_map(log_location, scene_tokens, out_path=out_path)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:03:42.509165Z","iopub.execute_input":"2021-05-22T12:03:42.509477Z","iopub.status.idle":"2021-05-22T12:03:42.588547Z","shell.execute_reply.started":"2021-05-22T12:03:42.509427Z","shell.execute_reply":"2021-05-22T12:03:42.587797Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Créez une autre classe appelée *LyftDatasetExplorer* qui nous aidera à visualiser les données.\n#### (click CODE on the right side)","metadata":{}},{"cell_type":"code","source":"class LyftDatasetExplorer:\n \"\"\"Helper class to list and visualize Lyft Dataset data. These are meant to serve as tutorials and templates for\n working with the data.\"\"\"\n\n def __init__(self, lyftd: LyftDataset):\n self.lyftd = lyftd\n\n @staticmethod\n def get_color(category_name: str) -> Tuple[int, int, int]:\n \"\"\"Provides the default colors based on the category names.\n This method works for the general Lyft Dataset categories, as well as the Lyft Dataset detection categories.\n Args:\n category_name:\n Returns:\n \"\"\"\n if \"bicycle\" in category_name or \"motorcycle\" in category_name:\n return 255, 61, 99 # Red\n elif \"vehicle\" in category_name or category_name in [\"bus\", \"car\", \"construction_vehicle\", \"trailer\", \"truck\"]:\n return 255, 158, 0 # Orange\n elif \"pedestrian\" in category_name:\n return 0, 0, 230 # Blue\n elif \"cone\" in category_name or \"barrier\" in category_name:\n return 0, 0, 0 # Black\n else:\n return 255, 0, 255 # Magenta\n\n def list_categories(self) -> None:\n \"\"\"Print categories, counts and stats.\"\"\"\n\n print(\"Category stats\")\n\n # Add all annotations\n categories = dict()\n for record in self.lyftd.sample_annotation:\n if record[\"category_name\"] not in categories:\n categories[record[\"category_name\"]] = []\n categories[record[\"category_name\"]].append(record[\"size\"] + [record[\"size\"][1] / record[\"size\"][0]])\n\n # Print stats\n for name, stats in sorted(categories.items()):\n stats = np.array(stats)\n print(\n \"{:27} n={:5}, width={:5.2f}\\u00B1{:.2f}, len={:5.2f}\\u00B1{:.2f}, height={:5.2f}\\u00B1{:.2f}, \"\n \"lw_aspect={:5.2f}\\u00B1{:.2f}\".format(\n name[:27],\n stats.shape[0],\n np.mean(stats[:, 0]),\n np.std(stats[:, 0]),\n np.mean(stats[:, 1]),\n np.std(stats[:, 1]),\n np.mean(stats[:, 2]),\n np.std(stats[:, 2]),\n np.mean(stats[:, 3]),\n np.std(stats[:, 3]),\n )\n )\n\n def list_attributes(self) -> None:\n \"\"\"Prints attributes and counts.\"\"\"\n attribute_counts = dict()\n for record in self.lyftd.sample_annotation:\n for attribute_token in record[\"attribute_tokens\"]:\n att_name = self.lyftd.get(\"attribute\", attribute_token)[\"name\"]\n if att_name not in attribute_counts:\n attribute_counts[att_name] = 0\n attribute_counts[att_name] += 1\n\n for name, count in sorted(attribute_counts.items()):\n print(\"{}: {}\".format(name, count))\n\n def list_scenes(self) -> None:\n \"\"\" Lists all scenes with some meta data. \"\"\"\n\n def ann_count(record):\n count = 0\n sample = self.lyftd.get(\"sample\", record[\"first_sample_token\"])\n while not sample[\"next\"] == \"\":\n count += len(sample[\"anns\"])\n sample = self.lyftd.get(\"sample\", sample[\"next\"])\n return count\n\n recs = [\n (self.lyftd.get(\"sample\", record[\"first_sample_token\"])[\"timestamp\"], record)\n for record in self.lyftd.scene\n ]\n\n for start_time, record in sorted(recs):\n start_time = self.lyftd.get(\"sample\", record[\"first_sample_token\"])[\"timestamp\"] / 1000000\n length_time = self.lyftd.get(\"sample\", record[\"last_sample_token\"])[\"timestamp\"] / 1000000 - start_time\n location = self.lyftd.get(\"log\", record[\"log_token\"])[\"location\"]\n desc = record[\"name\"] + \", \" + record[\"description\"]\n if len(desc) > 55:\n desc = desc[:51] + \"...\"\n if len(location) > 18:\n location = location[:18]\n\n print(\n \"{:16} [{}] {:4.0f}s, {}, #anns:{}\".format(\n desc,\n datetime.utcfromtimestamp(start_time).strftime(\"%y-%m-%d %H:%M:%S\"),\n length_time,\n location,\n ann_count(record),\n )\n )\n\n def list_sample(self, sample_token: str) -> None:\n \"\"\"Prints sample_data tokens and sample_annotation tokens related to the sample_token.\"\"\"\n\n sample_record = self.lyftd.get(\"sample\", sample_token)\n print(\"Sample: {}\\n\".format(sample_record[\"token\"]))\n for sd_token in sample_record[\"data\"].values():\n sd_record = self.lyftd.get(\"sample_data\", sd_token)\n print(\n \"sample_data_token: {}, mod: {}, channel: {}\".format(\n sd_token, sd_record[\"sensor_modality\"], sd_record[\"channel\"]\n )\n )\n print(\"\")\n for ann_token in sample_record[\"anns\"]:\n ann_record = self.lyftd.get(\"sample_annotation\", ann_token)\n print(\"sample_annotation_token: {}, category: {}\".format(ann_record[\"token\"], ann_record[\"category_name\"]))\n\n def map_pointcloud_to_image(self, pointsensor_token: str, camera_token: str) -> Tuple:\n \"\"\"Given a point sensor (lidar/radar) token and camera sample_data token, load point-cloud and map it to\n the image plane.\n Args:\n pointsensor_token: Lidar/radar sample_data token.\n camera_token: Camera sample_data token.\n Returns: (pointcloud , coloring , image ).\n \"\"\"\n\n cam = self.lyftd.get(\"sample_data\", camera_token)\n pointsensor = self.lyftd.get(\"sample_data\", pointsensor_token)\n pcl_path = self.lyftd.data_path / ('train_' + pointsensor[\"filename\"])\n if pointsensor[\"sensor_modality\"] == \"lidar\":\n pc = LidarPointCloud.from_file(pcl_path)\n else:\n pc = RadarPointCloud.from_file(pcl_path)\n im = Image.open(str(self.lyftd.data_path / ('train_' + cam[\"filename\"])))\n\n # Points live in the point sensor frame. So they need to be transformed via global to the image plane.\n # First step: transform the point-cloud to the ego vehicle frame for the timestamp of the sweep.\n cs_record = self.lyftd.get(\"calibrated_sensor\", pointsensor[\"calibrated_sensor_token\"])\n pc.rotate(Quaternion(cs_record[\"rotation\"]).rotation_matrix)\n pc.translate(np.array(cs_record[\"translation\"]))\n\n # Second step: transform to the global frame.\n poserecord = self.lyftd.get(\"ego_pose\", pointsensor[\"ego_pose_token\"])\n pc.rotate(Quaternion(poserecord[\"rotation\"]).rotation_matrix)\n pc.translate(np.array(poserecord[\"translation\"]))\n\n # Third step: transform into the ego vehicle frame for the timestamp of the image.\n poserecord = self.lyftd.get(\"ego_pose\", cam[\"ego_pose_token\"])\n pc.translate(-np.array(poserecord[\"translation\"]))\n pc.rotate(Quaternion(poserecord[\"rotation\"]).rotation_matrix.T)\n\n # Fourth step: transform into the camera.\n cs_record = self.lyftd.get(\"calibrated_sensor\", cam[\"calibrated_sensor_token\"])\n pc.translate(-np.array(cs_record[\"translation\"]))\n pc.rotate(Quaternion(cs_record[\"rotation\"]).rotation_matrix.T)\n\n # Fifth step: actually take a \"picture\" of the point cloud.\n # Grab the depths (camera frame z axis points away from the camera).\n depths = pc.points[2, :]\n\n # Retrieve the color from the depth.\n coloring = depths\n\n # Take the actual picture (matrix multiplication with camera-matrix + renormalization).\n points = view_points(pc.points[:3, :], np.array(cs_record[\"camera_intrinsic\"]), normalize=True)\n\n # Remove points that are either outside or behind the camera. Leave a margin of 1 pixel for aesthetic reasons.\n mask = np.ones(depths.shape[0], dtype=bool)\n mask = np.logical_and(mask, depths > 0)\n mask = np.logical_and(mask, points[0, :] > 1)\n mask = np.logical_and(mask, points[0, :] < im.size[0] - 1)\n mask = np.logical_and(mask, points[1, :] > 1)\n mask = np.logical_and(mask, points[1, :] < im.size[1] - 1)\n points = points[:, mask]\n coloring = coloring[mask]\n\n return points, coloring, im\n\n def render_pointcloud_in_image(\n self,\n sample_token: str,\n dot_size: int = 2,\n pointsensor_channel: str = \"LIDAR_TOP\",\n camera_channel: str = \"CAM_FRONT\",\n out_path: str = None,\n ) -> None:\n \"\"\"Scatter-plots a point-cloud on top of image.\n Args:\n sample_token: Sample token.\n dot_size: Scatter plot dot size.\n pointsensor_channel: RADAR or LIDAR channel name, e.g. 'LIDAR_TOP'.\n camera_channel: Camera channel name, e.g. 'CAM_FRONT'.\n out_path: Optional path to save the rendered figure to disk.\n Returns:\n \"\"\"\n sample_record = self.lyftd.get(\"sample\", sample_token)\n\n # Here we just grab the front camera and the point sensor.\n pointsensor_token = sample_record[\"data\"][pointsensor_channel]\n camera_token = sample_record[\"data\"][camera_channel]\n\n points, coloring, im = self.map_pointcloud_to_image(pointsensor_token, camera_token)\n plt.figure(figsize=(9, 16))\n plt.imshow(im)\n plt.scatter(points[0, :], points[1, :], c=coloring, s=dot_size)\n plt.axis(\"off\")\n\n if out_path is not None:\n plt.savefig(out_path)\n\n def render_sample(\n self, token: str, box_vis_level: BoxVisibility = BoxVisibility.ANY, nsweeps: int = 1, out_path: str = None\n ) -> None:\n \"\"\"Render all LIDAR and camera sample_data in sample along with annotations.\n Args:\n token: Sample token.\n box_vis_level: If sample_data is an image, this sets required visibility for boxes.\n nsweeps: Number of sweeps for lidar and radar.\n out_path: Optional path to save the rendered figure to disk.\n Returns:\n \"\"\"\n record = self.lyftd.get(\"sample\", token)\n\n # Separate RADAR from LIDAR and vision.\n radar_data = {}\n nonradar_data = {}\n for channel, token in record[\"data\"].items():\n sd_record = self.lyftd.get(\"sample_data\", token)\n sensor_modality = sd_record[\"sensor_modality\"]\n if sensor_modality in [\"lidar\", \"camera\"]:\n nonradar_data[channel] = token\n else:\n radar_data[channel] = token\n\n num_radar_plots = 1 if len(radar_data) > 0 else 0\n\n # Create plots.\n n = num_radar_plots + len(nonradar_data)\n cols = 2\n fig, axes = plt.subplots(int(np.ceil(n / cols)), cols, figsize=(16, 24))\n\n if len(radar_data) > 0:\n # Plot radar into a single subplot.\n ax = axes[0, 0]\n for i, (_, sd_token) in enumerate(radar_data.items()):\n self.render_sample_data(\n sd_token, with_anns=i == 0, box_vis_level=box_vis_level, ax=ax, num_sweeps=nsweeps\n )\n ax.set_title(\"Fused RADARs\")\n\n # Plot camera and lidar in separate subplots.\n for (_, sd_token), ax in zip(nonradar_data.items(), axes.flatten()[num_radar_plots:]):\n self.render_sample_data(sd_token, box_vis_level=box_vis_level, ax=ax, num_sweeps=nsweeps)\n\n axes.flatten()[-1].axis(\"off\")\n plt.tight_layout()\n fig.subplots_adjust(wspace=0, hspace=0)\n\n if out_path is not None:\n plt.savefig(out_path)\n\n def render_ego_centric_map(self, sample_data_token: str, axes_limit: float = 40, ax: Axes = None) -> None:\n \"\"\"Render map centered around the associated ego pose.\n Args:\n sample_data_token: Sample_data token.\n axes_limit: Axes limit measured in meters.\n ax: Axes onto which to render.\n \"\"\"\n\n def crop_image(image: np.array, x_px: int, y_px: int, axes_limit_px: int) -> np.array:\n x_min = int(x_px - axes_limit_px)\n x_max = int(x_px + axes_limit_px)\n y_min = int(y_px - axes_limit_px)\n y_max = int(y_px + axes_limit_px)\n\n cropped_image = image[y_min:y_max, x_min:x_max]\n\n return cropped_image\n\n sd_record = self.lyftd.get(\"sample_data\", sample_data_token)\n\n # Init axes.\n if ax is None:\n _, ax = plt.subplots(1, 1, figsize=(9, 9))\n\n sample = self.lyftd.get(\"sample\", sd_record[\"sample_token\"])\n scene = self.lyftd.get(\"scene\", sample[\"scene_token\"])\n log = self.lyftd.get(\"log\", scene[\"log_token\"])\n map = self.lyftd.get(\"map\", log[\"map_token\"])\n map_mask = map[\"mask\"]\n\n pose = self.lyftd.get(\"ego_pose\", sd_record[\"ego_pose_token\"])\n pixel_coords = map_mask.to_pixel_coords(pose[\"translation\"][0], pose[\"translation\"][1])\n\n scaled_limit_px = int(axes_limit * (1.0 / map_mask.resolution))\n mask_raster = map_mask.mask()\n\n cropped = crop_image(mask_raster, pixel_coords[0], pixel_coords[1], int(scaled_limit_px * math.sqrt(2)))\n\n ypr_rad = Quaternion(pose[\"rotation\"]).yaw_pitch_roll\n yaw_deg = -math.degrees(ypr_rad[0])\n\n rotated_cropped = np.array(Image.fromarray(cropped).rotate(yaw_deg))\n ego_centric_map = crop_image(\n rotated_cropped, rotated_cropped.shape[1] / 2, rotated_cropped.shape[0] / 2, scaled_limit_px\n )\n ax.imshow(\n ego_centric_map, extent=[-axes_limit, axes_limit, -axes_limit, axes_limit], cmap=\"gray\", vmin=0, vmax=150\n )\n\n def render_sample_data(\n self,\n sample_data_token: str,\n with_anns: bool = True,\n box_vis_level: BoxVisibility = BoxVisibility.ANY,\n axes_limit: float = 40,\n ax: Axes = None,\n num_sweeps: int = 1,\n out_path: str = None,\n underlay_map: bool = False,\n ):\n \"\"\"Render sample data onto axis.\n Args:\n sample_data_token: Sample_data token.\n with_anns: Whether to draw annotations.\n box_vis_level: If sample_data is an image, this sets required visibility for boxes.\n axes_limit: Axes limit for lidar and radar (measured in meters).\n ax: Axes onto which to render.\n num_sweeps: Number of sweeps for lidar and radar.\n out_path: Optional path to save the rendered figure to disk.\n underlay_map: When set to true, LIDAR data is plotted onto the map. This can be slow.\n \"\"\"\n\n # Get sensor modality.\n sd_record = self.lyftd.get(\"sample_data\", sample_data_token)\n sensor_modality = sd_record[\"sensor_modality\"]\n\n if sensor_modality == \"lidar\":\n # Get boxes in lidar frame.\n _, boxes, _ = self.lyftd.get_sample_data(\n sample_data_token, box_vis_level=box_vis_level, flat_vehicle_coordinates=True\n )\n\n # Get aggregated point cloud in lidar frame.\n sample_rec = self.lyftd.get(\"sample\", sd_record[\"sample_token\"])\n chan = sd_record[\"channel\"]\n ref_chan = \"LIDAR_TOP\"\n pc, times = LidarPointCloud.from_file_multisweep(\n self.lyftd, sample_rec, chan, ref_chan, num_sweeps=num_sweeps\n )\n\n # Compute transformation matrices for lidar point cloud\n cs_record = self.lyftd.get(\"calibrated_sensor\", sd_record[\"calibrated_sensor_token\"])\n pose_record = self.lyftd.get(\"ego_pose\", sd_record[\"ego_pose_token\"])\n vehicle_from_sensor = np.eye(4)\n vehicle_from_sensor[:3, :3] = Quaternion(cs_record[\"rotation\"]).rotation_matrix\n vehicle_from_sensor[:3, 3] = cs_record[\"translation\"]\n\n ego_yaw = Quaternion(pose_record[\"rotation\"]).yaw_pitch_roll[0]\n rot_vehicle_flat_from_vehicle = np.dot(\n Quaternion(scalar=np.cos(ego_yaw / 2), vector=[0, 0, np.sin(ego_yaw / 2)]).rotation_matrix,\n Quaternion(pose_record[\"rotation\"]).inverse.rotation_matrix,\n )\n\n vehicle_flat_from_vehicle = np.eye(4)\n vehicle_flat_from_vehicle[:3, :3] = rot_vehicle_flat_from_vehicle\n\n # Init axes.\n if ax is None:\n _, ax = plt.subplots(1, 1, figsize=(9, 9))\n\n if underlay_map:\n self.render_ego_centric_map(sample_data_token=sample_data_token, axes_limit=axes_limit, ax=ax)\n\n # Show point cloud.\n points = view_points(\n pc.points[:3, :], np.dot(vehicle_flat_from_vehicle, vehicle_from_sensor), normalize=False\n )\n dists = np.sqrt(np.sum(pc.points[:2, :] ** 2, axis=0))\n colors = np.minimum(1, dists / axes_limit / np.sqrt(2))\n ax.scatter(points[0, :], points[1, :], c=colors, s=0.2)\n\n # Show ego vehicle.\n ax.plot(0, 0, \"x\", color=\"red\")\n\n # Show boxes.\n if with_anns:\n for box in boxes:\n c = np.array(self.get_color(box.name)) / 255.0\n box.render(ax, view=np.eye(4), colors=(c, c, c))\n\n # Limit visible range.\n ax.set_xlim(-axes_limit, axes_limit)\n ax.set_ylim(-axes_limit, axes_limit)\n\n elif sensor_modality == \"radar\":\n # Get boxes in lidar frame.\n sample_rec = self.lyftd.get(\"sample\", sd_record[\"sample_token\"])\n lidar_token = sample_rec[\"data\"][\"LIDAR_TOP\"]\n _, boxes, _ = self.lyftd.get_sample_data(lidar_token, box_vis_level=box_vis_level)\n\n # Get aggregated point cloud in lidar frame.\n # The point cloud is transformed to the lidar frame for visualization purposes.\n chan = sd_record[\"channel\"]\n ref_chan = \"LIDAR_TOP\"\n pc, times = RadarPointCloud.from_file_multisweep(\n self.lyftd, sample_rec, chan, ref_chan, num_sweeps=num_sweeps\n )\n\n # Transform radar velocities (x is front, y is left), as these are not transformed when loading the point\n # cloud.\n radar_cs_record = self.lyftd.get(\"calibrated_sensor\", sd_record[\"calibrated_sensor_token\"])\n lidar_sd_record = self.lyftd.get(\"sample_data\", lidar_token)\n lidar_cs_record = self.lyftd.get(\"calibrated_sensor\", lidar_sd_record[\"calibrated_sensor_token\"])\n velocities = pc.points[8:10, :] # Compensated velocity\n velocities = np.vstack((velocities, np.zeros(pc.points.shape[1])))\n velocities = np.dot(Quaternion(radar_cs_record[\"rotation\"]).rotation_matrix, velocities)\n velocities = np.dot(Quaternion(lidar_cs_record[\"rotation\"]).rotation_matrix.T, velocities)\n velocities[2, :] = np.zeros(pc.points.shape[1])\n\n # Init axes.\n if ax is None:\n _, ax = plt.subplots(1, 1, figsize=(9, 9))\n\n # Show point cloud.\n points = view_points(pc.points[:3, :], np.eye(4), normalize=False)\n dists = np.sqrt(np.sum(pc.points[:2, :] ** 2, axis=0))\n colors = np.minimum(1, dists / axes_limit / np.sqrt(2))\n sc = ax.scatter(points[0, :], points[1, :], c=colors, s=3)\n\n # Show velocities.\n points_vel = view_points(pc.points[:3, :] + velocities, np.eye(4), normalize=False)\n max_delta = 10\n deltas_vel = points_vel - points\n deltas_vel = 3 * deltas_vel # Arbitrary scaling\n deltas_vel = np.clip(deltas_vel, -max_delta, max_delta) # Arbitrary clipping\n colors_rgba = sc.to_rgba(colors)\n for i in range(points.shape[1]):\n ax.arrow(points[0, i], points[1, i], deltas_vel[0, i], deltas_vel[1, i], color=colors_rgba[i])\n\n # Show ego vehicle.\n ax.plot(0, 0, \"x\", color=\"black\")\n\n # Show boxes.\n if with_anns:\n for box in boxes:\n c = np.array(self.get_color(box.name)) / 255.0\n box.render(ax, view=np.eye(4), colors=(c, c, c))\n\n # Limit visible range.\n ax.set_xlim(-axes_limit, axes_limit)\n ax.set_ylim(-axes_limit, axes_limit)\n\n elif sensor_modality == \"camera\":\n # Load boxes and image.\n data_path, boxes, camera_intrinsic = self.lyftd.get_sample_data(\n sample_data_token, box_vis_level=box_vis_level\n )\n\n data = Image.open(str(data_path)[:len(str(data_path)) - 46] + 'train_images/' +\\\n str(data_path)[len(str(data_path)) - 39 : len(str(data_path))])\n\n # Init axes.\n if ax is None:\n _, ax = plt.subplots(1, 1, figsize=(9, 16))\n\n # Show image.\n ax.imshow(data)\n\n # Show boxes.\n if with_anns:\n for box in boxes:\n c = np.array(self.get_color(box.name)) / 255.0\n box.render(ax, view=camera_intrinsic, normalize=True, colors=(c, c, c))\n\n # Limit visible range.\n ax.set_xlim(0, data.size[0])\n ax.set_ylim(data.size[1], 0)\n\n else:\n raise ValueError(\"Error: Unknown sensor modality!\")\n\n ax.axis(\"off\")\n ax.set_title(sd_record[\"channel\"])\n ax.set_aspect(\"equal\")\n\n if out_path is not None:\n num = len([name for name in os.listdir(out_path)])\n out_path = out_path + str(num).zfill(5) + \"_\" + sample_data_token + \".png\"\n plt.savefig(out_path)\n plt.close(\"all\")\n return out_path\n\n def render_annotation(\n self,\n ann_token: str,\n margin: float = 10,\n view: np.ndarray = np.eye(4),\n box_vis_level: BoxVisibility = BoxVisibility.ANY,\n out_path: str = None,\n ) -> None:\n \"\"\"Render selected annotation.\n Args:\n ann_token: Sample_annotation token.\n margin: How many meters in each direction to include in LIDAR view.\n view: LIDAR view point.\n box_vis_level: If sample_data is an image, this sets required visibility for boxes.\n out_path: Optional path to save the rendered figure to disk.\n \"\"\"\n\n ann_record = self.lyftd.get(\"sample_annotation\", ann_token)\n sample_record = self.lyftd.get(\"sample\", ann_record[\"sample_token\"])\n assert \"LIDAR_TOP\" in sample_record[\"data\"].keys(), \"No LIDAR_TOP in data, cant render\"\n\n fig, axes = plt.subplots(1, 2, figsize=(18, 9))\n\n # Figure out which camera the object is fully visible in (this may return nothing)\n boxes, cam = [], []\n cams = [key for key in sample_record[\"data\"].keys() if \"CAM\" in key]\n for cam in cams:\n _, boxes, _ = self.lyftd.get_sample_data(\n sample_record[\"data\"][cam], box_vis_level=box_vis_level, selected_anntokens=[ann_token]\n )\n if len(boxes) > 0:\n break # We found an image that matches. Let's abort.\n assert len(boxes) > 0, \"Could not find image where annotation is visible. Try using e.g. BoxVisibility.ANY.\"\n assert len(boxes) < 2, \"Found multiple annotations. Something is wrong!\"\n\n cam = sample_record[\"data\"][cam]\n\n # Plot LIDAR view\n lidar = sample_record[\"data\"][\"LIDAR_TOP\"]\n data_path, boxes, camera_intrinsic = self.lyftd.get_sample_data(lidar, selected_anntokens=[ann_token])\n LidarPointCloud.from_file(Path(str(data_path)[:len(str(data_path)) - 46] + 'train_lidar/' +\\\n str(data_path)[len(str(data_path)) - 40 : len(str(data_path))])).render_height(axes[0], view=view)\n for box in boxes:\n c = np.array(self.get_color(box.name)) / 255.0\n box.render(axes[0], view=view, colors=(c, c, c))\n corners = view_points(boxes[0].corners(), view, False)[:2, :]\n axes[0].set_xlim([np.min(corners[0, :]) - margin, np.max(corners[0, :]) + margin])\n axes[0].set_ylim([np.min(corners[1, :]) - margin, np.max(corners[1, :]) + margin])\n axes[0].axis(\"off\")\n axes[0].set_aspect(\"equal\")\n\n # Plot CAMERA view\n data_path, boxes, camera_intrinsic = self.lyftd.get_sample_data(cam, selected_anntokens=[ann_token])\n im = Image.open(Path(str(data_path)[:len(str(data_path)) - 46] + 'train_images/' +\\\n str(data_path)[len(str(data_path)) - 39 : len(str(data_path))]))\n axes[1].imshow(im)\n axes[1].set_title(self.lyftd.get(\"sample_data\", cam)[\"channel\"])\n axes[1].axis(\"off\")\n axes[1].set_aspect(\"equal\")\n for box in boxes:\n c = np.array(self.get_color(box.name)) / 255.0\n box.render(axes[1], view=camera_intrinsic, normalize=True, colors=(c, c, c))\n\n if out_path is not None:\n plt.savefig(out_path)\n\n def render_instance(self, instance_token: str, out_path: str = None) -> None:\n \"\"\"Finds the annotation of the given instance that is closest to the vehicle, and then renders it.\n Args:\n instance_token: The instance token.\n out_path: Optional path to save the rendered figure to disk.\n Returns:\n \"\"\"\n\n ann_tokens = self.lyftd.field2token(\"sample_annotation\", \"instance_token\", instance_token)\n closest = [np.inf, None]\n for ann_token in ann_tokens:\n ann_record = self.lyftd.get(\"sample_annotation\", ann_token)\n sample_record = self.lyftd.get(\"sample\", ann_record[\"sample_token\"])\n sample_data_record = self.lyftd.get(\"sample_data\", sample_record[\"data\"][\"LIDAR_TOP\"])\n pose_record = self.lyftd.get(\"ego_pose\", sample_data_record[\"ego_pose_token\"])\n dist = np.linalg.norm(np.array(pose_record[\"translation\"]) - np.array(ann_record[\"translation\"]))\n if dist < closest[0]:\n closest[0] = dist\n closest[1] = ann_token\n self.render_annotation(closest[1], out_path=out_path)\n\n def render_scene(self, scene_token: str, freq: float = 10, image_width: int = 640, out_path: Path = None) -> None:\n \"\"\"Renders a full scene with all surround view camera channels.\n Args:\n scene_token: Unique identifier of scene to render.\n freq: Display frequency (Hz).\n image_width: Width of image to render. Height is determined automatically to preserve aspect ratio.\n out_path: Optional path to write a video file of the rendered frames.\n \"\"\"\n\n if out_path is not None:\n assert out_path.suffix == \".avi\"\n\n # Get records from DB.\n scene_rec = self.lyftd.get(\"scene\", scene_token)\n first_sample_rec = self.lyftd.get(\"sample\", scene_rec[\"first_sample_token\"])\n last_sample_rec = self.lyftd.get(\"sample\", scene_rec[\"last_sample_token\"])\n\n channels = [\"CAM_FRONT_LEFT\", \"CAM_FRONT\", \"CAM_FRONT_RIGHT\", \"CAM_BACK_LEFT\", \"CAM_BACK\", \"CAM_BACK_RIGHT\"]\n\n horizontal_flip = [\"CAM_BACK_LEFT\", \"CAM_BACK\", \"CAM_BACK_RIGHT\"] # Flip these for aesthetic reasons.\n\n time_step = 1 / freq * 1e6 # Time-stamps are measured in micro-seconds.\n\n window_name = \"{}\".format(scene_rec[\"name\"])\n cv2.namedWindow(window_name)\n cv2.moveWindow(window_name, 0, 0)\n\n # Load first sample_data record for each channel\n current_recs = {} # Holds the current record to be displayed by channel.\n prev_recs = {} # Hold the previous displayed record by channel.\n for channel in channels:\n current_recs[channel] = self.lyftd.get(\"sample_data\", first_sample_rec[\"data\"][channel])\n prev_recs[channel] = None\n\n # We assume that the resolution is the same for all surround view cameras.\n image_height = int(image_width * current_recs[channels[0]][\"height\"] / current_recs[channels[0]][\"width\"])\n image_size = (image_width, image_height)\n\n # Set some display parameters\n layout = {\n \"CAM_FRONT_LEFT\": (0, 0),\n \"CAM_FRONT\": (image_size[0], 0),\n \"CAM_FRONT_RIGHT\": (2 * image_size[0], 0),\n \"CAM_BACK_LEFT\": (0, image_size[1]),\n \"CAM_BACK\": (image_size[0], image_size[1]),\n \"CAM_BACK_RIGHT\": (2 * image_size[0], image_size[1]),\n }\n\n canvas = np.ones((2 * image_size[1], 3 * image_size[0], 3), np.uint8)\n if out_path is not None:\n fourcc = cv2.VideoWriter_fourcc(*\"MJPG\")\n out = cv2.VideoWriter(out_path, fourcc, freq, canvas.shape[1::-1])\n else:\n out = None\n\n current_time = first_sample_rec[\"timestamp\"]\n\n while current_time < last_sample_rec[\"timestamp\"]:\n\n current_time += time_step\n\n # For each channel, find first sample that has time > current_time.\n for channel, sd_rec in current_recs.items():\n while sd_rec[\"timestamp\"] < current_time and sd_rec[\"next\"] != \"\":\n sd_rec = self.lyftd.get(\"sample_data\", sd_rec[\"next\"])\n current_recs[channel] = sd_rec\n\n # Now add to canvas\n for channel, sd_rec in current_recs.items():\n\n # Only update canvas if we have not already rendered this one.\n if not sd_rec == prev_recs[channel]:\n\n # Get annotations and params from DB.\n image_path, boxes, camera_intrinsic = self.lyftd.get_sample_data(\n sd_rec[\"token\"], box_vis_level=BoxVisibility.ANY\n )\n\n # Load and render\n if not image_path.exists():\n raise Exception(\"Error: Missing image %s\" % image_path)\n im = cv2.imread(str(image_path))\n for box in boxes:\n c = self.get_color(box.name)\n box.render_cv2(im, view=camera_intrinsic, normalize=True, colors=(c, c, c))\n\n im = cv2.resize(im, image_size)\n if channel in horizontal_flip:\n im = im[:, ::-1, :]\n\n canvas[\n layout[channel][1] : layout[channel][1] + image_size[1],\n layout[channel][0] : layout[channel][0] + image_size[0],\n :,\n ] = im\n\n prev_recs[channel] = sd_rec # Store here so we don't render the same image twice.\n\n # Show updated canvas.\n cv2.imshow(window_name, canvas)\n if out_path is not None:\n out.write(canvas)\n\n key = cv2.waitKey(1) # Wait a very short time (1 ms).\n\n if key == 32: # if space is pressed, pause.\n key = cv2.waitKey()\n\n if key == 27: # if ESC is pressed, exit.\n cv2.destroyAllWindows()\n break\n\n cv2.destroyAllWindows()\n if out_path is not None:\n out.release()\n\n def render_scene_channel(\n self,\n scene_token: str,\n channel: str = \"CAM_FRONT\",\n freq: float = 10,\n image_size: Tuple[float, float] = (640, 360),\n out_path: Path = None,\n ) -> None:\n \"\"\"Renders a full scene for a particular camera channel.\n Args:\n scene_token: Unique identifier of scene to render.\n channel: Channel to render.\n freq: Display frequency (Hz).\n image_size: Size of image to render. The larger the slower this will run.\n out_path: Optional path to write a video file of the rendered frames.\n \"\"\"\n\n valid_channels = [\n \"CAM_FRONT_LEFT\",\n \"CAM_FRONT\",\n \"CAM_FRONT_RIGHT\",\n \"CAM_BACK_LEFT\",\n \"CAM_BACK\",\n \"CAM_BACK_RIGHT\",\n ]\n\n assert image_size[0] / image_size[1] == 16 / 9, \"Aspect ratio should be 16/9.\"\n assert channel in valid_channels, \"Input channel {} not valid.\".format(channel)\n\n if out_path is not None:\n assert out_path.suffix == \".avi\"\n\n # Get records from DB\n scene_rec = self.lyftd.get(\"scene\", scene_token)\n sample_rec = self.lyftd.get(\"sample\", scene_rec[\"first_sample_token\"])\n sd_rec = self.lyftd.get(\"sample_data\", sample_rec[\"data\"][channel])\n\n # Open CV init\n name = \"{}: {} (Space to pause, ESC to exit)\".format(scene_rec[\"name\"], channel)\n cv2.namedWindow(name)\n cv2.moveWindow(name, 0, 0)\n\n if out_path is not None:\n fourcc = cv2.VideoWriter_fourcc(*\"MJPG\")\n out = cv2.VideoWriter(out_path, fourcc, freq, image_size)\n else:\n out = None\n\n has_more_frames = True\n while has_more_frames:\n\n # Get data from DB\n image_path, boxes, camera_intrinsic = self.lyftd.get_sample_data(\n sd_rec[\"token\"], box_vis_level=BoxVisibility.ANY\n )\n\n # Load and render\n if not image_path.exists():\n raise Exception(\"Error: Missing image %s\" % image_path)\n image = cv2.imread(str(image_path))\n for box in boxes:\n c = self.get_color(box.name)\n box.render_cv2(image, view=camera_intrinsic, normalize=True, colors=(c, c, c))\n\n # Render\n image = cv2.resize(image, image_size)\n cv2.imshow(name, image)\n if out_path is not None:\n out.write(image)\n\n key = cv2.waitKey(10) # Images stored at approx 10 Hz, so wait 10 ms.\n if key == 32: # If space is pressed, pause.\n key = cv2.waitKey()\n\n if key == 27: # if ESC is pressed, exit\n cv2.destroyAllWindows()\n break\n\n if not sd_rec[\"next\"] == \"\":\n sd_rec = self.lyftd.get(\"sample_data\", sd_rec[\"next\"])\n else:\n has_more_frames = False\n\n cv2.destroyAllWindows()\n if out_path is not None:\n out.release()\n\n def render_egoposes_on_map(\n self,\n log_location: str,\n scene_tokens: List = None,\n close_dist: float = 100,\n color_fg: Tuple[int, int, int] = (167, 174, 186),\n color_bg: Tuple[int, int, int] = (255, 255, 255),\n out_path: Path = None,\n ) -> None:\n \"\"\"Renders ego poses a the map. These can be filtered by location or scene.\n Args:\n log_location: Name of the location, e.g. \"singapore-onenorth\", \"singapore-hollandvillage\",\n \"singapore-queenstown' and \"boston-seaport\".\n scene_tokens: Optional list of scene tokens.\n close_dist: Distance in meters for an ego pose to be considered within range of another ego pose.\n color_fg: Color of the semantic prior in RGB format (ignored if map is RGB).\n color_bg: Color of the non-semantic prior in RGB format (ignored if map is RGB).\n out_path: Optional path to save the rendered figure to disk.\n Returns:\n \"\"\"\n\n # Get logs by location\n log_tokens = [l[\"token\"] for l in self.lyftd.log if l[\"location\"] == log_location]\n assert len(log_tokens) > 0, \"Error: This split has 0 scenes for location %s!\" % log_location\n\n # Filter scenes\n scene_tokens_location = [e[\"token\"] for e in self.lyftd.scene if e[\"log_token\"] in log_tokens]\n if scene_tokens is not None:\n scene_tokens_location = [t for t in scene_tokens_location if t in scene_tokens]\n if len(scene_tokens_location) == 0:\n print(\"Warning: Found 0 valid scenes for location %s!\" % log_location)\n\n map_poses = []\n map_mask = None\n\n print(\"Adding ego poses to map...\")\n for scene_token in tqdm(scene_tokens_location):\n\n # Get records from the database.\n scene_record = self.lyftd.get(\"scene\", scene_token)\n log_record = self.lyftd.get(\"log\", scene_record[\"log_token\"])\n map_record = self.lyftd.get(\"map\", log_record[\"map_token\"])\n map_mask = map_record[\"mask\"]\n\n # For each sample in the scene, store the ego pose.\n sample_tokens = self.lyftd.field2token(\"sample\", \"scene_token\", scene_token)\n for sample_token in sample_tokens:\n sample_record = self.lyftd.get(\"sample\", sample_token)\n\n # Poses are associated with the sample_data. Here we use the lidar sample_data.\n sample_data_record = self.lyftd.get(\"sample_data\", sample_record[\"data\"][\"LIDAR_TOP\"])\n pose_record = self.lyftd.get(\"ego_pose\", sample_data_record[\"ego_pose_token\"])\n\n # Calculate the pose on the map and append\n map_poses.append(\n np.concatenate(\n map_mask.to_pixel_coords(pose_record[\"translation\"][0], pose_record[\"translation\"][1])\n )\n )\n\n # Compute number of close ego poses.\n print(\"Creating plot...\")\n map_poses = np.vstack(map_poses)\n dists = sklearn.metrics.pairwise.euclidean_distances(map_poses * map_mask.resolution)\n close_poses = np.sum(dists < close_dist, axis=0)\n\n if len(np.array(map_mask.mask()).shape) == 3 and np.array(map_mask.mask()).shape[2] == 3:\n # RGB Colour maps\n mask = map_mask.mask()\n else:\n # Monochrome maps\n # Set the colors for the mask.\n mask = Image.fromarray(map_mask.mask())\n mask = np.array(mask)\n\n maskr = color_fg[0] * np.ones(np.shape(mask), dtype=np.uint8)\n maskr[mask == 0] = color_bg[0]\n maskg = color_fg[1] * np.ones(np.shape(mask), dtype=np.uint8)\n maskg[mask == 0] = color_bg[1]\n maskb = color_fg[2] * np.ones(np.shape(mask), dtype=np.uint8)\n maskb[mask == 0] = color_bg[2]\n mask = np.concatenate(\n (np.expand_dims(maskr, axis=2), np.expand_dims(maskg, axis=2), np.expand_dims(maskb, axis=2)), axis=2\n )\n\n # Plot.\n _, ax = plt.subplots(1, 1, figsize=(10, 10))\n ax.imshow(mask)\n title = \"Number of ego poses within {}m in {}\".format(close_dist, log_location)\n ax.set_title(title, color=\"k\")\n sc = ax.scatter(map_poses[:, 0], map_poses[:, 1], s=10, c=close_poses)\n color_bar = plt.colorbar(sc, fraction=0.025, pad=0.04)\n plt.rcParams[\"figure.facecolor\"] = \"black\"\n color_bar_ticklabels = plt.getp(color_bar.ax.axes, \"yticklabels\")\n plt.setp(color_bar_ticklabels, color=\"k\")\n plt.rcParams[\"figure.facecolor\"] = \"white\" # Reset for future plots\n\n if out_path is not None:\n plt.savefig(out_path)\n plt.close(\"all\")","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:04:17.432735Z","iopub.execute_input":"2021-05-22T12:04:17.433108Z","iopub.status.idle":"2021-05-22T12:04:17.615247Z","shell.execute_reply.started":"2021-05-22T12:04:17.433049Z","shell.execute_reply":"2021-05-22T12:04:17.614435Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Créer un objet *LyftDataset* à partir de l'ensemble de données existant.","metadata":{}},{"cell_type":"code","source":"lyft_dataset = LyftDataset(data_path=DATA_PATH, json_path=DATA_PATH+'train_data')","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","execution":{"iopub.status.busy":"2021-05-22T12:05:15.518440Z","iopub.execute_input":"2021-05-22T12:05:15.518736Z","iopub.status.idle":"2021-05-22T12:05:39.556990Z","shell.execute_reply.started":"2021-05-22T12:05:15.518683Z","shell.execute_reply":"2021-05-22T12:05:39.556078Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"L'ensemble de données se compose de plusieurs scences, qui sont des clips de 25-45 secondes d'images de données LiDAR d'une voiture à conduite autonome. Nous pouvons extraire et examiner la première séquence comme suit :","metadata":{}},{"cell_type":"code","source":"my_scene = lyft_dataset.scene[179]\nmy_scene","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:08:25.767166Z","iopub.execute_input":"2021-05-22T12:08:25.767479Z","iopub.status.idle":"2021-05-22T12:08:25.774149Z","shell.execute_reply.started":"2021-05-22T12:08:25.767428Z","shell.execute_reply":"2021-05-22T12:08:25.773316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Comme on peut le voir ci-dessus, chaque scène est constituée d'un dictionnaire d'informations. Il y a quelques ID de jetons et un nom pour chaque scène. Le \"nom\" correspond au nom du fichier de données LiDAR associé à la scène donnée. Ici, le nom du fichier LiDAR est :\n\n**host-a101-lidar0-1241893239199111666-1241893264098084346**.","metadata":{}},{"cell_type":"markdown","source":"*Note:* Vous pouvez lister toutes les scènes de l'ensemble de données en utilisant:\n\n**lyft_dataset.list_scenes()**","metadata":{}},{"cell_type":"code","source":"#lyft_dataset.list_scenes()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:09:46.449702Z","iopub.execute_input":"2021-05-22T12:09:46.449988Z","iopub.status.idle":"2021-05-22T12:09:46.453649Z","shell.execute_reply.started":"2021-05-22T12:09:46.449941Z","shell.execute_reply":"2021-05-22T12:09:46.452641Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Maintenant, visualisons certaines des images et des données LiDAR.","metadata":{}},{"cell_type":"markdown","source":"### Créer une fonction pour rendre les scences dans l'ensemble de données","metadata":{}},{"cell_type":"code","source":"def render_scene(index):\n my_scene = lyft_dataset.scene[index]\n my_sample_token = my_scene[\"first_sample_token\"]\n lyft_dataset.render_sample(my_sample_token)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:10:10.108534Z","iopub.execute_input":"2021-05-22T12:10:10.108831Z","iopub.status.idle":"2021-05-22T12:10:10.113312Z","shell.execute_reply.started":"2021-05-22T12:10:10.108782Z","shell.execute_reply":"2021-05-22T12:10:10.112212Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Rendu de la première scène (image et LiDAR)","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"render_scene(179)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:10:19.968308Z","iopub.execute_input":"2021-05-22T12:10:19.968619Z","iopub.status.idle":"2021-05-22T12:10:27.731419Z","shell.execute_reply.started":"2021-05-22T12:10:19.968571Z","shell.execute_reply":"2021-05-22T12:10:27.730699Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Rendu de la deuxième scène (image et LiDAR)","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"render_scene(1)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:11:37.023321Z","iopub.execute_input":"2021-05-22T12:11:37.023606Z","iopub.status.idle":"2021-05-22T12:11:44.932323Z","shell.execute_reply.started":"2021-05-22T12:11:37.023562Z","shell.execute_reply":"2021-05-22T12:11:44.931298Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Les images ci-dessus montrent les données d'image et LiDAR collectées à l'aide des caméras et des capteurs sous différents angles de la voiture. Les boîtes jaunes autour des objets dans les images sont les boîtes de délimitation ou les volumes de délimitation qui montrent l'emplacement des objets dans l'image.","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Notez qu'un échantillon est un instantané des données à un moment donné de la scène. Par conséquent, chaque scène est composée de plusieurs échantillons.","metadata":{}},{"cell_type":"markdown","source":"Maintenant, extrayons le premier échantillon de la première scence.Now, let us extract the first sample sample from the first scence.","metadata":{}},{"cell_type":"code","source":"my_sample_token = my_scene[\"first_sample_token\"]\nmy_sample = lyft_dataset.get('sample', my_sample_token)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:13:20.711949Z","iopub.execute_input":"2021-05-22T12:13:20.712246Z","iopub.status.idle":"2021-05-22T12:13:20.716105Z","shell.execute_reply.started":"2021-05-22T12:13:20.712189Z","shell.execute_reply":"2021-05-22T12:13:20.715316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"my_sample","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"*Note :* Vous pouvez lister tous les échantillons d'une scène en utilisant:\n\n**lyft_dataset.list_sample(my_sample['token'])**","metadata":{}},{"cell_type":"code","source":"lyft_dataset.list_sample(my_sample['token'])","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:14:32.855838Z","iopub.execute_input":"2021-05-22T12:14:32.856119Z","iopub.status.idle":"2021-05-22T12:14:32.866072Z","shell.execute_reply.started":"2021-05-22T12:14:32.856073Z","shell.execute_reply":"2021-05-22T12:14:32.865126Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Ensuite, nous allons rendre un nuage de points pour un échantillon d'image dans l'ensemble de données. Le nuage de points est essentiellement un ensemble de contours qui représentent la distance de divers objets mesurée par le LiDAR. Fondamentalement, le LiDAR utilise des faisceaux lumineux pour mesurer la distance de divers objets (comme nous l'avons vu précédemment) et cette information de distance peut être visualisée comme un ensemble de contours 3D. Les couleurs de ces lignes de contour représentent la distance. Les lignes de contour violettes et bleues plus foncées représentent les objets les plus proches et les lignes vertes et jaunes plus claires représentent les objets les plus éloignés. Fondamentalement, plus la longueur d'onde de la couleur de la ligne de contour est élevée, plus l'objet est éloigné de la caméra.","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lyft_dataset.render_pointcloud_in_image(sample_token = my_sample[\"token\"],\n dot_size = 1,\n camera_channel = 'CAM_FRONT')","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:15:53.535006Z","iopub.execute_input":"2021-05-22T12:15:53.535314Z","iopub.status.idle":"2021-05-22T12:15:54.444892Z","shell.execute_reply.started":"2021-05-22T12:15:53.535242Z","shell.execute_reply":"2021-05-22T12:15:54.438462Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Nous pouvons également imprimer toutes les annotations sur l'ensemble des données d'un échantillon donné, comme indiqué ci-dessous :","metadata":{}},{"cell_type":"code","source":"my_sample['data']","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:16:29.533371Z","iopub.execute_input":"2021-05-22T12:16:29.533671Z","iopub.status.idle":"2021-05-22T12:16:29.539715Z","shell.execute_reply.started":"2021-05-22T12:16:29.533623Z","shell.execute_reply":"2021-05-22T12:16:29.538687Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can also render the image data from particular sensors, as follows:","metadata":{}},{"cell_type":"markdown","source":"### Front Camera\nImages from the front camera","metadata":{}},{"cell_type":"code","source":"sensor_channel = 'CAM_FRONT'\nmy_sample_data = lyft_dataset.get('sample_data', my_sample['data'][sensor_channel])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:16:59.088089Z","iopub.execute_input":"2021-05-22T12:16:59.088390Z","iopub.status.idle":"2021-05-22T12:16:59.092588Z","shell.execute_reply.started":"2021-05-22T12:16:59.088339Z","shell.execute_reply":"2021-05-22T12:16:59.091421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lyft_dataset.render_sample_data(my_sample_data['token'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:17:04.669472Z","iopub.execute_input":"2021-05-22T12:17:04.669791Z","iopub.status.idle":"2021-05-22T12:17:05.287050Z","shell.execute_reply.started":"2021-05-22T12:17:04.669729Z","shell.execute_reply":"2021-05-22T12:17:05.286357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Back Camera\nImages from the back camera","metadata":{}},{"cell_type":"code","source":"sensor_channel = 'CAM_BACK'\nmy_sample_data = lyft_dataset.get('sample_data', my_sample['data'][sensor_channel])\nlyft_dataset.render_sample_data(my_sample_data['token'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:17:23.689033Z","iopub.execute_input":"2021-05-22T12:17:23.689347Z","iopub.status.idle":"2021-05-22T12:17:24.296978Z","shell.execute_reply.started":"2021-05-22T12:17:23.689274Z","shell.execute_reply":"2021-05-22T12:17:24.296121Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Front-Left Camera\nImages from the front-left camera","metadata":{}},{"cell_type":"code","source":"sensor_channel = 'CAM_FRONT_LEFT'\nmy_sample_data = lyft_dataset.get('sample_data', my_sample['data'][sensor_channel])\nlyft_dataset.render_sample_data(my_sample_data['token'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:17:33.653347Z","iopub.execute_input":"2021-05-22T12:17:33.653638Z","iopub.status.idle":"2021-05-22T12:17:34.077080Z","shell.execute_reply.started":"2021-05-22T12:17:33.653592Z","shell.execute_reply":"2021-05-22T12:17:34.076173Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Front-Right Camera\nImages from the front-right camera","metadata":{}},{"cell_type":"code","source":"sensor_channel = 'CAM_FRONT_RIGHT'\nmy_sample_data = lyft_dataset.get('sample_data', my_sample['data'][sensor_channel])\nlyft_dataset.render_sample_data(my_sample_data['token'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:17:41.849215Z","iopub.execute_input":"2021-05-22T12:17:41.849561Z","iopub.status.idle":"2021-05-22T12:17:42.254779Z","shell.execute_reply.started":"2021-05-22T12:17:41.849510Z","shell.execute_reply":"2021-05-22T12:17:42.254105Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Back-Left Camera\nImages from the back-left camera","metadata":{}},{"cell_type":"code","source":"sensor_channel = 'CAM_BACK_LEFT'\nmy_sample_data = lyft_dataset.get('sample_data', my_sample['data'][sensor_channel])\nlyft_dataset.render_sample_data(my_sample_data['token'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:17:51.191016Z","iopub.execute_input":"2021-05-22T12:17:51.191419Z","iopub.status.idle":"2021-05-22T12:17:51.707815Z","shell.execute_reply.started":"2021-05-22T12:17:51.191365Z","shell.execute_reply":"2021-05-22T12:17:51.706981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Back-Right Camera\nImages from the back-right camera","metadata":{}},{"cell_type":"code","source":"sensor_channel = 'CAM_BACK_RIGHT'\nmy_sample_data = lyft_dataset.get('sample_data', my_sample['data'][sensor_channel])\nlyft_dataset.render_sample_data(my_sample_data['token'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:18:03.645319Z","iopub.execute_input":"2021-05-22T12:18:03.645610Z","iopub.status.idle":"2021-05-22T12:18:03.966804Z","shell.execute_reply.started":"2021-05-22T12:18:03.645563Z","shell.execute_reply":"2021-05-22T12:18:03.965976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Nous pouvons choisir une annotation donnée à partir d'un échantillon dans les données et ne rendre que cette annotation, comme indiqué ci-dessous :","metadata":{}},{"cell_type":"code","source":"my_annotation_token = my_sample['anns'][10]\nmy_annotation = my_sample_data.get('sample_annotation', my_annotation_token)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:18:11.549168Z","iopub.execute_input":"2021-05-22T12:18:11.549478Z","iopub.status.idle":"2021-05-22T12:18:11.553754Z","shell.execute_reply.started":"2021-05-22T12:18:11.549427Z","shell.execute_reply":"2021-05-22T12:18:11.552751Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lyft_dataset.render_annotation(my_annotation_token)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:18:13.832512Z","iopub.execute_input":"2021-05-22T12:18:13.832967Z","iopub.status.idle":"2021-05-22T12:18:16.853551Z","shell.execute_reply.started":"2021-05-22T12:18:13.832755Z","shell.execute_reply":"2021-05-22T12:18:16.851731Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can also pick a given instance from the dataset and render only that instance, as shown below:","metadata":{}},{"cell_type":"code","source":"my_instance = lyft_dataset.instance[100]\nmy_instance","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:18:22.632657Z","iopub.execute_input":"2021-05-22T12:18:22.632945Z","iopub.status.idle":"2021-05-22T12:18:22.638133Z","shell.execute_reply.started":"2021-05-22T12:18:22.632898Z","shell.execute_reply":"2021-05-22T12:18:22.637309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"instance_token = my_instance['token']\nlyft_dataset.render_instance(instance_token)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:18:31.803593Z","iopub.execute_input":"2021-05-22T12:18:31.803899Z","iopub.status.idle":"2021-05-22T12:18:34.614212Z","shell.execute_reply.started":"2021-05-22T12:18:31.803851Z","shell.execute_reply":"2021-05-22T12:18:34.613403Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lyft_dataset.render_annotation(my_instance['last_annotation_token'])","metadata":{"execution":{"iopub.status.busy":"2021-05-22T12:18:51.451342Z","iopub.execute_input":"2021-05-22T12:18:51.451740Z","iopub.status.idle":"2021-05-22T12:18:54.250205Z","shell.execute_reply.started":"2021-05-22T12:18:51.451662Z","shell.execute_reply":"2021-05-22T12:18:54.249393Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can also get the LiDAR data collected from various LIDAR sensors on the car as follows:","metadata":{}},{"cell_type":"markdown","source":"### Top LiDAR \nLiDAR data from the top sensor","metadata":{}},{"cell_type":"code","source":"my_scene = lyft_dataset.scene[0]\nmy_sample_token = my_scene[\"first_sample_token\"]\nmy_sample = lyft_dataset.get('sample', my_sample_token)\nlyft_dataset.render_sample_data(my_sample['data']['LIDAR_TOP'], nsweeps=5)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:19:09.885566Z","iopub.execute_input":"2021-05-22T12:19:09.885856Z","iopub.status.idle":"2021-05-22T12:19:16.178563Z","shell.execute_reply.started":"2021-05-22T12:19:09.885806Z","shell.execute_reply":"2021-05-22T12:19:16.177902Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Front-Left LiDAR \nLiDAR data from the front-left sensor","metadata":{}},{"cell_type":"code","source":"my_scene = lyft_dataset.scene[0]\nmy_sample_token = my_scene[\"first_sample_token\"]\nmy_sample = lyft_dataset.get('sample', my_sample_token)\nlyft_dataset.render_sample_data(my_sample['data']['LIDAR_FRONT_LEFT'], nsweeps=5)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:19:41.000275Z","iopub.execute_input":"2021-05-22T12:19:41.000589Z","iopub.status.idle":"2021-05-22T12:19:44.910864Z","shell.execute_reply.started":"2021-05-22T12:19:41.000541Z","shell.execute_reply":"2021-05-22T12:19:44.910188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Front-Right LiDAR \nLiDAR data from the front-right sensor","metadata":{}},{"cell_type":"code","source":"my_scene = lyft_dataset.scene[0]\nmy_sample_token = my_scene[\"first_sample_token\"]\nmy_sample = lyft_dataset.get('sample', my_sample_token)\nlyft_dataset.render_sample_data(my_sample['data']['LIDAR_FRONT_RIGHT'], nsweeps=5)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:20:08.613401Z","iopub.execute_input":"2021-05-22T12:20:08.613691Z","iopub.status.idle":"2021-05-22T12:20:12.408966Z","shell.execute_reply.started":"2021-05-22T12:20:08.613642Z","shell.execute_reply":"2021-05-22T12:20:12.408149Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Image and LiDAR animation\n\nThis section is from [@xhulu](https://www.kaggle.com/xhlulu)'s brilliant [animation kernel](https://www.kaggle.com/xhlulu/lyft-eda-animations-generating-csvs). I use functions from that kernel to animate the image and LiDAR data. \n\nPlease upvote [xhulu's kernel](https://www.kaggle.com/xhlulu/lyft-eda-animations-generating-csvs) if you find this interesting.","metadata":{}},{"cell_type":"code","source":"def generate_next_token(scene):\n scene = lyft_dataset.scene[scene]\n sample_token = scene['first_sample_token']\n sample_record = lyft_dataset.get(\"sample\", sample_token)\n \n while sample_record['next']:\n sample_token = sample_record['next']\n sample_record = lyft_dataset.get(\"sample\", sample_token)\n \n yield sample_token\n\ndef animate_images(scene, frames, pointsensor_channel='LIDAR_TOP', interval=1):\n cams = [\n 'CAM_FRONT',\n 'CAM_FRONT_RIGHT',\n 'CAM_BACK_RIGHT',\n 'CAM_BACK',\n 'CAM_BACK_LEFT',\n 'CAM_FRONT_LEFT',\n ]\n\n generator = generate_next_token(scene)\n\n fig, axs = plt.subplots(\n 2, len(cams), figsize=(3*len(cams), 6), \n sharex=True, sharey=True, gridspec_kw = {'wspace': 0, 'hspace': 0.1}\n )\n \n plt.close(fig)\n\n def animate_fn(i):\n for _ in range(interval):\n sample_token = next(generator)\n \n for c, camera_channel in enumerate(cams): \n sample_record = lyft_dataset.get(\"sample\", sample_token)\n\n pointsensor_token = sample_record[\"data\"][pointsensor_channel]\n camera_token = sample_record[\"data\"][camera_channel]\n \n axs[0, c].clear()\n axs[1, c].clear()\n \n lyft_dataset.render_sample_data(camera_token, with_anns=False, ax=axs[0, c])\n lyft_dataset.render_sample_data(camera_token, with_anns=True, ax=axs[1, c])\n \n axs[0, c].set_title(\"\")\n axs[1, c].set_title(\"\")\n\n anim = animation.FuncAnimation(fig, animate_fn, frames=frames, interval=interval)\n \n return anim","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:21:02.948180Z","iopub.execute_input":"2021-05-22T12:21:02.948499Z","iopub.status.idle":"2021-05-22T12:21:02.961641Z","shell.execute_reply.started":"2021-05-22T12:21:02.948449Z","shell.execute_reply":"2021-05-22T12:21:02.960360Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Animate image data (for 3 scences)","metadata":{}},{"cell_type":"markdown","source":"### Scence 1","metadata":{}},{"cell_type":"code","source":"anim = animate_images(scene=3, frames=100, interval=1)\nHTML(anim.to_jshtml(fps=8))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:21:14.418365Z","iopub.execute_input":"2021-05-22T12:21:14.418649Z","iopub.status.idle":"2021-05-22T12:24:07.915610Z","shell.execute_reply.started":"2021-05-22T12:21:14.418604Z","shell.execute_reply":"2021-05-22T12:24:07.912516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Scence 2","metadata":{}},{"cell_type":"code","source":"anim = animate_images(scene=7, frames=100, interval=1)\nHTML(anim.to_jshtml(fps=8))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:26:36.454493Z","iopub.execute_input":"2021-05-22T12:26:36.454795Z","iopub.status.idle":"2021-05-22T12:29:15.521533Z","shell.execute_reply.started":"2021-05-22T12:26:36.454745Z","shell.execute_reply":"2021-05-22T12:29:15.517653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Scence 3","metadata":{}},{"cell_type":"code","source":"anim = animate_images(scene=4, frames=100, interval=1)\nHTML(anim.to_jshtml(fps=8))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-21T23:54:55.441633Z","iopub.execute_input":"2021-05-21T23:54:55.441982Z","iopub.status.idle":"2021-05-21T23:58:51.714975Z","shell.execute_reply.started":"2021-05-21T23:54:55.441922Z","shell.execute_reply":"2021-05-21T23:58:51.712494Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Animate LiDAR data (for 3 scences)","metadata":{}},{"cell_type":"code","source":"def animate_lidar(scene, frames, pointsensor_channel='LIDAR_TOP', with_anns=True, interval=1):\n generator = generate_next_token(scene)\n\n fig, axs = plt.subplots(1, 1, figsize=(8, 8))\n plt.close(fig)\n\n def animate_fn(i):\n for _ in range(interval):\n sample_token = next(generator)\n \n axs.clear()\n sample_record = lyft_dataset.get(\"sample\", sample_token)\n pointsensor_token = sample_record[\"data\"][pointsensor_channel]\n lyft_dataset.render_sample_data(pointsensor_token, with_anns=with_anns, ax=axs)\n\n anim = animation.FuncAnimation(fig, animate_fn, frames=frames, interval=interval)\n \n return anim","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:30:13.592640Z","iopub.execute_input":"2021-05-22T12:30:13.592937Z","iopub.status.idle":"2021-05-22T12:30:13.600739Z","shell.execute_reply.started":"2021-05-22T12:30:13.592889Z","shell.execute_reply":"2021-05-22T12:30:13.599968Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Scence 1","metadata":{}},{"cell_type":"code","source":"anim = animate_lidar(scene=5, frames=100, interval=1)\nHTML(anim.to_jshtml(fps=8))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T12:30:40.736096Z","iopub.execute_input":"2021-05-22T12:30:40.736394Z","iopub.status.idle":"2021-05-22T12:34:01.851759Z","shell.execute_reply.started":"2021-05-22T12:30:40.736342Z","shell.execute_reply":"2021-05-22T12:34:01.850523Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Scence 2","metadata":{}},{"cell_type":"code","source":"anim = animate_lidar(scene=25, frames=100, interval=1)\nHTML(anim.to_jshtml(fps=8))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T00:02:41.960945Z","iopub.execute_input":"2021-05-22T00:02:41.962166Z","iopub.status.idle":"2021-05-22T00:10:29.552178Z","shell.execute_reply.started":"2021-05-22T00:02:41.961985Z","shell.execute_reply":"2021-05-22T00:10:29.550376Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Scence 3","metadata":{}},{"cell_type":"code","source":"anim = animate_lidar(scene=10, frames=100, interval=1)\nHTML(anim.to_jshtml(fps=8))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T00:10:29.554548Z","iopub.execute_input":"2021-05-22T00:10:29.555046Z","iopub.status.idle":"2021-05-22T00:14:20.593773Z","shell.execute_reply.started":"2021-05-22T00:10:29.554955Z","shell.execute_reply":"2021-05-22T00:14:20.591691Z"},"trusted":true},"execution_count":null,"outputs":[]}]}
![](\"https://i.imgur.com/8dUga6i.jpg\")
![](\"https://i.imgur.com/yG3CewG.jpg\")
![](\"https://i.imgur.com/Frl3hgk.gif\")
","metadata":{}},{"cell_type":"markdown","source":"des faisceaux laser sont tirés dans tous les sens par un laser. Les faisceaux laser se réfléchissent sur les objets qui se trouvent sur leur chemin et les faisceaux réfléchis sont collectés par un capteur. Maintenant, un dispositif spécial appelé **caméra flash LiDAR** est utilisé pour créer des cartes en 3D en utilisant les informations de ces capteurs.","metadata":{}},{"cell_type":"markdown","source":"### Flash LiDAR Camera","metadata":{}},{"cell_type":"markdown","source":"![](\"https://i.imgur.com/C3zUR7X.jpg\")
","metadata":{}},{"cell_type":"markdown","source":"L'appareil présenté dans l'image ci-dessus s'appelle une caméra Flash LiDAR. Le plan focal d'une caméra Flash LiDAR comporte des rangées et des colonnes de pixels ayant une \"profondeur\" et une \"intensité\" suffisantes pour créer des modèles de paysage en 3D. Chaque pixel enregistre le temps que met chaque impulsion laser à atteindre la cible et à revenir au capteur, ainsi que la profondeur, l'emplacement et l'intensité de réflexion de l'objet touché par l'impulsion laser.\n\nLe Flash LiDAR utilise une seule source lumineuse qui illumine le champ de vision en une seule impulsion. Tout comme un appareil photo qui prend des photos de la distance, au lieu des couleurs.\n\nLa source d'illumination embarquée fait du Flash LiDAR un capteur actif. Le signal renvoyé est traité par des algorithmes intégrés pour produire un rendu 3D quasi instantané des objets et des caractéristiques du terrain dans le champ de vision du capteur. La fréquence de répétition des impulsions laser est suffisante pour générer des vidéos 3D avec une résolution et une précision élevées. La fréquence d'images élevée du capteur en fait un outil utile pour une variété d'applications qui bénéficient d'une visualisation en temps réel, comme la conduite autonome des véhicules. En renvoyant immédiatement un maillage d'élévation 3D des paysages cibles, un capteur flash peut être utilisé par un véhicule autonome pour prendre des décisions concernant le réglage de la vitesse, le freinage, la direction, etc.\n\nCe type de caméra est fixé au sommet des voitures autonomes, et ces voitures l'utilisent pour naviguer tout en conduisant.","metadata":{}},{"cell_type":"markdown","source":"# Visualisation de données ","metadata":{}},{"cell_type":"markdown","source":"### Install *lyft_dataset_sdk* and import the necessary libraries","metadata":{}},{"cell_type":"markdown","source":"Nous aurons besoin de la bibliothèque *lyft_dataset_sdk* car elle nous aidera à visualiser facilement l'image et les données LiDAR. Une simple commande *pip install* est nécessaire. J'utiliserai également l'installation de la bibliothèque *chart_studio* pour générer des graphiques interactifs.","metadata":{}},{"cell_type":"code","source":"!pip install lyft_dataset_sdk","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2021-05-22T10:57:22.290660Z","iopub.execute_input":"2021-05-22T10:57:22.291008Z","iopub.status.idle":"2021-05-22T10:57:46.344443Z","shell.execute_reply.started":"2021-05-22T10:57:22.290962Z","shell.execute_reply":"2021-05-22T10:57:46.343350Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport gc\nimport numpy as np\nimport pandas as pd\n\nimport json\nimport math\nimport sys\nimport time\nfrom datetime import datetime\nfrom typing import Tuple, List\n\nimport cv2\nimport matplotlib.pyplot as plt\nimport sklearn.metrics\nfrom PIL import Image\n\nfrom matplotlib.axes import Axes\nfrom matplotlib import animation, rc\nimport plotly.graph_objs as go\nimport plotly.tools as tls\nfrom plotly.offline import plot, init_notebook_mode\nimport plotly.figure_factory as ff\n\ninit_notebook_mode(connected=True)\n\nimport seaborn as sns\nfrom pyquaternion import Quaternion\nfrom tqdm import tqdm\n\nfrom lyft_dataset_sdk.utils.map_mask import MapMask\nfrom lyft_dataset_sdk.lyftdataset import LyftDataset\nfrom lyft_dataset_sdk.utils.geometry_utils import view_points, box_in_image, BoxVisibility\nfrom lyft_dataset_sdk.utils.geometry_utils import view_points, transform_matrix\nfrom pathlib import Path\n\nimport struct\nfrom abc import ABC, abstractmethod\nfrom functools import reduce\nfrom typing import Tuple, List, Dict\nimport copy","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-05-22T10:59:35.829643Z","iopub.execute_input":"2021-05-22T10:59:35.829938Z","iopub.status.idle":"2021-05-22T10:59:39.703471Z","shell.execute_reply.started":"2021-05-22T10:59:35.829884Z","shell.execute_reply":"2021-05-22T10:59:39.702710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### le chemin de données","metadata":{}},{"cell_type":"code","source":"## créér le chémin où les donnée\nDATA_PATH = '/kaggle/input/3d-object-detection-for-autonomous-vehicles/'","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:00:32.237983Z","iopub.execute_input":"2021-05-22T11:00:32.238299Z","iopub.status.idle":"2021-05-22T11:00:32.244534Z","shell.execute_reply.started":"2021-05-22T11:00:32.238242Z","shell.execute_reply":"2021-05-22T11:00:32.243764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Importer les données de training","metadata":{}},{"cell_type":"code","source":"## importer le dataset train \ntrain = pd.read_csv(DATA_PATH + 'train.csv')\nsample_submission = pd.read_csv(DATA_PATH + 'sample_submission.csv')","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:03:47.370905Z","iopub.execute_input":"2021-05-22T11:03:47.371425Z","iopub.status.idle":"2021-05-22T11:03:48.538886Z","shell.execute_reply.started":"2021-05-22T11:03:47.371224Z","shell.execute_reply":"2021-05-22T11:03:48.538166Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:04:14.634693Z","iopub.execute_input":"2021-05-22T11:04:14.634980Z","iopub.status.idle":"2021-05-22T11:04:14.655211Z","shell.execute_reply.started":"2021-05-22T11:04:14.634932Z","shell.execute_reply":"2021-05-22T11:04:14.654140Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n### Regrouper les données par catégorie d'objet","metadata":{}},{"cell_type":"code","source":"# Taken from https://www.kaggle.com/gaborfodor/eda-3d-object-detection-challenge\n\nobject_columns = ['sample_id', 'object_id', 'center_x', 'center_y', 'center_z',\n 'width', 'length', 'height', 'yaw', 'class_name']\nobjects = []\nfor sample_id, ps in tqdm(train.values[:]):\n object_params = ps.split()\n n_objects = len(object_params)\n for i in range(n_objects // 8):\n x, y, z, w, l, h, yaw, c = tuple(object_params[i * 8: (i + 1) * 8])\n objects.append([sample_id, i, x, y, z, w, l, h, yaw, c])\ntrain_objects = pd.DataFrame(\n objects,\n columns = object_columns\n)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:07:16.867644Z","iopub.execute_input":"2021-05-22T11:07:16.867933Z","iopub.status.idle":"2021-05-22T11:07:19.749912Z","shell.execute_reply.started":"2021-05-22T11:07:16.867883Z","shell.execute_reply":"2021-05-22T11:07:19.749163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Convertir les colonnes de type string en numérique (float32)","metadata":{}},{"cell_type":"code","source":"train_objects.head()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:08:03.199957Z","iopub.execute_input":"2021-05-22T11:08:03.200239Z","iopub.status.idle":"2021-05-22T11:08:03.217047Z","shell.execute_reply.started":"2021-05-22T11:08:03.200191Z","shell.execute_reply":"2021-05-22T11:08:03.215897Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"numerical_cols = ['object_id', 'center_x', 'center_y', 'center_z', 'width', 'length', 'height', 'yaw']\ntrain_objects[numerical_cols] = np.float32(train_objects[numerical_cols].values)","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:08:06.391039Z","iopub.execute_input":"2021-05-22T11:08:06.391369Z","iopub.status.idle":"2021-05-22T11:08:07.802498Z","shell.execute_reply.started":"2021-05-22T11:08:06.391311Z","shell.execute_reply":"2021-05-22T11:08:07.801553Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_objects.head()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:08:07.804198Z","iopub.execute_input":"2021-05-22T11:08:07.804503Z","iopub.status.idle":"2021-05-22T11:08:07.823240Z","shell.execute_reply.started":"2021-05-22T11:08:07.804460Z","shell.execute_reply":"2021-05-22T11:08:07.822651Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_objects.info()","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:09:31.494919Z","iopub.execute_input":"2021-05-22T11:09:31.495206Z","iopub.status.idle":"2021-05-22T11:09:31.621163Z","shell.execute_reply.started":"2021-05-22T11:09:31.495159Z","shell.execute_reply":"2021-05-22T11:09:31.620058Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Analyse exploratoire de données ","metadata":{}},{"cell_type":"markdown","source":"### center_x and center_y","metadata":{}},{"cell_type":"markdown","source":"**center_x** et **center_y** correspondent aux coordonnées *x* et *y* du centre de l'emplacement d'un objet (volume limite). Ces coordonnées représentent l'emplacement d'un objet sur le plan *x-y*.","metadata":{}},{"cell_type":"markdown","source":"### Distributions *center_x* and *center_y*","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['center_x'], color='darkorange', ax=ax).set_title('center_x and center_y', fontsize=16)\nsns.distplot(train_objects['center_y'], color='purple', ax=ax).set_title('center_x and center_y', fontsize=16)\nplt.xlabel('center_x and center_y', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:11:23.794328Z","iopub.execute_input":"2021-05-22T11:11:23.794619Z","iopub.status.idle":"2021-05-22T11:11:24.671813Z","shell.execute_reply.started":"2021-05-22T11:11:23.794573Z","shell.execute_reply":"2021-05-22T11:11:24.670889Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Sur ce graphique ci-dessus, la distribution violette est celle de *center_y* et la distribution orange est celle de *center_x*. Le diagramme ci-dessus montre que les distributions de *centre_x* et de *centre_y* ont plusieurs pics et sont donc multimodales. Les deux distributions présentent également une nette inclinaison vers la droite ou une inclinaison positive. Mais, la distribution de *center_y* (violet) a un biais significativement plus élevé que la distribution de *center_x* (orange). La distribution *center_x* est plus uniformément répartie. \n\nCela indique que les objets sont répartis très uniformément le long de l'axe *x*, mais pas de la même manière le long de l'axe *y*. Cela est probablement dû au fait que la caméra de la voiture peut facilement détecter des objets à gauche ou à droite (le long de l'axe *x*) en raison de la faible largeur de la route. Mais, comme la longueur de la route est beaucoup plus grande que sa largeur, et qu'il y a plus de chances que la vue de la caméra soit bloquée depuis cet angle, la caméra ne peut trouver que des objets situés juste devant ou juste derrière (et pas plus loin).","metadata":{}},{"cell_type":"markdown","source":"### Relation entre *center_x* and *center_y*","metadata":{}},{"cell_type":"markdown","source":"### KDE Plot","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"new_train_objects = train_objects.query('class_name == \"car\"')\nplot = sns.jointplot(x=new_train_objects['center_x'][:1000], y=new_train_objects['center_y'][:1000], kind='kde', color='blueviolet')\nplot.set_axis_labels('center_x', 'center_y', fontsize=16)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:15:31.678101Z","iopub.execute_input":"2021-05-22T11:15:31.678443Z","iopub.status.idle":"2021-05-22T11:15:33.408915Z","shell.execute_reply.started":"2021-05-22T11:15:31.678386Z","shell.execute_reply":"2021-05-22T11:15:33.407925Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le graphique KDE ci-dessus, nous pouvons voir que *center_x* et *center_y* semblent avoir une corrélation quelque peu négative. Cela est probablement dû, une fois de plus, aux limites du système de caméra. La caméra peut détecter des objets qui sont loin devant, mais pas trop loin sur le côté. Et elle peut également détecter des objets qui sont loin sur le côté, mais pas trop loin devant. Mais **la caméra ne peut pas détecter les objets qui sont à la fois loin devant et loin sur le côté**. Pour cette raison, les objets situés loin devant et loin sur le côté ne sont pas du tout détectés, et seuls les objets qui remplissent une (ou aucune) de ces conditions sont détectés. Il en résulte une relation négative entre *center_x* et *center_y*.","metadata":{}},{"cell_type":"markdown","source":"### center_z","metadata":{}},{"cell_type":"markdown","source":"**center_z** correspond à la coordonnée *xz* du centre de l'emplacement d'un objet (volume limite). Cette coordonnée représente la hauteur de l'objet au-dessus du plan *x-y*.","metadata":{}},{"cell_type":"markdown","source":"### Distribution *center_z*","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['center_z'], color='navy', ax=ax).set_title('center_z', fontsize=16)\nplt.xlabel('center_z', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:18:37.705377Z","iopub.execute_input":"2021-05-22T11:18:37.705889Z","iopub.status.idle":"2021-05-22T11:18:38.473961Z","shell.execute_reply.started":"2021-05-22T11:18:37.705703Z","shell.execute_reply":"2021-05-22T11:18:38.473111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la distribution de *center_z* a une asymétrie positive (vers la droite) extrêmement élevée et qu'elle est regroupée autour de la marque -20 (qui est proche de sa valeur moyenne). La variation (dispersion) de *center_z* est nettement plus faible que celle de *center_x* et *center_y*. Cela s'explique probablement par le fait que la plupart des objets sont très proches du plan plat de la route et qu'il n'y a donc pas de grande variation de la hauteur des objets au-dessus (ou au-dessous) de la caméra. Il y a naturellement une variation beaucoup plus grande dans les coordonnées *x* et *y* de l'objet.\n\nDe plus, la plupart des coordonnées *z* sont négatives car la caméra est fixée au sommet de la voiture. Ainsi, la plupart du temps, la caméra doit \"regarder vers le bas\" pour voir les objets. Par conséquent, la hauteur ou les coordonnées *z* des objets par rapport à la caméra sont généralement négatives.","metadata":{}},{"cell_type":"markdown","source":"### yaw","metadata":{}},{"cell_type":"markdown","source":"**yaw** est l'angle du volume autour de l'axe *z*, ce qui fait que le \"lacet\" est la direction vers laquelle l'avant du véhicule/boîte englobante est dirigé lorsqu'il est au sol.","metadata":{}},{"cell_type":"markdown","source":"### Distribution de *yaw*","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['yaw'], color='darkgreen', ax=ax).set_title('yaw', fontsize=16)\nplt.xlabel('yaw', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:38:06.489867Z","iopub.execute_input":"2021-05-22T11:38:06.490478Z","iopub.status.idle":"2021-05-22T11:38:07.044164Z","shell.execute_reply.started":"2021-05-22T11:38:06.490164Z","shell.execute_reply":"2021-05-22T11:38:07.043409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la distribution de *yaw* est grossièrement bimodale, *c'est-à-dire qu'il y a deux pics majeurs dans la distribution. L'un des pics se situe autour de 0,5 et l'autre autour de 2,5. On peut estimer que la moyenne se situe entre 1 et 2 (autour de 1,5). La distribution ne présente pas d'asymétrie nette. La présence des deux pics à des positions symétriques réduit l'asymétrie dans les deux directions (et ils s'annulent), ce qui rend la distribution plus équilibrée que les distributions de *centre_x*, *centre_y* et *centre_z*.","metadata":{}},{"cell_type":"markdown","source":"### width","metadata":{}},{"cell_type":"markdown","source":"**width** est simplement la largeur du volume délimité dans lequel se trouve l'objet.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['width'], color='magenta', ax=ax).set_title('width', fontsize=16)\nplt.xlabel('width', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:39:50.933860Z","iopub.execute_input":"2021-05-22T11:39:50.934172Z","iopub.status.idle":"2021-05-22T11:39:51.456382Z","shell.execute_reply.started":"2021-05-22T11:39:50.934123Z","shell.execute_reply":"2021-05-22T11:39:51.455564Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la *largeur* est distribuée à peu près normalement avec une moyenne d'environ 2, avec quelques valeurs aberrantes de chaque côté. La majorité des objets sont des voitures (comme nous le verrons plus tard), et celles-ci constituent une largeur d'environ 2 (au sommet). Les valeurs aberrantes à droite représentent des objets plus grands comme les camions et les camionnettes, et les valeurs aberrantes à gauche représentent des objets plus petits comme les piétons et les bicyclettes.","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### length","metadata":{}},{"cell_type":"markdown","source":"**length** est simplement la longueur du volume délimité dans lequel se trouve l'objet.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['length'], color='crimson', ax=ax).set_title('length', fontsize=16)\nplt.xlabel('length', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:41:26.875518Z","iopub.execute_input":"2021-05-22T11:41:26.875837Z","iopub.status.idle":"2021-05-22T11:41:27.383567Z","shell.execute_reply.started":"2021-05-22T11:41:26.875787Z","shell.execute_reply":"2021-05-22T11:41:27.382619Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la *longueur* a une distribution fortement positive (skew vers la droite) avec une moyenne d'environ 5, avec quelques valeurs aberrantes de chaque côté. La majorité des objets sont des voitures (comme nous le verrons plus tard), et celles-ci constituent une longueur d'environ 5 (au sommet). Les valeurs aberrantes sur la droite représentent des objets plus grands comme les camions et les camionnettes, et les valeurs aberrantes sur la gauche représentent des objets plus petits comme les piétons et les bicyclettes.","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### height","metadata":{}},{"cell_type":"markdown","source":"**height** est simplement la hauteur du volume délimité dans lequel se trouve l'objet.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nsns.distplot(train_objects['height'], color='indigo', ax=ax).set_title('height', fontsize=16)\nplt.xlabel('height', fontsize=15)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:42:31.953641Z","iopub.execute_input":"2021-05-22T11:42:31.953937Z","iopub.status.idle":"2021-05-22T11:42:32.464587Z","shell.execute_reply.started":"2021-05-22T11:42:31.953888Z","shell.execute_reply":"2021-05-22T11:42:32.463710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans le diagramme ci-dessus, nous pouvons voir que la *hauteur* a une distribution fortement positive (skew vers la droite) avec une moyenne d'environ 2, avec quelques aberrations de part et d'autre. La majorité des objets sont des voitures (comme nous le verrons plus tard), et celles-ci constituent une longueur d'environ 2 (au sommet). Les valeurs aberrantes sur la droite représentent des objets plus grands comme les camions et les camionnettes, et les valeurs aberrantes sur la gauche représentent des objets plus petits comme les piétons et les bicyclettes.","metadata":{}},{"cell_type":"markdown","source":"### Fréquence des objets","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(10, 10))\nplot = sns.countplot(y=\"class_name\", data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette=['navy', 'darkblue', 'blue', 'dodgerblue', 'skyblue', 'lightblue']).set_title('Object Frequencies', fontsize=16)\nplt.yticks(fontsize=14)\nplt.xlabel(\"Count\", fontsize=15)\nplt.ylabel(\"Class Name\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:44:05.860924Z","iopub.execute_input":"2021-05-22T11:44:05.861213Z","iopub.status.idle":"2021-05-22T11:44:06.595027Z","shell.execute_reply.started":"2021-05-22T11:44:05.861164Z","shell.execute_reply":"2021-05-22T11:44:06.594250Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Le diagramme ci-dessus montre que la classe d'objets la plus courante dans l'ensemble de données est la \"voiture\". Cela n'est pas surprenant car les images sont prises dans les rues de Palo Alto, dans la Silicon Valley, en Californie. Et le véhicule (ou l'entité, d'ailleurs) le plus communément visible sur ces routes est la voiture. Toutes les autres classes d'objets sont loin d'être proches des voitures en termes de fréquence.","metadata":{}},{"cell_type":"code","source":"## Analyse multivariée ","metadata":{"execution":{"iopub.status.busy":"2021-05-22T11:45:46.470002Z","iopub.execute_input":"2021-05-22T11:45:46.470326Z","iopub.status.idle":"2021-05-22T11:45:46.474036Z","shell.execute_reply.started":"2021-05-22T11:45:46.470255Z","shell.execute_reply":"2021-05-22T11:45:46.473218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### center_x *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de **center_x** change pour différents **nom de classe_des objets.**.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"center_x\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGnBu',\n split=True, ax=ax).set_title('center_x (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_x\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:46:40.544552Z","iopub.execute_input":"2021-05-22T11:46:40.544841Z","iopub.status.idle":"2021-05-22T11:46:43.411018Z","shell.execute_reply.started":"2021-05-22T11:46:40.544795Z","shell.execute_reply":"2021-05-22T11:46:43.410171Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon ci-dessus, nous pouvons voir que les distributions de *center_x* pour les grands véhicules, y compris les camions, les bus et autres véhicules, sont bien réparties. Elles ne présentent pratiquement pas d'asymétrie et ont des moyennes plus élevées que les distributions des piétons et des bicyclettes. Cela s'explique probablement par le fait que ces gros véhicules ont tendance à garder une plus grande distance avec les autres véhicules, et que les petits véhicules ne restent pas trop près de ces gros véhicules afin d'éviter les accidents. Par conséquent, la moyenne *center_x* est nettement supérieure pour les gros véhicules comme les bus et les camions.\n\nEn revanche, les objets plus petits comme les piétons et les bicyclettes ont des distributions *center_x* fortement inclinées vers la droite. Ces distributions ont également des moyennes nettement plus faibles que celles des véhicules plus grands. Cela est probablement dû au fait que les piétons (qui traversent la route) et les cyclistes n'ont pas besoin de maintenir de grandes distances avec les voitures et les camions pour éviter les accidents. Ils traversent généralement la route pendant un feu rouge, lorsque le trafic s'arrête.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"center_x\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGnBu', ax=ax).set_title('center_x (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_x\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:49:25.633246Z","iopub.execute_input":"2021-05-22T11:49:25.633624Z","iopub.status.idle":"2021-05-22T11:49:26.640091Z","shell.execute_reply.started":"2021-05-22T11:49:25.633577Z","shell.execute_reply":"2021-05-22T11:49:26.639183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In the box plots above, we can notice the same observation as in the violin plot above. The *center_x* distributions for smaller objects like pedestrians and bicycles have very low mean and quartile values as compared to larger objects like cars, trucks, and buses.","metadata":{}},{"cell_type":"markdown","source":"### center_y *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, nous allons explorer comment la distribution de **center_y** change pour différents **classes_noms** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"center_y\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlOrRd',\n split=True, ax=ax).set_title('center_y (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_y\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:50:52.650733Z","iopub.execute_input":"2021-05-22T11:50:52.651072Z","iopub.status.idle":"2021-05-22T11:50:55.421171Z","shell.execute_reply.started":"2021-05-22T11:50:52.651021Z","shell.execute_reply":"2021-05-22T11:50:55.420362Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon ci-dessus, nous pouvons voir que les distributions de *centre_y* pour les petits objets, y compris les piétons et les bicyclettes, ont une valeur moyenne plus grande que les grands objets comme les camions et les bus. Les distributions pour les petits objets ont une densité de probabilité beaucoup plus grande concentrée à des valeurs plus élevées de *centre_y* par rapport aux grands objets. Cela signifie que les petits objets, en général, ont des valeurs de *center_y* plus élevées que les grands objets. \n\nCela est probablement dû au fait que les grands véhicules ont tendance à se trouver dans le champ de vision de la caméra en raison de leur grande taille. Mais les objets plus petits, comme les bicyclettes et les piétons, ne peuvent pas rester dans le champ de vision de la caméra lorsqu'ils sont trop proches. Par conséquent, la plupart des piétons et des vélos qui sont détectés ont tendance à être éloignés. Le *centre_y* est donc plus grand (en moyenne) pour les petits objets que pour les grands.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"center_y\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlOrRd', ax=ax).set_title('center_y (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_y\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:52:41.066865Z","iopub.execute_input":"2021-05-22T11:52:41.067197Z","iopub.status.idle":"2021-05-22T11:52:41.940086Z","shell.execute_reply.started":"2021-05-22T11:52:41.067155Z","shell.execute_reply":"2021-05-22T11:52:41.939249Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions *center_y* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus grandes que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### center_z *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de **center_z** change pour différents **classes_noms** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"center_z\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"').query('center_z <= -5'),\n palette='RdPu',\n split=True, ax=ax).set_title('center_z (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_z\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:53:46.757168Z","iopub.execute_input":"2021-05-22T11:53:46.757484Z","iopub.status.idle":"2021-05-22T11:53:49.337041Z","shell.execute_reply.started":"2021-05-22T11:53:46.757433Z","shell.execute_reply":"2021-05-22T11:53:49.336084Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon ci-dessus, nous pouvons voir que les distributions de *center_z* pour les petits objets, y compris les piétons et les bicyclettes, ont une valeur moyenne nettement inférieure à celle des grands objets comme les camions et les bus. Les distributions pour les petits objets ont une densité de probabilité beaucoup plus importante concentrée à des valeurs plus faibles de *centre_z* par rapport aux grands objets. Cela signifie que les petits objets, en général, ont des valeurs de *center_y* plus petites que les grands objets. \n\nCela est probablement dû au fait que les petits objets comme les piétons et les vélos ont tendance à avoir une hauteur plus faible par rapport à la caméra. Et, d'autre part, les objets plus grands comme les voitures, les camions et les bus ont tendance à avoir une plus grande hauteur par rapport à la caméra.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"center_z\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"').query('center_z <= -5'),\n palette='RdPu', ax=ax).set_title('center_z (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"center_z\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:55:10.581600Z","iopub.execute_input":"2021-05-22T11:55:10.581888Z","iopub.status.idle":"2021-05-22T11:55:11.403009Z","shell.execute_reply.started":"2021-05-22T11:55:10.581839Z","shell.execute_reply":"2021-05-22T11:55:11.402155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions *center_z* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### width *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de **largeur** change pour différents **noms de classe** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"width\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGn',\n split=True, ax=ax).set_title('width (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"width\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:56:24.885126Z","iopub.execute_input":"2021-05-22T11:56:24.885457Z","iopub.status.idle":"2021-05-22T11:56:27.716860Z","shell.execute_reply.started":"2021-05-22T11:56:24.885400Z","shell.execute_reply":"2021-05-22T11:56:27.715945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon, nous pouvons clairement voir que les distributions de *largeur* pour les grands véhicules comme les voitures, les bus et les camions ont des moyennes beaucoup plus grandes que celles des petits objets comme les piétons et les bicyclettes. Cela n'est pas surprenant car les camions, les bus et les voitures ont presque toujours une largeur beaucoup plus grande que les piétons et les vélos.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"width\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\"'),\n palette='YlGn', ax=ax).set_title('width (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"width\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:57:25.796188Z","iopub.execute_input":"2021-05-22T11:57:25.796530Z","iopub.status.idle":"2021-05-22T11:57:26.591057Z","shell.execute_reply.started":"2021-05-22T11:57:25.796480Z","shell.execute_reply":"2021-05-22T11:57:26.590298Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions de *largeur* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### length *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"In the plots below, I will explore how the distribution of **length** changes for different object **class_names**.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"length\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and length < 15'),\n palette='Purples',\n split=True, ax=ax).set_title('length (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"length\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:57:56.182637Z","iopub.execute_input":"2021-05-22T11:57:56.182990Z","iopub.status.idle":"2021-05-22T11:57:58.648718Z","shell.execute_reply.started":"2021-05-22T11:57:56.182927Z","shell.execute_reply":"2021-05-22T11:57:58.647862Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon, nous pouvons clairement voir que les distributions de *longueur* pour les grands véhicules comme les voitures, les bus et les camions ont des moyennes beaucoup plus grandes que celles des petits objets comme les piétons et les bicyclettes. Ce n'est pas surprenant car les camions, les bus et les voitures ont presque toujours une longueur beaucoup plus grande que les piétons et les vélos.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"length\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and length < 15'),\n palette='Purples', ax=ax).set_title('length (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"length\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:58:38.336924Z","iopub.execute_input":"2021-05-22T11:58:38.337213Z","iopub.status.idle":"2021-05-22T11:58:39.195024Z","shell.execute_reply.started":"2021-05-22T11:58:38.337163Z","shell.execute_reply":"2021-05-22T11:58:39.194247Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions de *longueur* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.","metadata":{}},{"cell_type":"markdown","source":"### height *vs.* class_name","metadata":{}},{"cell_type":"markdown","source":"Dans les graphiques ci-dessous, je vais explorer comment la distribution de la **hauteur** change pour différents **noms de classe** d'objets.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.violinplot(x=\"class_name\", y=\"height\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and height < 6'),\n palette='Reds',\n split=True, ax=ax).set_title('height (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"height\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:59:04.044292Z","iopub.execute_input":"2021-05-22T11:59:04.044626Z","iopub.status.idle":"2021-05-22T11:59:06.561721Z","shell.execute_reply.started":"2021-05-22T11:59:04.044577Z","shell.execute_reply":"2021-05-22T11:59:06.560862Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes de violon, nous pouvons clairement voir que les distributions de *longueur* pour les grands véhicules comme les bus et les camions ont des moyennes beaucoup plus grandes que celles des petits objets comme les piétons et les bicyclettes. Ce n'est pas surprenant car les camions et les bus ont presque toujours une longueur beaucoup plus grande que les piétons et les vélos.\n\nLes voitures constituent la seule exception à cette tendance. Elles ont tendance à avoir une hauteur similaire à celle des piétons.","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(15, 15))\n\nplot = sns.boxplot(x=\"class_name\", y=\"height\",\n data=train_objects.query('class_name != \"motorcycle\" and class_name != \"emergency_vehicle\" and class_name != \"animal\" and height < 6'),\n palette='Reds', ax=ax).set_title('height (for different objects)', fontsize=16)\n\nplt.yticks(fontsize=14)\nplt.xticks(fontsize=14)\nplt.xlabel(\"Class Name\", fontsize=15)\nplt.ylabel(\"height\", fontsize=15)\nplt.show(plot)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-05-22T11:59:35.905404Z","iopub.execute_input":"2021-05-22T11:59:35.905692Z","iopub.status.idle":"2021-05-22T11:59:36.697307Z","shell.execute_reply.started":"2021-05-22T11:59:35.905643Z","shell.execute_reply":"2021-05-22T11:59:36.696577Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dans les diagrammes en boîte ci-dessus, nous pouvons noter la même observation que dans le diagramme en violon ci-dessus. Les distributions de *hauteur* pour les petits objets comme les piétons et les bicyclettes ont des valeurs moyennes et quartiles beaucoup plus petites que celles des objets plus grands comme les voitures, les camions et les bus.\n\nUne fois encore, les voitures constituent la seule exception à cette tendance. Elles ont tendance à avoir une hauteur similaire à celle des piétons.","metadata":{}},{"cell_type":"markdown","source":"# analyse les images et les données LiDAR","metadata":{}},{"cell_type":"markdown","source":"### Define some functions to help create the *LyftDataset* class\n#### (click CODE on the right side)","metadata":{}},{"cell_type":"code","source":"# Lyft Dataset SDK dev-kit.\n# Code written by Oscar Beijbom, 2018.\n# Licensed under the Creative Commons [see licence.txt]\n# Modified by Vladimir Iglovikov 2019.\n\nclass PointCloud(ABC):\n \"\"\"\n Abstract class for manipulating and viewing point clouds.\n Every point cloud (lidar and radar) consists of points where:\n - Dimensions 0, 1, 2 represent x, y, z coordinates.\n These are modified when the point cloud is rotated or translated.\n - All other dimensions are optional. Hence these have to be manually modified if the reference frame changes.\n \"\"\"\n\n def __init__(self, points: np.ndarray):\n \"\"\"\n Initialize a point cloud and check it has the correct dimensions.\n :param points: