{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# all of this code is taken from the amazing Kernel of Awsaf :  \n\nhttps://www.kaggle.com/awsaf49\n\nhttps://www.kaggle.com/awsaf49/happywhale-boundingbox-yolov5","metadata":{}},{"cell_type":"markdown","source":"# [Happywhale - Whale and Dolphin Identification](https://www.kaggle.com/c/happy-whale-and-dolphin)\n> Identify whales and dolphins by unique characteristic\n\n<img src=\"https://storage.googleapis.com/kaggle-competitions/kaggle/22962/logos/header.png?t=2021-03-17-22-44-09\">","metadata":{}},{"cell_type":"markdown","source":"# 📌 Methodology\n* In this notebook, we'll generate **bounding box** using **YOLOv5**.\n* This notebook mostly based on this notebook, [Great-Barrier-Reef: YOLOv5 [train] 🌊](https://www.kaggle.com/awsaf49/great-barrier-reef-yolov5-train).\n* For train and test data we'll use only **Whale Flute**. We have total **1200** samples with **bounding box**.\n* Finally, we'll use **Whale Flute** model to predict on our **Whale and Dolphin** dataset.\n\n> **Caution:** As this is **Out of Distribution (OOD)** problem, there might be some **False Positives (FP)**. It is recommended to use this dataset carefully.","metadata":{}},{"cell_type":"markdown","source":"# 🛠 Install Libraries","metadata":{}},{"cell_type":"code","source":"!pip install -qU wandb\n!pip install -qU bbox-utility # check https://github.com/awsaf49/bbox for source code\n!pip install -q imagesize","metadata":{"_kg_hide-output":true,"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:22.774097Z","iopub.execute_input":"2022-02-26T13:34:22.774481Z","iopub.status.idle":"2022-02-26T13:34:45.979464Z","shell.execute_reply.started":"2022-02-26T13:34:22.774423Z","shell.execute_reply":"2022-02-26T13:34:45.978580Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 📚 Import Libraries","metadata":{}},{"cell_type":"code","source":"import numpy as np\nfrom tqdm.notebook import tqdm\n\ntqdm.pandas()\nimport pandas as pd\nimport os\nimport cv2\nimport matplotlib.pyplot as plt\nimport glob\n\nimport imagesize\nimport shutil\n\nfrom joblib import Parallel, delayed\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-02-26T13:34:45.984819Z","iopub.execute_input":"2022-02-26T13:34:45.986805Z","iopub.status.idle":"2022-02-26T13:34:45.996487Z","shell.execute_reply.started":"2022-02-26T13:34:45.986757Z","shell.execute_reply":"2022-02-26T13:34:45.995488Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Please Upvote if you find this Helpful","metadata":{}},{"cell_type":"markdown","source":"# ⭐ WandB\n<img src=\"https://camo.githubusercontent.com/dd842f7b0be57140e68b2ab9cb007992acd131c48284eaf6b1aca758bfea358b/68747470733a2f2f692e696d6775722e636f6d2f52557469567a482e706e67\" width=600>\n\nWeights & Biases (W&B) is MLOps platform for tracking our experiemnts. We can use it to Build better models faster with experiment tracking, dataset versioning, and model management. Some of the cool features of W&B:\n\n* Track, compare, and visualize ML experiments\n* Get live metrics, terminal logs, and system stats streamed to the centralized dashboard.\n* Explain how your model works, show graphs of how model versions improved, discuss bugs, and demonstrate progress towards milestones.\n","metadata":{}},{"cell_type":"code","source":"import wandb\n\ntry:\n    from kaggle_secrets import UserSecretsClient\n\n    user_secrets = UserSecretsClient()\n    api_key = user_secrets.get_secret(\"WANDB\")\n    wandb.login(key=api_key)\n    anonymous = None\nexcept:\n    wandb.login(anonymous=\"must\")\n    print(\n        \"To use your W&B account,\\nGo to Add-ons -> Secrets and provide your W&B access token. Use the Label name as WANDB. \\nGet your W&B access token from here: https://wandb.ai/authorize\"\n    )\n","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:46.001237Z","iopub.execute_input":"2022-02-26T13:34:46.003382Z","iopub.status.idle":"2022-02-26T13:34:46.252432Z","shell.execute_reply.started":"2022-02-26T13:34:46.003346Z","shell.execute_reply":"2022-02-26T13:34:46.251711Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"FOLD = 1  # which fold to train\nDIM = 512\nMODEL = \"yolov5x\"\nBATCH = 24\nEPOCHS = 25\nOPTMIZER = \"SGD\"\n\nPROJECT = \"happywhale-det-public\"  # w&b in yolov5\nNAME = f\"{MODEL}-dim{DIM}-fold{FOLD}_test01_allfin3\"  # w&b for yolov5\n\nROOT_DIR = \"../input/happy-whale-and-dolphin/train_images\"\nIMAGE_DIR = \"/kaggle/data1/images\"  # directory to save images\nLABEL_DIR = \"/kaggle/data1/labels\"  # directory to save labels\n","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:46.253729Z","iopub.execute_input":"2022-02-26T13:34:46.254122Z","iopub.status.idle":"2022-02-26T13:34:46.259943Z","shell.execute_reply.started":"2022-02-26T13:34:46.254087Z","shell.execute_reply":"2022-02-26T13:34:46.259281Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Create Directories","metadata":{}},{"cell_type":"code","source":"!mkdir -p {IMAGE_DIR}\n!mkdir -p {LABEL_DIR}","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:46.262696Z","iopub.execute_input":"2022-02-26T13:34:46.263012Z","iopub.status.idle":"2022-02-26T13:34:47.590474Z","shell.execute_reply.started":"2022-02-26T13:34:46.262978Z","shell.execute_reply":"2022-02-26T13:34:47.589529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Get Paths","metadata":{}},{"cell_type":"code","source":"# Train Data\ndf = pd.read_csv(\"/kaggle/input/backfin-annotations/backfin_annotations.csv\")\ndf.columns = [\"image_id\", \"x\", \"y\", \"w\", \"h\"]\ndf[\"old_image_path\"] = f\"{ROOT_DIR}/\" + df.image_id.astype(str)\ndf[\"image_path\"] = f\"{IMAGE_DIR}/\" + df.image_id\ndf[\"label_path\"] = f\"{LABEL_DIR}/\" + df.image_id.str.replace(\"jpg\", \"txt\")\ndf.head(2)\n","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.592815Z","iopub.execute_input":"2022-02-26T13:34:47.593612Z","iopub.status.idle":"2022-02-26T13:34:47.627926Z","shell.execute_reply.started":"2022-02-26T13:34:47.593570Z","shell.execute_reply":"2022-02-26T13:34:47.627236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ✏️ Write Images\n* We need to copy the Images to Current Directory(`/kaggle/working`) as `/kaggle/input` doesn't have **write access** which is needed for **YOLOv5**.\n* We can make this process faster using **Joblib** which uses **Parallel** computing.","metadata":{}},{"cell_type":"code","source":"def make_copy(row):\n    shutil.copyfile(row.old_image_path, row.image_path)\n    return","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.630151Z","iopub.execute_input":"2022-02-26T13:34:47.630480Z","iopub.status.idle":"2022-02-26T13:34:47.636529Z","shell.execute_reply.started":"2022-02-26T13:34:47.630442Z","shell.execute_reply":"2022-02-26T13:34:47.635837Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image_paths = df.old_image_path.tolist()\n_ = Parallel(n_jobs=-1, backend='threading')(delayed(make_copy)(row) for _, row in tqdm(df.iterrows(), total=len(df)))","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.637944Z","iopub.execute_input":"2022-02-26T13:34:47.638680Z","iopub.status.idle":"2022-02-26T13:34:47.815339Z","shell.execute_reply.started":"2022-02-26T13:34:47.638628Z","shell.execute_reply":"2022-02-26T13:34:47.812017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.listdir(\"/kaggle/\")","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:49:18.456342Z","iopub.execute_input":"2022-02-26T13:49:18.457065Z","iopub.status.idle":"2022-02-26T13:49:18.463884Z","shell.execute_reply.started":"2022-02-26T13:49:18.457024Z","shell.execute_reply":"2022-02-26T13:49:18.463074Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🔨 Helper","metadata":{}},{"cell_type":"code","source":"# check https://github.com/awsaf49/bbox for source code of following utility functions\nfrom bbox.utils import coco2yolo, coco2voc, voc2yolo, yolo2voc\nfrom bbox.utils import draw_bboxes, load_image\nfrom bbox.utils import clip_bbox, str2annot, annot2str\n\ndef get_bbox(annots):\n    bboxes = [list(annot.values()) for annot in annots]\n    return bboxes\n\ndef get_imgsize(row):\n    row['width'], row['height'] = imagesize.get(row['image_path'])\n    return row\n\nnp.random.seed(32)\ncolors = [(np.random.randint(255), np.random.randint(255), np.random.randint(255))\\\n          for idx in range(1)]","metadata":{"_kg_hide-input":false,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.816118Z","iopub.status.idle":"2022-02-26T13:34:47.816393Z","shell.execute_reply.started":"2022-02-26T13:34:47.816243Z","shell.execute_reply":"2022-02-26T13:34:47.816263Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Create BBox","metadata":{}},{"cell_type":"code","source":"def x2bbox(points):\n    xmin, ymin, xmax, ymax = points.split(\" \")#points.split(\" \")points[:, 0].min(), points[:, 1].min(), points[:, 0].max(), points[:, 1].max()\n    xmin, ymin,xmax, ymax = int(xmin), int(ymin), int(xmax), int(ymax)\n    xmax = xmin + xmax\n    ymax = ymin + ymax\n    return [[xmin, ymin, xmax, ymax]]","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.820177Z","iopub.status.idle":"2022-02-26T13:34:47.820816Z","shell.execute_reply.started":"2022-02-26T13:34:47.820549Z","shell.execute_reply":"2022-02-26T13:34:47.820574Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df[\"bbox\"] = df[\"x\"].astype(str) + \" \" +  df[\"y\"].astype(str) + \" \" + df[\"w\"].astype(str) + \" \" + df[\"h\"].astype(str)\ndf['bbox'] = df.bbox.map(x2bbox)","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.821895Z","iopub.status.idle":"2022-02-26T13:34:47.822837Z","shell.execute_reply.started":"2022-02-26T13:34:47.822565Z","shell.execute_reply":"2022-02-26T13:34:47.822591Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Get Image-Size","metadata":{}},{"cell_type":"code","source":"df = df.progress_apply(get_imgsize, axis=1)\ndisplay(df.head(2))","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.823898Z","iopub.status.idle":"2022-02-26T13:34:47.824825Z","shell.execute_reply.started":"2022-02-26T13:34:47.824530Z","shell.execute_reply":"2022-02-26T13:34:47.824556Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🏷️ Create Labels\nWe need to export our labels to **YOLO** format, with one `*.txt` file per image (if no objects in image, no `*.txt` file is required). The *.txt file specifications are:\n\n* One row per object\n* Each row is class `[x_center, y_center, width, height]` format.\n* Box coordinates must be in **normalized** `xywh` format (from `0 - 1`). If your boxes are in pixels, divide `x_center` and `width` by `image width`, and `y_center` and `height` by `image height`.\n* Class numbers are **zero-indexed** (start from `0`).\n\n> Dataset bbox format is **VOC-PASCAL** hence `[x_min, y_min, x_max, y_max]`. So, we need to convert form **VOC-PASCAL** to **YOLO** format.\n","metadata":{}},{"cell_type":"code","source":"cnt = 0\nall_bboxes = []\nbboxes_info = []\nfor row_idx in tqdm(range(df.shape[0])):\n    row = df.iloc[row_idx]\n    image_height = row.height\n    image_width = row.width\n    bboxes_voc = np.array(row.bbox).astype(np.float32).copy()\n    num_bbox = len(bboxes_voc)\n    names = [\"whale\"] * num_bbox\n    labels = np.array([0] * num_bbox)[..., None].astype(str)\n    ## Create Annotation(YOLO)\n    with open(row.label_path, \"w\") as f:\n        if num_bbox < 1:\n            annot = \"\"\n            f.write(annot)\n            cnt += 1\n            continue\n        #         bboxes_voc  = coco2voc(bboxes_coco, image_height, image_width)\n        bboxes_voc = clip_bbox(bboxes_voc, image_height, image_width)\n        bboxes_yolo = voc2yolo(bboxes_voc, image_height, image_width).astype(str)\n        all_bboxes.extend(bboxes_yolo.astype(float))\n        bboxes_info.extend([[row.image_id]] * len(bboxes_yolo))\n        annots = np.concatenate([labels, bboxes_yolo], axis=1)\n        string = annot2str(annots)\n        f.write(string)\nprint(\"Missing:\", cnt)\n","metadata":{"_kg_hide-input":false,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.825990Z","iopub.status.idle":"2022-02-26T13:34:47.826916Z","shell.execute_reply.started":"2022-02-26T13:34:47.826681Z","shell.execute_reply":"2022-02-26T13:34:47.826704Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 📁 Create Folds\n> Number of samples aren't same in each fold which can create large variance in **Cross-Validation**.","metadata":{}},{"cell_type":"code","source":"from sklearn.model_selection import KFold\nkf = KFold(n_splits=6, random_state=42, shuffle=True)\ndf = df.reset_index(drop=True)\ndf['fold'] = -1\nfor fold, (train_idx, val_idx) in enumerate(kf.split(df)):\n    df.loc[val_idx, 'fold'] = fold\ndf.fold.value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.827968Z","iopub.status.idle":"2022-02-26T13:34:47.828756Z","shell.execute_reply.started":"2022-02-26T13:34:47.828501Z","shell.execute_reply":"2022-02-26T13:34:47.828526Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = df[(df[\"x\"] > 0) & (df[\"y\"] > 0) & (df[\"w\"] > 0) & (df[\"h\"] > 0)].reset_index(drop = True)","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.829927Z","iopub.status.idle":"2022-02-26T13:34:47.830790Z","shell.execute_reply.started":"2022-02-26T13:34:47.830531Z","shell.execute_reply":"2022-02-26T13:34:47.830555Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ⭕ BBox Distribution","metadata":{}},{"cell_type":"code","source":"bbox_df = pd.DataFrame(np.concatenate([bboxes_info, all_bboxes], axis=1),\n             columns=['image_id','xmid','ymid','w','h'])\nbbox_df[['xmid','ymid','w','h']] = bbox_df[['xmid','ymid','w','h']].astype(float)\nbbox_df['area'] = bbox_df.w * bbox_df.h\nbbox_df = bbox_df.merge(df[['image_id','fold']], on='image_id', how='left')\nbbox_df.head(2)","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.831852Z","iopub.status.idle":"2022-02-26T13:34:47.832705Z","shell.execute_reply.started":"2022-02-26T13:34:47.832451Z","shell.execute_reply":"2022-02-26T13:34:47.832475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## `x_center` Vs `y_center`","metadata":{}},{"cell_type":"code","source":"from scipy.stats import gaussian_kde\n\nall_bboxes = np.array(all_bboxes)\n\nx_val = all_bboxes[...,0]\ny_val = all_bboxes[...,1]\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\n# ax.axis('off')\nax.scatter(x_val, y_val, c=z, s=50, cmap='viridis')\n# ax.set_xlabel('x_mid')\n# ax.set_ylabel('y_mid')\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.833767Z","iopub.status.idle":"2022-02-26T13:34:47.834656Z","shell.execute_reply.started":"2022-02-26T13:34:47.834393Z","shell.execute_reply":"2022-02-26T13:34:47.834417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## `width` Vs `height`","metadata":{}},{"cell_type":"code","source":"x_val = all_bboxes[...,2]\ny_val = all_bboxes[...,3]\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\n# ax.axis('off')\nax.scatter(x_val, y_val, c=z, s=50, cmap='viridis')\n# ax.set_xlabel('bbox_width')\n# ax.set_ylabel('bbox_height')\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.835734Z","iopub.status.idle":"2022-02-26T13:34:47.836685Z","shell.execute_reply.started":"2022-02-26T13:34:47.836405Z","shell.execute_reply":"2022-02-26T13:34:47.836432Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Area","metadata":{}},{"cell_type":"code","source":"import matplotlib as mpl\nimport seaborn as sns\n\nf, ax = plt.subplots(figsize=(12, 6))\nsns.despine(f)\n\nsns.histplot(\n    bbox_df,\n    x=\"area\", hue=\"fold\",\n    multiple=\"stack\",\n    palette=\"viridis\",\n    edgecolor=\".3\",\n    linewidth=.5,\n    log_scale=True,\n)\nax.xaxis.set_major_formatter(mpl.ticker.ScalarFormatter())","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.837768Z","iopub.status.idle":"2022-02-26T13:34:47.838661Z","shell.execute_reply.started":"2022-02-26T13:34:47.838403Z","shell.execute_reply":"2022-02-26T13:34:47.838429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🌈 Visualization","metadata":{}},{"cell_type":"code","source":"df2 = df.sample(100) # takes samples with bbox\ny = 2\nx = 5\nplt.figure(figsize=(4 * x, 4 * y))\nfor idx in range(x*y):\n    row = df2.iloc[idx]\n    img           = load_image(row.image_path)\n    img           = cv2.resize(img, (512, 512))\n    image_height  = row.height\n    image_width   = row.width\n    with open(row.label_path) as f:\n        annot = str2annot(f.read())\n    bboxes_yolo = annot[...,1:]\n    labels      = annot[..., 0].astype(int).tolist()\n    names         = ['whale']*len(bboxes_yolo)\n    plt.subplot(y, x, idx+1)\n    plt.imshow(draw_bboxes(img = img,\n                           bboxes = bboxes_yolo, \n                           classes = names,\n                           class_ids = labels,\n                           class_name = True, \n                           colors = colors, \n                           bbox_format = 'yolo',\n                           line_thickness = 2))\n    plt.axis('OFF')\nplt.tight_layout()\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.839756Z","iopub.status.idle":"2022-02-26T13:34:47.840659Z","shell.execute_reply.started":"2022-02-26T13:34:47.840359Z","shell.execute_reply":"2022-02-26T13:34:47.840403Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🍚 Dataset","metadata":{}},{"cell_type":"code","source":"train_files = []\nval_files   = []\ntrain_df = df.query(\"fold!=@FOLD\")\nvalid_df = df.query(\"fold==@FOLD\")\ntrain_files += list(train_df.image_path.unique())\nval_files += list(valid_df.image_path.unique())\nlen(train_files), len(val_files)","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.841904Z","iopub.status.idle":"2022-02-26T13:34:47.842325Z","shell.execute_reply.started":"2022-02-26T13:34:47.842087Z","shell.execute_reply":"2022-02-26T13:34:47.842109Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ⚙️ Configuration\nThe dataset config file requires\n1. The dataset root directory path and relative paths to `train / val / test` image directories (or *.txt files with image paths)\n2. The number of classes `nc` and \n3. A list of class `names`:`['cots']`","metadata":{}},{"cell_type":"code","source":"import yaml\n\ncwd = '/kaggle/working/'\n\nwith open(os.path.join( cwd , 'train.txt'), 'w') as f:\n    for path in train_df.image_path.tolist():\n        f.write(path+'\\n')\n            \nwith open(os.path.join(cwd , 'val.txt'), 'w') as f:\n    for path in valid_df.image_path.tolist():\n        f.write(path+'\\n')\n\ndata = dict(\n    path  = cwd,\n    train =  os.path.join( cwd , 'train.txt') ,\n    val   =  os.path.join( cwd , 'val.txt' ),\n    nc    = 1,\n    names = ['whale'],\n    )\n\nwith open(os.path.join( cwd , 'happywhale.yaml'), 'w') as outfile:\n    yaml.dump(data, outfile, default_flow_style=False)\n\nf = open(os.path.join( cwd , 'happywhale.yaml'), 'r')\nprint('\\nyaml:')\nprint(f.read())","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.843586Z","iopub.status.idle":"2022-02-26T13:34:47.844136Z","shell.execute_reply.started":"2022-02-26T13:34:47.843899Z","shell.execute_reply":"2022-02-26T13:34:47.843924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%writefile /kaggle/working/hyp.yaml\nlr0: 0.05  # initial learning rate (SGD=1E-2, Adam=1E-3)\nlrf: 0.1  # final OneCycleLR learning rate (lr0 * lrf)\nmomentum: 0.937  # SGD momentum/Adam beta1\nweight_decay: 0.0005  # optimizer weight decay 5e-4\nwarmup_epochs: 3.0  # warmup epochs (fractions ok)\nwarmup_momentum: 0.8  # warmup initial momentum\nwarmup_bias_lr: 0.1  # warmup initial bias lr\nbox: 0.05  # box loss gain\ncls: 0.5  # cls loss gain\ncls_pw: 1.0  # cls BCELoss positive_weight\nobj: 1.0  # obj loss gain (scale with pixels)\nobj_pw: 1.0  # obj BCELoss positive_weight\niou_t: 0.20  # IoU training threshold\nanchor_t: 4.0  # anchor-multiple threshold\n# anchors: 3  # anchors per output layer (0 to ignore)\nfl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)\nhsv_h: 0.015  # image HSV-Hue augmentation (fraction)\nhsv_s: 0.7  # image HSV-Saturation augmentation (fraction)\nhsv_v: 0.4  # image HSV-Value augmentation (fraction)\ndegrees: 30.0  # image rotation (+/- deg)\ntranslate: 0.10  # image translation (+/- fraction)\nscale: 0.75  # image scale (+/- gain)\nshear: 10.0  # image shear (+/- deg)\nperspective: 0.0  # image perspective (+/- fraction), range 0-0.001\nflipud: 0.05  # image flip up-down (probability)\nfliplr: 0.5  # image flip left-right (probability)\nmosaic: 0.75  # image mosaic (probability)\nmixup: 0.0 # image mixup (probability)\ncopy_paste: 0.0  # segment copy-paste (probability)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.845372Z","iopub.status.idle":"2022-02-26T13:34:47.846110Z","shell.execute_reply.started":"2022-02-26T13:34:47.845856Z","shell.execute_reply":"2022-02-26T13:34:47.845881Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 📦 [YOLOv5](https://github.com/ultralytics/yolov5/)\n<div align=center><img src=\"https://github.com/ultralytics/yolov5/releases/download/v1.0/splash.jpg\" width=600>","metadata":{}},{"cell_type":"code","source":"%cd /kaggle/working\n!rm -r /kaggle/working/yolov5\n# !git clone https://github.com/ultralytics/yolov5 # clone\n# !cp -r /kaggle/input/yolov5-lib-ds /kaggle/working/yolov5\n!cp -r /kaggle/input/happywhale-boundingbox-yolov5-ds/yolov5 /kaggle/working/yolov5\n%cd yolov5\n%pip install -qr requirements.txt  # install\n\nfrom yolov5 import utils\n_ = utils.notebook_init()  # check","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.848361Z","iopub.status.idle":"2022-02-26T13:34:47.849272Z","shell.execute_reply.started":"2022-02-26T13:34:47.849024Z","shell.execute_reply":"2022-02-26T13:34:47.849049Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🚅 Training\nUncomment following cell for **training**. I'm using previously **trained** weights from earlier **version** of this notebook.","metadata":{}},{"cell_type":"code","source":"!python train.py --img {DIM}\\\n--batch {BATCH}\\\n--epochs {EPOCHS}\\\n--optimizer {OPTMIZER}\\\n--data /kaggle/working/happywhale.yaml\\\n--hyp /kaggle/working/hyp.yaml\\\n--weights {MODEL}.pt\\\n--project {PROJECT} --name {NAME}\\\n--exist-ok","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.850342Z","iopub.status.idle":"2022-02-26T13:34:47.851233Z","shell.execute_reply.started":"2022-02-26T13:34:47.851004Z","shell.execute_reply":"2022-02-26T13:34:47.851027Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ✨ Overview\n<span style=\"color: #000508; font-family: Segoe UI; font-size: 1.5em; font-weight: 300;\"><a href=\"https://wandb.ai/awsaf49/happywhale-det-public\">View the Complete Dashboard Here ⮕</a></span>\n![image.png](attachment:6f95d62a-f459-4978-aa22-7810d09d2a54.png)","metadata":{},"attachments":{"6f95d62a-f459-4978-aa22-7810d09d2a54.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"## Output Files","metadata":{}},{"cell_type":"code","source":"OUTPUT_DIR = '{}/{}'.format(PROJECT, NAME)\n!ls {OUTPUT_DIR}","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.852291Z","iopub.status.idle":"2022-02-26T13:34:47.853009Z","shell.execute_reply.started":"2022-02-26T13:34:47.852746Z","shell.execute_reply":"2022-02-26T13:34:47.852771Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls {OUTPUT_DIR}/weights/best.pt","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.854302Z","iopub.status.idle":"2022-02-26T13:34:47.854721Z","shell.execute_reply.started":"2022-02-26T13:34:47.854483Z","shell.execute_reply":"2022-02-26T13:34:47.854506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🔭 Batch Image","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.figure(figsize = (10, 10))\nplt.imshow(plt.imread(f'{OUTPUT_DIR}/train_batch0.jpg'))\n\nplt.figure(figsize = (10, 10))\nplt.imshow(plt.imread(f'{OUTPUT_DIR}/train_batch1.jpg'))\n\nplt.figure(figsize = (10, 10))\nplt.imshow(plt.imread(f'{OUTPUT_DIR}/train_batch2.jpg'))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.855838Z","iopub.status.idle":"2022-02-26T13:34:47.856656Z","shell.execute_reply.started":"2022-02-26T13:34:47.856399Z","shell.execute_reply":"2022-02-26T13:34:47.856423Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Score Vs Epoch","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(30,15))\nplt.axis('off')\nplt.imshow(plt.imread(f'{OUTPUT_DIR}/results.png'));","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.857929Z","iopub.status.idle":"2022-02-26T13:34:47.858408Z","shell.execute_reply.started":"2022-02-26T13:34:47.858120Z","shell.execute_reply":"2022-02-26T13:34:47.858142Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Confusion Matrix","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(12,10))\nplt.axis('off')\nplt.imshow(plt.imread(f'{OUTPUT_DIR}/confusion_matrix.png'));","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.860385Z","iopub.status.idle":"2022-02-26T13:34:47.860937Z","shell.execute_reply.started":"2022-02-26T13:34:47.860694Z","shell.execute_reply":"2022-02-26T13:34:47.860719Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Metrics","metadata":{}},{"cell_type":"code","source":"for metric in ['F1', 'PR', 'P', 'R']:\n    print(f'Metric: {metric}')\n    plt.figure(figsize=(12,10))\n    plt.axis('off')\n    plt.imshow(plt.imread(f'{OUTPUT_DIR}/{metric}_curve.png'));\n    plt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-26T13:34:47.862296Z","iopub.status.idle":"2022-02-26T13:34:47.863179Z","shell.execute_reply.started":"2022-02-26T13:34:47.862948Z","shell.execute_reply":"2022-02-26T13:34:47.862971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Whale and Dolphin** Data 🐋🐬","metadata":{}},{"cell_type":"code","source":"class CFG:\n    seed = 42\n    base_path = '/kaggle/input/happy-whale-and-dolphin'","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.864225Z","iopub.status.idle":"2022-02-26T13:34:47.865010Z","shell.execute_reply.started":"2022-02-26T13:34:47.864768Z","shell.execute_reply":"2022-02-26T13:34:47.864794Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_output = '/kaggle/working/output/train'\ntest_output = '/kaggle/working/output/test'","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.866179Z","iopub.status.idle":"2022-02-26T13:34:47.866955Z","shell.execute_reply.started":"2022-02-26T13:34:47.866708Z","shell.execute_reply":"2022-02-26T13:34:47.866733Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df2 = pd.read_csv(f\"/kaggle/input/happywhale-data-distribution/train.csv\")\ndf2[\"image_id\"] = df2[\"image\"]\ndf2[\"label_path\"] = train_output + \"/labels/\" + df2[\"image_id\"].str.replace('jpg','txt')\n\n\ntest_df2 = pd.read_csv(f\"/kaggle/input/happywhale-data-distribution/test.csv\")\ntest_df2[\"image_id\"] = test_df2[\"image\"]\ntest_df2[\"label_path\"] = test_output + \"/labels/\" + test_df2[\"image_id\"].str.replace('jpg','txt')\n\nprint(\"Train Images: {:,} | Test Images: {:,}\".format(len(df2), len(test_df2)))\n","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.868126Z","iopub.status.idle":"2022-02-26T13:34:47.868758Z","shell.execute_reply.started":"2022-02-26T13:34:47.868506Z","shell.execute_reply":"2022-02-26T13:34:47.868529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Predict on **Train**","metadata":{}},{"cell_type":"code","source":"!rm -rf {train_output}\n!mkdir -p {train_output}","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.869929Z","iopub.status.idle":"2022-02-26T13:34:47.870541Z","shell.execute_reply.started":"2022-02-26T13:34:47.870309Z","shell.execute_reply":"2022-02-26T13:34:47.870334Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!python detect.py --img {DIM}\\\n--source /kaggle/input/happy-whale-and-dolphin/train_images\\\n--weights {OUTPUT_DIR}/weights/best.pt\\\n--project /kaggle/working/output --name train\\\n--conf 0.01 --iou 0.4 --max-det 1\\\n--save-txt --save-conf\\\n--nosave\\\n--half\\\n--exist-ok","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.871737Z","iopub.status.idle":"2022-02-26T13:34:47.872357Z","shell.execute_reply.started":"2022-02-26T13:34:47.872124Z","shell.execute_reply":"2022-02-26T13:34:47.872148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Visualize **Train**","metadata":{}},{"cell_type":"code","source":"label_paths = glob.glob(f\"{train_output}/labels/*\")\nnp.random.shuffle(label_paths)\n\ny = 2\nx = 5\nplt.figure(figsize=(4 * x, 4 * y))\nfor idx in range(x * y):\n    label_path = label_paths[idx]\n    image_id = label_path.split(\"/\")[-1].replace(\"txt\", \"jpg\")\n    row = df2[df2.image_id == image_id].squeeze()\n    image_path = f\"/kaggle/input/happy-whale-and-dolphin/train_images/{image_id}\"\n    img = load_image(image_path)\n    img = cv2.resize(img, (512, 512))\n    image_height = row.height\n    image_width = row.width\n    with open(label_path) as f:\n        data = f.read().strip().split(' ')\n    annot = np.array(data).reshape(-1, 6).astype(float)\n    bboxes_yolo = annot[..., 1:]\n    labels = annot[..., 0].astype(int).tolist()\n    names = [\"whale/dolphin\"] * len(bboxes_yolo)\n    plt.subplot(y, x, idx + 1)\n    plt.imshow(\n        draw_bboxes(\n            img=img,\n            bboxes=bboxes_yolo,\n            classes=names,\n            class_ids=labels,\n            class_name=True,\n            colors=colors,\n            bbox_format=\"yolo\",\n            line_thickness=2,\n        )\n    )\n    plt.axis(\"OFF\")\nplt.tight_layout()\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.873553Z","iopub.status.idle":"2022-02-26T13:34:47.874193Z","shell.execute_reply.started":"2022-02-26T13:34:47.873959Z","shell.execute_reply":"2022-02-26T13:34:47.873984Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Predict on **Test**","metadata":{}},{"cell_type":"code","source":"!rm -rf {test_output}\n!mkdir -p {test_output}","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.875359Z","iopub.status.idle":"2022-02-26T13:34:47.875990Z","shell.execute_reply.started":"2022-02-26T13:34:47.875744Z","shell.execute_reply":"2022-02-26T13:34:47.875768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!python detect.py --img {DIM}\\\n--source /kaggle/input/happy-whale-and-dolphin/test_images\\\n--weights {OUTPUT_DIR}/weights/best.pt\\\n--project /kaggle/working/output --name test\\\n--conf 0.001 --iou 0.4 --max-det 1\\\n--save-txt --save-conf\\\n--nosave\\\n--half\\\n--exist-ok","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.877151Z","iopub.status.idle":"2022-02-26T13:34:47.877806Z","shell.execute_reply.started":"2022-02-26T13:34:47.877542Z","shell.execute_reply":"2022-02-26T13:34:47.877566Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Visualize **Test**","metadata":{}},{"cell_type":"code","source":"label_paths = glob.glob(f\"{test_output}/labels/*\")\nnp.random.shuffle(label_paths)\n\ny = 2\nx = 5\nplt.figure(figsize=(4 * x, 4 * y))\nfor idx in range(x * y):\n    label_path = label_paths[idx]\n    image_id = label_path.split(\"/\")[-1].replace(\"txt\", \"jpg\")\n    row = test_df2[test_df2.image_id == image_id].squeeze()\n    image_path = f\"/kaggle/input/happy-whale-and-dolphin/test_images/{image_id}\"\n    img = load_image(image_path)\n    img = cv2.resize(img, (512, 512))\n    image_height = row.height\n    image_width = row.width\n    with open(label_path) as f:\n        data = f.read().strip().split(' ')\n    annot = np.array(data).reshape(-1, 6).astype(float)\n    bboxes_yolo = annot[..., 1:]\n    labels = annot[..., 0].astype(int).tolist()\n    names = [\"whale/dolphin\"] * len(bboxes_yolo)\n    plt.subplot(y, x, idx + 1)\n    plt.imshow(\n        draw_bboxes(\n            img=img,\n            bboxes=bboxes_yolo,\n            classes=names,\n            class_ids=labels,\n            class_name=True,\n            colors=colors,\n            bbox_format=\"yolo\",\n            line_thickness=2,\n        )\n    )\n    plt.axis(\"OFF\")\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.878999Z","iopub.status.idle":"2022-02-26T13:34:47.879609Z","shell.execute_reply.started":"2022-02-26T13:34:47.879376Z","shell.execute_reply":"2022-02-26T13:34:47.879399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Process **Annotations**","metadata":{}},{"cell_type":"code","source":"def get_annot(row, with_conf=True):\n    try:\n        with open(row['label_path'], 'r') as f:\n            data = f.read().strip().split(' ')\n    except:\n        return row # don't have any label\n    data = np.array(data).reshape(-1, 6 if with_conf else 5).astype(float)\n    if with_conf:\n        bbox = data[:, 1:-1]\n        conf = data[:, -1]\n        row['conf'] = conf\n    else:\n        bbox = data[:, 1:]\n    bbox = yolo2voc(bbox, row['height'], row['width'])\n    bbox = bbox.round().astype(np.int32)\n    row['bbox'] = bbox\n    return row","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.880807Z","iopub.status.idle":"2022-02-26T13:34:47.881423Z","shell.execute_reply.started":"2022-02-26T13:34:47.881186Z","shell.execute_reply":"2022-02-26T13:34:47.881210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df2 = df2.progress_apply(get_annot, axis=1)\ndf2.to_csv('/kaggle/working/train.csv',index=False)\ndisplay(df2.head())\n\ntest_df2 = test_df2.progress_apply(get_annot, axis=1)\ntest_df2.to_csv('/kaggle/working/test.csv',index=False)\ndisplay(test_df2.head())","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.882612Z","iopub.status.idle":"2022-02-26T13:34:47.883250Z","shell.execute_reply.started":"2022-02-26T13:34:47.883014Z","shell.execute_reply":"2022-02-26T13:34:47.883038Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ✂️ Remove Files","metadata":{}},{"cell_type":"code","source":"!rm -r {IMAGE_DIR}\n!rm -r {LABEL_DIR}","metadata":{"execution":{"iopub.status.busy":"2022-02-26T13:34:47.884395Z","iopub.status.idle":"2022-02-26T13:34:47.885033Z","shell.execute_reply.started":"2022-02-26T13:34:47.884796Z","shell.execute_reply":"2022-02-26T13:34:47.884820Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 💡 Reference\n* [Humpback Whale Identification - Fluke Location](https://www.kaggle.com/martinpiotte/humpback-whale-identification-fluke-location)","metadata":{}},{"cell_type":"markdown","source":"<div align=\"center\"><img src=\"https://www.pngall.com/wp-content/uploads/2018/04/Under-Construction-PNG-File.png\" width=400>","metadata":{}}]}