{"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":"[](http://)","metadata":{}},{"cell_type":"markdown","source":"# Something in the wrong way, pay attention to two stadge methods!","metadata":{}},{"cell_type":"markdown","source":"![image.png](attachment:467ce382-4c53-4ae5-8842-dd0ec4b6eabe.png)","metadata":{},"attachments":{"467ce382-4c53-4ae5-8842-dd0ec4b6eabe.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"## 📒 Notebooks:\n* Train: [Great-Barrier-Reef: YOLOv5 [train] 🌊](https://www.kaggle.com/awsaf49/great-barrier-reef-yolov5-train)\n* Infer: [Great-Barrier-Reef: YOLOv5 [infer] 🌊](https://www.kaggle.com/awsaf49/great-barrier-reef-yolov5-infer)","metadata":{}},{"cell_type":"markdown","source":"# 🚩 Version Info\n| Version | Model | Conf | IoU | LB  | Comment\n|---|---|---|---|---|---|\n| v25 | YOLOv5s | 0.15 | 0.50 | 0.453 |  |\n| v30 | YOLOv5s | 0.19 | 0.45 | 0.433 | tta |\n","metadata":{}},{"cell_type":"markdown","source":"# 🛠 Install Libraries","metadata":{}},{"cell_type":"code","source":"# bbox-utility, check https://github.com/awsaf49/bbox for source code\n!pip install -q /kaggle/input/loguru-lib-ds/loguru-0.5.3-py3-none-any.whl\n!pip install -q /kaggle/input/bbox-lib-ds","metadata":{"_kg_hide-output":true,"_kg_hide-input":false,"execution":{"iopub.status.busy":"2022-02-05T11:34:49.640385Z","iopub.execute_input":"2022-02-05T11:34:49.641104Z","iopub.status.idle":"2022-02-05T11:35:50.14462Z","shell.execute_reply.started":"2022-02-05T11:34:49.640998Z","shell.execute_reply":"2022-02-05T11:35:50.143518Z"},"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\ntqdm.pandas()\nimport pandas as pd\nimport os\nimport cv2\nimport matplotlib.pyplot as plt\nimport glob\nimport shutil\nimport sys\nsys.path.append('../input/tensorflow-great-barrier-reef')\nimport torch\nfrom PIL import Image","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-02-05T11:35:50.146653Z","iopub.execute_input":"2022-02-05T11:35:50.146938Z","iopub.status.idle":"2022-02-05T11:35:51.586199Z","shell.execute_reply.started":"2022-02-05T11:35:50.146905Z","shell.execute_reply":"2022-02-05T11:35:51.585399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 📌 Key-Points\n* One have to submit prediction using the provided **python time-series API**, which makes this competition different from previous Object Detection Competitions.\n* Each prediction row needs to include all bounding boxes for the image. Submission is format seems also **COCO** which means `[x_min, y_min, width, height]`\n* Copmetition metric `F2` tolerates some false positives(FP) in order to ensure very few starfish are missed. Which means tackling **false negatives(FN)** is more important than false positives(FP). \n$$F2 = 5 \\cdot \\frac{precision \\cdot recall}{4\\cdot precision + recall}$$","metadata":{}},{"cell_type":"markdown","source":"## Please Upvote if you find this Helpful","metadata":{}},{"cell_type":"markdown","source":"# 📖 Meta Data\n* `train_images/` - Folder containing training set photos of the form `video_{video_id}/{video_frame}.jpg`.\n\n* `[train/test].csv` - Metadata for the images. As with other test files, most of the test metadata data is only available to your notebook upon submission. Just the first few rows available for download.\n\n* `video_id` - ID number of the video the image was part of. The video ids are not meaningfully ordered.\n* `video_frame` - The frame number of the image within the video. Expect to see occasional gaps in the frame number from when the diver surfaced.\n* `sequence` - ID of a gap-free subset of a given video. The sequence ids are not meaningfully ordered.\n* `sequence_frame` - The frame number within a given sequence.\n* `image_id` - ID code for the image, in the format `{video_id}-{video_frame}`\n* `annotations` - The bounding boxes of any starfish detections in a string format that can be evaluated directly with Python. Does not use the same format as the predictions you will submit. Not available in test.csv. A bounding box is described by the pixel coordinate `(x_min, y_min)` of its lower left corner within the image together with its `width` and `height` in pixels --> (COCO format).","metadata":{}},{"cell_type":"markdown","source":"###### ROOT_DIR  = '/kaggle/input/tensorflow-great-barrier-reef/'\n# CKPT_DIR  = '/kaggle/input/greatbarrierreef-yolov5-train-ds'\nCKPT_PATH = '/kaggle/input/leonv5inferv5s60/best.pt' # by @steamedsheep\nIMG_SIZE  = 6400\nCONF      = 0.30\nIOU       = 0.50\nAUGMENT   = True","metadata":{"execution":{"iopub.status.busy":"2022-01-03T06:34:55.27914Z","iopub.execute_input":"2022-01-03T06:34:55.279794Z","iopub.status.idle":"2022-01-03T06:34:55.409887Z","shell.execute_reply.started":"2022-01-03T06:34:55.279751Z","shell.execute_reply":"2022-01-03T06:34:55.409186Z"}}},{"cell_type":"code","source":"# Train Data\ndf = pd.read_csv(f'/kaggle/input/tensorflow-great-barrier-reef/train.csv')\ndf['image_path'] = f'/kaggle/input/tensorflow-great-barrier-reef/train_images/video_'+df.video_id.astype(str)+'/'+df.video_frame.astype(str)+'.jpg'\ndf['annotations'] = df['annotations'].progress_apply(eval)\ndisplay(df.head(2))","metadata":{"execution":{"iopub.status.busy":"2022-02-05T11:35:51.588236Z","iopub.execute_input":"2022-02-05T11:35:51.588788Z","iopub.status.idle":"2022-02-05T11:35:52.091604Z","shell.execute_reply.started":"2022-02-05T11:35:51.588738Z","shell.execute_reply":"2022-02-05T11:35:52.090729Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Number of BBoxes","metadata":{}},{"cell_type":"code","source":"df['num_bbox'] = df['annotations'].progress_apply(lambda x: len(x))\ndata = (df.num_bbox>0).value_counts()/len(df)*100\nprint(f\"No BBox: {data[0]:0.2f}% | With BBox: {data[1]:0.2f}%\")","metadata":{"execution":{"iopub.status.busy":"2022-02-05T11:35:52.094024Z","iopub.execute_input":"2022-02-05T11:35:52.094344Z","iopub.status.idle":"2022-02-05T11:35:52.1997Z","shell.execute_reply.started":"2022-02-05T11:35:52.094303Z","shell.execute_reply":"2022-02-05T11:35:52.198741Z"},"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, voc2coco\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":true,"execution":{"iopub.status.busy":"2022-02-05T11:35:52.200858Z","iopub.execute_input":"2022-02-05T11:35:52.201079Z","iopub.status.idle":"2022-02-05T11:35:52.99215Z","shell.execute_reply.started":"2022-02-05T11:35:52.201053Z","shell.execute_reply":"2022-02-05T11:35:52.991304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 📦 [YOLOv5](https://github.com/ultralytics/yolov5/)\n<img src=\"https://github.com/ultralytics/yolov5/releases/download/v1.0/splash.jpg\" width=800>","metadata":{}},{"cell_type":"code","source":"!mkdir -p /root/.config/Ultralytics\n!cp /kaggle/input/yolov5-font/Arial.ttf /root/.config/Ultralytics/","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-05T11:35:52.993508Z","iopub.execute_input":"2022-02-05T11:35:52.993735Z","iopub.status.idle":"2022-02-05T11:35:54.520898Z","shell.execute_reply.started":"2022-02-05T11:35:52.993707Z","shell.execute_reply":"2022-02-05T11:35:54.519582Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def load_model(ckpt_path, conf=0.25, iou=0.50):\n    model = torch.hub.load('/kaggle/input/yolov5-lib-ds',\n                           'custom',\n                           path=ckpt_path,\n                           source='local',\n                           force_reload=True)  # local repo\n    model.conf = conf  # NMS confidence threshold\n    model.iou  = iou  # NMS IoU threshold\n    model.classes = None   # (optional list) filter by class, i.e. = [0, 15, 16] for persons, cats and dogs\n    model.multi_label = False  # NMS multiple labels per box\n    model.max_det = 1000  # maximum number of detections per image\n    return model","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-05T11:35:54.523166Z","iopub.execute_input":"2022-02-05T11:35:54.523507Z","iopub.status.idle":"2022-02-05T11:35:54.530122Z","shell.execute_reply.started":"2022-02-05T11:35:54.523473Z","shell.execute_reply":"2022-02-05T11:35:54.529179Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 🔭 Inference","metadata":{}},{"cell_type":"markdown","source":"## Helper","metadata":{}},{"cell_type":"code","source":"def predict(model, img, size=768, augment=False):\n    height, width = img.shape[:2]\n    results = model(img, size=size, augment=augment)  # custom inference size\n    preds   = results.pandas().xyxy[0]\n    bboxes  = preds[['xmin','ymin','xmax','ymax']].values\n    if len(bboxes):\n        bboxes  = voc2coco(bboxes,height,width).astype(int)\n        confs   = preds.confidence.values\n        return bboxes, confs\n    else:\n        return [],[]\n    \ndef format_prediction(bboxes, confs):\n    annot = ''\n    if len(bboxes)>0:\n        for idx in range(len(bboxes)):\n            xmin, ymin, w, h = bboxes[idx]\n            conf             = confs[idx]\n            annot += f'{conf} {xmin} {ymin} {w} {h}'\n            annot +=' '\n        annot = annot.strip(' ')\n    return annot\n\ndef show_img(img, bboxes, bbox_format='yolo'):\n    names  = ['starfish']*len(bboxes)\n    labels = [0]*len(bboxes)\n    img    = draw_bboxes(img = img,\n                           bboxes = bboxes, \n                           classes = names,\n                           class_ids = labels,\n                           class_name = True, \n                           colors = colors, \n                           bbox_format = bbox_format,\n                           line_thickness = 2)\n    return Image.fromarray(img).resize((800, 400))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-05T11:35:54.531777Z","iopub.execute_input":"2022-02-05T11:35:54.532069Z","iopub.status.idle":"2022-02-05T11:35:54.547123Z","shell.execute_reply.started":"2022-02-05T11:35:54.532029Z","shell.execute_reply":"2022-02-05T11:35:54.546373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Run Inference on **Train**","metadata":{}},{"cell_type":"code","source":"CKPT_PATH = '../input/yolov5s6/f2_sub2.pt'\nCONF = 0.30\nIOU = 0.50\nIMG_SIZE = 6400\nAUGMENT = False","metadata":{"execution":{"iopub.status.busy":"2022-02-05T11:35:54.548417Z","iopub.execute_input":"2022-02-05T11:35:54.548741Z","iopub.status.idle":"2022-02-05T11:35:54.559301Z","shell.execute_reply.started":"2022-02-05T11:35:54.548699Z","shell.execute_reply":"2022-02-05T11:35:54.558674Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pwd","metadata":{"execution":{"iopub.status.busy":"2022-02-05T11:35:54.56257Z","iopub.execute_input":"2022-02-05T11:35:54.56286Z","iopub.status.idle":"2022-02-05T11:35:54.57682Z","shell.execute_reply.started":"2022-02-05T11:35:54.562819Z","shell.execute_reply":"2022-02-05T11:35:54.576003Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = load_model(CKPT_PATH, conf=CONF, iou=IOU)\nimage_paths = df[df.num_bbox>1].sample(100).image_path.tolist()\nfor idx, path in enumerate(image_paths):\n    img = cv2.imread(path)[...,::-1]\n    bboxes, confis = predict(model, img, size=IMG_SIZE, augment=AUGMENT)\n    display(show_img(img, bboxes, bbox_format='coco'))\n    if idx>5:\n        break","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-05T11:35:54.578293Z","iopub.execute_input":"2022-02-05T11:35:54.578869Z","iopub.status.idle":"2022-02-05T11:37:06.200793Z","shell.execute_reply.started":"2022-02-05T11:35:54.578828Z","shell.execute_reply":"2022-02-05T11:37:06.199969Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Init `Env`","metadata":{}},{"cell_type":"code","source":"import greatbarrierreef\nenv = greatbarrierreef.make_env()# initialize the environment\niter_test = env.iter_test()      # an iterator which loops over the test set and sample submission","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-05T11:37:06.202469Z","iopub.execute_input":"2022-02-05T11:37:06.202922Z","iopub.status.idle":"2022-02-05T11:37:06.227815Z","shell.execute_reply.started":"2022-02-05T11:37:06.202873Z","shell.execute_reply":"2022-02-05T11:37:06.226828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"iter_test = env.iter_test()      # an iterator which loops over the test set and sample submission","metadata":{"execution":{"iopub.status.busy":"2022-02-05T11:37:06.229435Z","iopub.execute_input":"2022-02-05T11:37:06.229799Z","iopub.status.idle":"2022-02-05T11:37:06.234707Z","shell.execute_reply.started":"2022-02-05T11:37:06.22975Z","shell.execute_reply":"2022-02-05T11:37:06.233852Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Run Inference on **Test**","metadata":{}},{"cell_type":"code","source":"model = load_model(CKPT_PATH, conf=CONF, iou=IOU)\nfor idx, (img, pred_df) in enumerate(tqdm(iter_test)):\n    bboxes, confs  = predict(model, img, size=IMG_SIZE, augment=AUGMENT)\n    annot          = format_prediction(bboxes, confs)\n    pred_df['annotations'] = annot\n    env.predict(pred_df)\n    if idx<3:\n        display(show_img(img, bboxes, bbox_format='coco'))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-02-05T11:37:06.235765Z","iopub.execute_input":"2022-02-05T11:37:06.235988Z","iopub.status.idle":"2022-02-05T11:37:35.933822Z","shell.execute_reply.started":"2022-02-05T11:37:06.23596Z","shell.execute_reply":"2022-02-05T11:37:35.932789Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 👀 Check Submission","metadata":{}},{"cell_type":"code","source":"sub_df = pd.read_csv('submission.csv')\nsub_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-02-05T11:37:35.935261Z","iopub.execute_input":"2022-02-05T11:37:35.935519Z","iopub.status.idle":"2022-02-05T11:37:35.948146Z","shell.execute_reply.started":"2022-02-05T11:37:35.935488Z","shell.execute_reply":"2022-02-05T11:37:35.947296Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Please Upvote if you find this Helpful","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=600>","metadata":{}}]}