{"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":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport torch\nfrom tqdm import tqdm\nimport sys\nimport 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\nimport ast\nsys.path.append('../input/tensorflow-great-barrier-reef')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-01-26T01:41:47.022821Z","iopub.execute_input":"2022-01-26T01:41:47.023562Z","iopub.status.idle":"2022-01-26T01:41:47.034677Z","shell.execute_reply.started":"2022-01-26T01:41:47.023506Z","shell.execute_reply":"2022-01-26T01:41:47.033736Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"CONF      = 0.01\nIOU       = 0.45\nIMG_SIZE  = 9000\nAUGMENT   = True\nCKPT_PATH = '../input/reef-baseline-fold12/l6_3600_uflip_vm5_f12_up/f1/best.pt'","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:41:47.036283Z","iopub.execute_input":"2022-01-26T01:41:47.036712Z","iopub.status.idle":"2022-01-26T01:41:47.050158Z","shell.execute_reply.started":"2022-01-26T01:41:47.036672Z","shell.execute_reply":"2022-01-26T01:41:47.049017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def voc2yolo(bboxes, image_height=720, image_width=1280):\n    \"\"\"\n    voc  => [x1, y1, x2, y1]\n    yolo => [xmid, ymid, w, h] (normalized)\n    \"\"\"\n    \n    bboxes = bboxes.copy().astype(float) # otherwise all value will be 0 as voc_pascal dtype is np.int\n    \n    bboxes[..., [0, 2]] = bboxes[..., [0, 2]]/ image_width\n    bboxes[..., [1, 3]] = bboxes[..., [1, 3]]/ image_height\n    \n    w = bboxes[..., 2] - bboxes[..., 0]\n    h = bboxes[..., 3] - bboxes[..., 1]\n    \n    bboxes[..., 0] = bboxes[..., 0] + w/2\n    bboxes[..., 1] = bboxes[..., 1] + h/2\n    bboxes[..., 2] = w\n    bboxes[..., 3] = h\n    \n    return bboxes\n\ndef yolo2voc(bboxes, image_height=720, image_width=1280):\n    \"\"\"\n    yolo => [xmid, ymid, w, h] (normalized)\n    voc  => [x1, y1, x2, y1]\n    \n    \"\"\" \n    bboxes = bboxes.copy().astype(float) # otherwise all value will be 0 as voc_pascal dtype is np.int\n    \n    bboxes[..., [0, 2]] = bboxes[..., [0, 2]]* image_width\n    bboxes[..., [1, 3]] = bboxes[..., [1, 3]]* image_height\n    \n    bboxes[..., [0, 1]] = bboxes[..., [0, 1]] - bboxes[..., [2, 3]]/2\n    bboxes[..., [2, 3]] = bboxes[..., [0, 1]] + bboxes[..., [2, 3]]\n    \n    return bboxes\n\ndef coco2yolo(bboxes, image_height=720, image_width=1280):\n    \"\"\"\n    coco => [xmin, ymin, w, h]\n    yolo => [xmid, ymid, w, h] (normalized)\n    \"\"\"\n    \n    bboxes = bboxes.copy().astype(float) # otherwise all value will be 0 as voc_pascal dtype is np.int\n    \n    # normolizinig\n    bboxes[..., [0, 2]]= bboxes[..., [0, 2]]/ image_width\n    bboxes[..., [1, 3]]= bboxes[..., [1, 3]]/ image_height\n    \n    # converstion (xmin, ymin) => (xmid, ymid)\n    bboxes[..., [0, 1]] = bboxes[..., [0, 1]] + bboxes[..., [2, 3]]/2\n    \n    return bboxes\n\ndef yolo2coco(bboxes, image_height=720, image_width=1280):\n    \"\"\"\n    yolo => [xmid, ymid, w, h] (normalized)\n    coco => [xmin, ymin, w, h]\n    \n    \"\"\" \n    bboxes = bboxes.copy().astype(float) # otherwise all value will be 0 as voc_pascal dtype is np.int\n    \n    # denormalizing\n    bboxes[..., [0, 2]]= bboxes[..., [0, 2]]* image_width\n    bboxes[..., [1, 3]]= bboxes[..., [1, 3]]* image_height\n    \n    # converstion (xmid, ymid) => (xmin, ymin) \n    bboxes[..., [0, 1]] = bboxes[..., [0, 1]] - bboxes[..., [2, 3]]/2\n    \n    return bboxes\n\ndef voc2coco(bboxes, image_height=720, image_width=1280):\n    bboxes  = voc2yolo(bboxes, image_height, image_width)\n    bboxes  = yolo2coco(bboxes, image_height, image_width)\n    return bboxes\n\n\ndef load_image(image_path):\n    return cv2.cvtColor(cv2.imread(image_path), cv2.COLOR_BGR2RGB)\n\n\ndef plot_one_box(x, img, color=None, label=None, line_thickness=None):\n    # Plots one bounding box on image img\n    tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line/font thickness\n    color = color or [random.randint(0, 255) for _ in range(3)]\n    c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))\n    cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)\n    if label:\n        tf = max(tl - 1, 1)  # font thickness\n        t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]\n        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3\n        cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA)  # filled\n        cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)\n\ndef draw_bboxes(img, bboxes, classes, class_ids, colors = None, show_classes = None, bbox_format = 'yolo', class_name = False, line_thickness = 2):  \n     \n    image = img.copy()\n    show_classes = classes if show_classes is None else show_classes\n    colors = (0, 255 ,0) if colors is None else colors\n    \n    if bbox_format == 'yolo':\n        \n        for idx in range(len(bboxes)):  \n            \n            bbox  = bboxes[idx]\n            cls   = classes[idx]\n            cls_id = class_ids[idx]\n            color = colors[cls_id] if type(colors) is list else colors\n            \n            if cls in show_classes:\n            \n                x1 = round(float(bbox[0])*image.shape[1])\n                y1 = round(float(bbox[1])*image.shape[0])\n                w  = round(float(bbox[2])*image.shape[1]/2) #w/2 \n                h  = round(float(bbox[3])*image.shape[0]/2)\n\n                voc_bbox = (x1-w, y1-h, x1+w, y1+h)\n                plot_one_box(voc_bbox, \n                             image,\n                             color = color,\n                             label = cls if class_name else str(get_label(cls)),\n                             line_thickness = line_thickness)\n            \n    elif bbox_format == 'coco':\n        \n        for idx in range(len(bboxes)):  \n            \n            bbox  = bboxes[idx]\n            cls   = classes[idx]\n            cls_id = class_ids[idx]\n            color = colors[cls_id] if type(colors) is list else colors\n            \n            if cls in show_classes:            \n                x1 = int(round(bbox[0]))\n                y1 = int(round(bbox[1]))\n                w  = int(round(bbox[2]))\n                h  = int(round(bbox[3]))\n\n                voc_bbox = (x1, y1, x1+w, y1+h)\n                plot_one_box(voc_bbox, \n                             image,\n                             color = color,\n                             label = cls if class_name else str(cls_id),\n                             line_thickness = line_thickness)\n\n    elif bbox_format == 'voc_pascal':\n        \n        for idx in range(len(bboxes)):  \n            \n            bbox  = bboxes[idx]\n            cls   = classes[idx]\n            cls_id = class_ids[idx]\n            color = colors[cls_id] if type(colors) is list else colors\n            \n            if cls in show_classes: \n                x1 = int(round(bbox[0]))\n                y1 = int(round(bbox[1]))\n                x2 = int(round(bbox[2]))\n                y2 = int(round(bbox[3]))\n                voc_bbox = (x1, y1, x2, y2)\n                plot_one_box(voc_bbox, \n                             image,\n                             color = color,\n                             label = cls if class_name else str(cls_id),\n                             line_thickness = line_thickness)\n    else:\n        raise ValueError('wrong bbox format')\n\n    return image\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":{"execution":{"iopub.status.busy":"2022-01-26T01:41:47.052055Z","iopub.execute_input":"2022-01-26T01:41:47.052467Z","iopub.status.idle":"2022-01-26T01:41:47.106752Z","shell.execute_reply.started":"2022-01-26T01:41:47.052418Z","shell.execute_reply":"2022-01-26T01:41:47.105675Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"def get_path(row):\n    row['image_path'] = f'{ROOT_DIR}/train_images/video_{row.video_id}/{row.video_frame}.jpg'\n    return row","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:41:47.108248Z","iopub.execute_input":"2022-01-26T01:41:47.108734Z","iopub.status.idle":"2022-01-26T01:41:47.119594Z","shell.execute_reply.started":"2022-01-26T01:41:47.108682Z","shell.execute_reply":"2022-01-26T01:41:47.118863Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT_DIR  = '/kaggle/input/tensorflow-great-barrier-reef/'\n# Train Data\ndf = pd.read_csv(f'{ROOT_DIR}/train.csv')\ndf = df.progress_apply(get_path, axis=1)\ndf['annotations'] = df['annotations'].progress_apply(lambda x: ast.literal_eval(x))\ndisplay(df.head(2))","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:41:47.121948Z","iopub.execute_input":"2022-01-26T01:41:47.122245Z","iopub.status.idle":"2022-01-26T01:42:05.240208Z","shell.execute_reply.started":"2022-01-26T01:41:47.122210Z","shell.execute_reply":"2022-01-26T01:42:05.239404Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2022-01-26T01:42:05.241343Z","iopub.execute_input":"2022-01-26T01:42:05.241586Z","iopub.status.idle":"2022-01-26T01:42:05.348047Z","shell.execute_reply.started":"2022-01-26T01:42:05.241557Z","shell.execute_reply":"2022-01-26T01:42:05.347080Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!mkdir -p /root/.config/Ultralytics\n!cp /kaggle/input/yolov5-font/Arial.ttf /root/.config/Ultralytics/","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:42:05.349552Z","iopub.execute_input":"2022-01-26T01:42:05.349876Z","iopub.status.idle":"2022-01-26T01:42:06.902657Z","shell.execute_reply.started":"2022-01-26T01:42:05.349833Z","shell.execute_reply":"2022-01-26T01:42:06.901412Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def load_model(ckpt_path, conf=0.01, iou=0.50):\n    model = torch.hub.load('../input/yolov5-lib-ds',\n                           'custom',\n                           path=ckpt_path,\n                           source='local',\n                           force_reload=True)  # local repo\n    model.conf = 0.01  # NMS confidence threshold\n    model.iou  = 0.5 # 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":{"execution":{"iopub.status.busy":"2022-01-26T01:42:06.904193Z","iopub.execute_input":"2022-01-26T01:42:06.904505Z","iopub.status.idle":"2022-01-26T01:42:06.911360Z","shell.execute_reply.started":"2022-01-26T01:42:06.904473Z","shell.execute_reply":"2022-01-26T01:42:06.910689Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\n\n## addition of multiple names\ndef show_img(img, bboxes, bbox_format='yolo'):\n    names  = ['patrick star1', 'patrick star2', 'patrick star3']*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":{"execution":{"iopub.status.busy":"2022-01-26T01:43:44.030789Z","iopub.execute_input":"2022-01-26T01:43:44.031302Z","iopub.status.idle":"2022-01-26T01:43:44.043899Z","shell.execute_reply.started":"2022-01-26T01:43:44.031249Z","shell.execute_reply":"2022-01-26T01:43:44.043282Z"},"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(20).image_path.tolist()\nfor idx, path in enumerate(image_paths):\n    img = cv2.imread(path)[...,::-1]\n    bboxes, confis = predict(model, img, size=500, augment=AUGMENT)\n    display(show_img(img, bboxes, bbox_format='coco'))\n    if idx>5:\n        break\n        \n\n","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:43:49.327792Z","iopub.execute_input":"2022-01-26T01:43:49.328544Z","iopub.status.idle":"2022-01-26T01:43:53.339333Z","shell.execute_reply.started":"2022-01-26T01:43:49.328510Z","shell.execute_reply":"2022-01-26T01:43:53.338278Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"results.pandas()","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:42:10.745070Z","iopub.execute_input":"2022-01-26T01:42:10.745744Z","iopub.status.idle":"2022-01-26T01:42:10.863800Z","shell.execute_reply.started":"2022-01-26T01:42:10.745711Z","shell.execute_reply":"2022-01-26T01:42:10.862671Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2022-01-26T01:42:10.865000Z","iopub.execute_input":"2022-01-26T01:42:10.865614Z","iopub.status.idle":"2022-01-26T01:42:10.906123Z","shell.execute_reply.started":"2022-01-26T01:42:10.865576Z","shell.execute_reply":"2022-01-26T01:42:10.904953Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = torch.hub.load('../input/yolov5-lib-ds', \n                       'custom', \n                       path='../input/reef-baseline-fold12/l6_3600_uflip_vm5_f12_up/f1/best.pt',\n                       source='local',\n                       force_reload=True)  # local repo\nmodel.conf = 0.01","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:42:10.907298Z","iopub.status.idle":"2022-01-26T01:42:10.907838Z","shell.execute_reply.started":"2022-01-26T01:42:10.907646Z","shell.execute_reply":"2022-01-26T01:42:10.907666Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for idx, (img, pred_df) in enumerate(tqdm(iter_test)):\n    anno = ''\n    r = model(img, size=IMG_SIZE, augment=True)\n    if r.pandas().xyxy[0].shape[0] == 0:\n        anno = ''\n    else:\n        for idx, row in r.pandas().xyxy[0].iterrows():\n            if row.confidence > 0.15:\n                anno += '{} {} {} {} {} '.format(row.confidence, int(row.xmin), int(row.ymin), int(row.xmax-row.xmin), int(row.ymax-row.ymin))\n#                 pred.append([row.confidence, row.xmin, row.ymin, row.xmax-row.xmin, row.ymax-row.ymin])\n    pred_df['annotations'] = anno.strip(' ')\n    env.predict(pred_df)","metadata":{"execution":{"iopub.status.busy":"2022-01-26T01:42:10.909065Z","iopub.status.idle":"2022-01-26T01:42:10.909602Z","shell.execute_reply.started":"2022-01-26T01:42:10.909412Z","shell.execute_reply":"2022-01-26T01:42:10.909432Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}