{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":20604,"databundleVersionId":1357052,"sourceType":"competition"},{"sourceId":1543925,"sourceType":"datasetVersion","datasetId":910712},{"sourceId":1577571,"sourceType":"datasetVersion","datasetId":932728},{"sourceId":7254987,"sourceType":"datasetVersion","datasetId":4203945}],"dockerImageVersionId":30018,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"pip install --upgrade pip","metadata":{"id":"1_dPgKgwSQfp","_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-01-08T07:49:16.99024Z","iopub.execute_input":"2024-01-08T07:49:16.990701Z","iopub.status.idle":"2024-01-08T07:49:24.872162Z","shell.execute_reply.started":"2024-01-08T07:49:16.990659Z","shell.execute_reply":"2024-01-08T07:49:24.871046Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# !pip install albumentations\n!pip install albumentations==0.4.6\n!pip install git+https://github.com/qubvel/segmentation_models.pytorch","metadata":{"execution":{"iopub.status.busy":"2024-01-08T07:49:24.874336Z","iopub.execute_input":"2024-01-08T07:49:24.874629Z","iopub.status.idle":"2024-01-08T07:49:50.360594Z","shell.execute_reply.started":"2024-01-08T07:49:24.874599Z","shell.execute_reply":"2024-01-08T07:49:50.359551Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Importing libraries","metadata":{}},{"cell_type":"code","source":"# !pip install segmentation_models_pytorch --upgrade\nimport os\nimport time\nimport io\nimport base64\n\nimport numpy as np\nimport pandas as pd\nimport cv2\n\nimport matplotlib.pyplot as plt\nimport matplotlib.colors as mpl_colors\nimport seaborn as sns\n\nfrom sklearn.model_selection import train_test_split\n\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.optim import Adam\nfrom torch.optim.lr_scheduler import ReduceLROnPlateau\n# !pip install scipy\nfrom albumentations.pytorch import ToTensor, ToTensorV2 \nfrom albumentations import (HorizontalFlip,\n VerticalFlip,\n Normalize,\n Compose)\n\n# from segmentation_models_pytorch.unet import Unet\nfrom segmentation_models_pytorch import Unet\n\nfrom IPython.display import HTML\nfrom IPython.display import clear_output\nimport warnings\nwarnings.simplefilter(\"ignore\")","metadata":{"id":"bK6emFemSkOo","_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-01-08T07:49:50.362371Z","iopub.execute_input":"2024-01-08T07:49:50.362746Z","iopub.status.idle":"2024-01-08T07:49:50.372192Z","shell.execute_reply.started":"2024-01-08T07:49:50.362709Z","shell.execute_reply":"2024-01-08T07:49:50.371488Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Helper functions","metadata":{}},{"cell_type":"code","source":"# utils\ndef get_one_slice_data(img_name: str,\n mask_name: str,\n root_imgs_path: str = \"images/\",\n root_masks_path: str = \"masks/\",) -> np.ndarray:\n\n img_path = os.path.join(root_imgs_path, img_name)\n mask_path = os.path.join(root_masks_path, mask_name)\n one_slice_img = cv2.imread(img_path)#[:,:,0] uncomment for grayscale\n one_slice_mask = cv2.imread(mask_path)\n one_slice_mask[one_slice_mask < 240] = 0 # remove artifacts\n one_slice_mask[one_slice_mask >= 240] = 255\n\n return one_slice_img, one_slice_mask\n\n\ndef get_id_predictions(net: nn.Module,\n ct_scan_id_df: pd.DataFrame,\n root_imgs_dir: str,\n treshold: float = 0.3) -> list:\n\n \"\"\"\n Factory for getting predictions and storing them and images in lists as uint8 images.\n Params:\n net: model for prediction.\n ct_scan_id_df: df with unique patient id.\n root_imgs_dir: root path for images.\n treshold: threshold for probabilities.\n \"\"\"\n sigmoid = lambda x: 1 / (1 + np.exp(-x))\n images = []\n predictions = []\n net.eval()\n device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n print(\"device:\", device)\n with torch.no_grad():\n for idx in range(len(ct_scan_id_df)):\n img_name = ct_scan_id_df.loc[idx, \"ImageId\"]\n path = os.path.join(root_imgs_dir, img_name)\n\n img_ = cv2.imread(path)\n \n img = Normalize().apply(img_)\n tensor = torch.FloatTensor(img).permute(2, 0, 1).unsqueeze(0)\n prediction = net.forward(tensor.to(device))\n prediction = prediction.cpu().detach().numpy()\n prediction = prediction.squeeze(0).transpose(1, 2, 0)\n prediction = sigmoid(prediction)\n prediction = (prediction >= treshold).astype(np.float32)\n\n predictions.append((prediction * 255).astype(\"uint8\"))\n images.append(img_)\n\n return images, predictions\n\n\n# Save image in original resolution\n# helpful link - https://stackoverflow.com/questions/34768717/matplotlib-unable-to-save-image-in-same-resolution-as-original-image\n\ndef get_overlaid_masks_on_image(\n one_slice_image: np.ndarray,\n one_slice_mask: np.ndarray, \n w: float = 512,\n h: float = 512, \n dpi: float = 100,\n write: bool = False,\n path_to_save: str = '/content/',\n name_to_save: str = 'img_name'):\n \"\"\"overlap masks on image and save this as a new image.\"\"\"\n\n path_to_save_ = os.path.join(path_to_save, name_to_save)\n lung, heart, trachea = [one_slice_mask[:, :, i] for i in range(3)]\n figsize = (w / dpi), (h / dpi)\n fig = plt.figure(figsize=(figsize))\n fig.add_axes([0, 0, 1, 1])\n \n # image\n plt.imshow(one_slice_image, cmap=\"bone\")\n\n # overlaying segmentation masks\n plt.imshow(np.ma.masked_where(lung == False, lung),\n cmap='cool', alpha=0.3)\n plt.imshow(np.ma.masked_where(heart == False, heart),\n cmap='autumn', alpha=0.3)\n plt.imshow(np.ma.masked_where(trachea == False, trachea),\n cmap='autumn_r', alpha=0.3) \n\n #plt.axis(\"off\") ## dont work in kaggle kernel\n fig.axes[0].get_xaxis().set_visible(False) ## work in kaggle kernel\n fig.axes[0].get_yaxis().set_visible(False)\n \n\n fig.savefig(f\"{path_to_save_}.png\",bbox_inches='tight', \n pad_inches=0, dpi=dpi, format=\"png\")\n \n if write:\n plt.close()\n else:\n plt.show()\n \ndef get_overlaid_masks_on_full_ctscan(ct_scan_id_df: pd.DataFrame, \n path_to_save: str,\n root_imgs_dir: str,\n root_masks_dir: str,\n ):\n \"\"\"\n Creating images with overlaid masks on each slice of CT scan.\n Params:\n ct_scan_id_df: df with unique patient id.\n path_to_save: path to save images.\n \"\"\"\n num_slice = len(ct_scan_id_df)\n for slice_ in range(num_slice):\n img_name = ct_scan_id_df.loc[slice_, \"ImageId\"]\n mask_name = ct_scan_id_df.loc[slice_, \"MaskId\"]\n one_slice_img, one_slice_mask = get_one_slice_data(img_name, mask_name,\n root_imgs_dir, root_masks_dir)\n get_overlaid_masks_on_image(one_slice_img,\n one_slice_mask,\n write=True, \n path_to_save=path_to_save,\n name_to_save=str(slice_)\n )\n\ndef create_video(path_to_imgs: str, video_name: str, framerate: int):\n \"\"\"\n Create video from images.\n Params:\n path_to_imgs: path to dir with images.\n video_name: name for saving video.\n framerate: num frames per sec in video.\n \"\"\"\n img_names = sorted(os.listdir(path_to_imgs), key=lambda x: int(x[:-4])) # img_name must be numbers\n img_path = os.path.join(path_to_imgs, img_names[0])\n frame_width, frame_height, _ = cv2.imread(img_path).shape\n fourc = cv2.VideoWriter_fourcc(*'XVID') ## MP4V - dont work in kaggle kernel\n video = cv2.VideoWriter(video_name + \".avi\", ##'mp4' \n fourc, \n framerate, \n (frame_width, frame_height))\n\n for img_name in img_names:\n img_path = os.path.join(path_to_imgs, img_name)\n image = cv2.imread(img_path)\n video.write(image)\n \n cv2.destroyAllWindows()\n video.release()\n\n \ndef compute_scores_per_classes(model,\n dataloader,\n classes):\n \"\"\"\n Compute Dice and Jaccard coefficients for each class.\n Params:\n model: neural net for make predictions.\n dataloader: dataset object to load data from.\n classes: list with classes.\n Returns: dictionaries with dice and jaccard coefficients for each class for each slice.\n \"\"\"\n device = 'cuda' if torch.cuda.is_available() else 'cpu'\n dice_scores_per_classes = {key: list() for key in classes}\n iou_scores_per_classes = {key: list() for key in classes}\n\n with torch.no_grad():\n for i, (imgs, targets) in enumerate(dataloader):\n imgs, targets = imgs.to(device), targets.to(device)\n logits = model(imgs)\n logits = logits.detach().cpu().numpy()\n targets = targets.detach().cpu().numpy()\n \n dice_scores = dice_coef_metric_per_classes(logits, targets)\n iou_scores = jaccard_coef_metric_per_classes(logits, targets)\n\n for key in dice_scores.keys():\n dice_scores_per_classes[key].extend(dice_scores[key])\n\n for key in iou_scores.keys():\n iou_scores_per_classes[key].extend(iou_scores[key])\n\n return dice_scores_per_classes, iou_scores_per_classes\n\n\n# loss\ndef dice_coef_metric_per_classes(probabilities: np.ndarray,\n truth: np.ndarray,\n treshold: float = 0.5,\n eps: float = 1e-9,\n classes: list = ['lung', 'heart', 'trachea']) -> np.ndarray:\n \"\"\"\n Calculate Dice score for data batch and for each class.\n Params:\n probobilities: model outputs after activation function.\n truth: model targets.\n threshold: threshold for probabilities.\n eps: additive to refine the estimate.\n classes: list with name classes.\n Returns: dict with dice scores for each class.\n \"\"\"\n scores = {key: list() for key in classes}\n num = probabilities.shape[0]\n num_classes = probabilities.shape[1]\n predictions = (probabilities >= treshold).astype(np.float32)\n assert(predictions.shape == truth.shape)\n\n for i in range(num):\n for class_ in range(num_classes):\n prediction = predictions[i][class_]\n truth_ = truth[i][class_]\n intersection = 2.0 * (truth_ * prediction).sum()\n union = truth_.sum() + prediction.sum()\n if truth_.sum() == 0 and prediction.sum() == 0:\n scores[classes[class_]].append(1.0)\n else:\n scores[classes[class_]].append((intersection + eps) / union)\n \n return scores\n\n\ndef jaccard_coef_metric_per_classes(probabilities: np.ndarray,\n truth: np.ndarray,\n treshold: float = 0.5,\n eps: float = 1e-9,\n classes: list = ['lung', 'heart', 'trachea']) -> np.ndarray:\n \"\"\"\n Calculate Jaccard index for data batch and for each class.\n Params:\n probobilities: model outputs after activation function.\n truth: model targets.\n threshold: threshold for probabilities.\n eps: additive to refine the estimate.\n classes: list with name classes.\n Returns: dict with jaccard scores for each class.\"\n \"\"\"\n scores = {key: list() for key in classes}\n num = probabilities.shape[0]\n num_classes = probabilities.shape[1]\n predictions = (probabilities >= treshold).astype(np.float32)\n assert(predictions.shape == truth.shape)\n\n for i in range(num):\n for class_ in range(num_classes):\n prediction = predictions[i][class_]\n truth_ = truth[i][class_]\n intersection = (prediction * truth_).sum()\n union = (prediction.sum() + truth_.sum()) - intersection + eps\n if truth_.sum() == 0 and prediction.sum() == 0:\n scores[classes[class_]].append(1.0)\n else:\n scores[classes[class_]].append((intersection + eps) / union)\n\n return scores\n\n\n# visualizer\ndef show_data_augmentations(img_tensor: torch.Tensor,\n mask_tensor: torch.Tensor,\n mean: tuple = (0.485, 0.456, 0.406),\n std: tuple = (0.229, 0.224, 0.225),\n labels: list=[\"image\", \"lung\", \"heart\", \"trachea\"]):\n \n img = img_tensor.numpy().transpose(1, 2, 0)\n img = (img * std + mean).astype(\"float32\")\n img = np.clip(img, 0, 1)\n mask = mask_tensor.numpy().transpose(1, 2, 0)\n data_to_plot = [img, *[mask[:,:, i] for i in range(3)]]\n\n fig, axes = plt.subplots(nrows=1, ncols=4, figsize=(15, 8))\n for i, ax in enumerate(axes):\n ax.imshow(data_to_plot[i])\n ax.set_title(labels[i])\n\n plt.show()\n \n \ndef show_video(video_path: str):\n \"\"\"\n show video in jupyter notebook, agent interaction in environment.\n Takes - path to video file.\n Returns - html video player in jupyter notebook.\n \"\"\" \n video = io.open(video_path, 'r+b').read()\n encoded = base64.b64encode(video)\n\n return HTML(data=''''''\n .format(encoded.decode('ascii')))\n\n\ndef get_color_info(classes: list = ['lung', 'heart', 'trachea']):\n\n def get_color(cmap):\n new_cmap = mpl_colors.LinearSegmentedColormap.from_list(\n (cmap.name, 0.0, 0.0,),\n cmap(np.linspace(0.0, 0.0, 100))\n )\n return new_cmap\n\n colormaps = [plt.get_cmap(cmap_name) for cmap_name in \n ['cool', 'autumn', 'autumn_r']\n ]\n arr = np.linspace(0, 50, 100).reshape((10, 10))\n fig, ax = plt.subplots(1, 3, figsize=(15, 5))\n for i in range(3):\n cmap = get_color(colormaps[i])\n ax[i].axis('off')\n ax[i].imshow(arr, cmap=cmap)\n ax[i].set_title(classes[i], fontsize=15)\n\n fig.suptitle(\"Color definition\", fontsize=20, y=0.99)\n fig.savefig(f\"color_definition.png\", bbox_inches='tight', \n pad_inches=0.2, dpi=100, format=\"png\")\n \n plt.savefig(f\"color_definition.svg\", bbox_inches='tight',\n pad_inches=0.2, dpi=100, format=\"svg\")","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-01-08T07:49:50.374546Z","iopub.execute_input":"2024-01-08T07:49:50.374907Z","iopub.status.idle":"2024-01-08T07:49:50.45712Z","shell.execute_reply.started":"2024-01-08T07:49:50.374869Z","shell.execute_reply":"2024-01-08T07:49:50.456366Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"config with global variables","metadata":{}},{"cell_type":"code","source":"class GlobalConfig:\n def __init__(self):\n self.seed = 555\n self.path_to_csv = '../input/chest-ct-segmentation/train.csv'\n self.path_to_imgs_dir = '../input/chest-ct-segmentation/images/images'\n self.path_to_masks_dir = '../input/chest-ct-segmentation/masks/masks'\n self.pretrained_model_path = '../input/chest-ct-segmentation/pretrained_model/pretrained_model/model_100_epoch.pth'\n self.train_logs_path = '../input/chest-ct-segmentation/pretrained_model/pretrained_model/train_log_100_epoch.csv'\n\n\ndef seed_everything(seed: int):\n torch.manual_seed(seed)\n torch.cuda.manual_seed(seed)\n np.random.seed(seed)\n \nconfig = GlobalConfig()\nseed_everything(config.seed)","metadata":{"id":"8WmHqD50SkRe","execution":{"iopub.status.busy":"2024-01-08T07:49:50.460744Z","iopub.execute_input":"2024-01-08T07:49:50.460994Z","iopub.status.idle":"2024-01-08T07:49:50.471261Z","shell.execute_reply.started":"2024-01-08T07:49:50.460969Z","shell.execute_reply":"2024-01-08T07:49:50.47043Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Dataset and Dataloader","metadata":{}},{"cell_type":"code","source":"class LungsDataset(Dataset):\n def __init__(self, \n imgs_dir: str,\n masks_dir:str,\n df: pd.DataFrame,\n phase: str):\n \"\"\"Initialization.\"\"\"\n self.root_imgs_dir = imgs_dir\n self.root_masks_dir = masks_dir\n self.df = df\n self.augmentations = get_augmentations(phase)\n \n def __len__(self):\n return len(self.df)\n\n def __getitem__(self, idx):\n img_name = self.df.loc[idx, \"ImageId\"]\n mask_name = self.df.loc[idx, \"MaskId\"]\n img_path = os.path.join(self.root_imgs_dir, img_name)\n mask_path = os.path.join(self.root_masks_dir, mask_name)\n img = cv2.imread(img_path)\n mask = cv2.imread(mask_path)\n mask[mask < 240] = 0 # remove artifacts\n mask[mask > 0] = 1\n\n augmented = self.augmentations(image=img, \n mask=mask.astype(np.float32))\n img = augmented['image']\n mask = augmented['mask'].permute(2, 0, 1)\n\n return img, mask\n\n\ndef get_augmentations(phase,\n mean: tuple = (0.485, 0.456, 0.406),\n std: tuple = (0.229, 0.224, 0.225),):\n list_transforms = []\n if phase == \"train\":\n list_transforms.extend(\n [\n VerticalFlip(p=0.5), \n ]\n )\n list_transforms.extend(\n [\n Normalize(mean=mean, std=std, p=1),\n #ToTensor(num_classes=3, sigmoid=False),\n ToTensorV2(),\n ]\n )\n list_trfms = Compose(list_transforms)\n return list_trfms\n\n\ndef get_dataloader(\n imgs_dir: str,\n masks_dir: str,\n path_to_csv: str,\n phase: str,\n batch_size: int = 8,\n num_workers: int = 6,\n test_size: float = 0.2,\n):\n '''Returns: dataloader for the model training'''\n df = pd.read_csv(path_to_csv)\n \n\n train_df, val_df = train_test_split(df, \n test_size=test_size, \n random_state=69)\n train_df, val_df = train_df.reset_index(drop=True), val_df.reset_index(drop=True)\n\n df = train_df if phase == \"train\" else val_df\n image_dataset = LungsDataset(imgs_dir, masks_dir, df, phase)\n dataloader = DataLoader(\n image_dataset,\n batch_size=batch_size,\n num_workers=num_workers,\n pin_memory=True,\n shuffle=True, \n )\n\n return dataloader","metadata":{"execution":{"iopub.status.busy":"2024-01-08T07:49:50.474713Z","iopub.execute_input":"2024-01-08T07:49:50.474985Z","iopub.status.idle":"2024-01-08T07:49:50.495723Z","shell.execute_reply.started":"2024-01-08T07:49:50.47496Z","shell.execute_reply":"2024-01-08T07:49:50.494713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Loss and Metrics","metadata":{}},{"cell_type":"code","source":"def dice_coef_metric(probabilities: torch.Tensor,\n truth: torch.Tensor,\n treshold: float = 0.5,\n eps: float = 1e-9) -> np.ndarray:\n \"\"\"\n Calculate Dice score for data batch.\n Params:\n probobilities: model outputs after activation function.\n truth: truth values.\n threshold: threshold for probabilities.\n eps: additive to refine the estimate.\n Returns: dice score aka f1.\n \"\"\"\n scores = []\n num = probabilities.shape[0]\n predictions = (probabilities >= treshold).float()\n assert(predictions.shape == truth.shape)\n for i in range(num):\n prediction = predictions[i]\n truth_ = truth[i]\n intersection = 2.0 * (truth_ * prediction).sum()\n union = truth_.sum() + prediction.sum()\n if truth_.sum() == 0 and prediction.sum() == 0:\n scores.append(1.0)\n else:\n scores.append((intersection + eps) / union)\n return np.mean(scores)\n\n\ndef jaccard_coef_metric(probabilities: torch.Tensor,\n truth: torch.Tensor,\n treshold: float = 0.5,\n eps: float = 1e-9) -> np.ndarray:\n \"\"\"\n Calculate Jaccard index for data batch.\n Params:\n probobilities: model outputs after activation function.\n truth: truth values.\n threshold: threshold for probabilities.\n eps: additive to refine the estimate.\n Returns: jaccard score aka iou.\"\n \"\"\"\n scores = []\n num = probabilities.shape[0]\n predictions = (probabilities >= treshold).float()\n assert(predictions.shape == truth.shape)\n\n for i in range(num):\n prediction = predictions[i]\n truth_ = truth[i]\n intersection = (prediction * truth_).sum()\n union = (prediction.sum() + truth_.sum()) - intersection + eps\n if truth_.sum() == 0 and prediction.sum() == 0:\n scores.append(1.0)\n else:\n scores.append((intersection + eps) / union)\n return np.mean(scores)\n\n\nclass Meter:\n '''factory for storing and updating iou and dice scores.'''\n def __init__(self, treshold: float = 0.5):\n self.threshold: float = treshold\n self.dice_scores: list = []\n self.iou_scores: list = []\n \n def update(self, logits: torch.Tensor, targets: torch.Tensor):\n \"\"\"\n Takes: logits from output model and targets,\n calculates dice and iou scores, and stores them in lists.\n \"\"\"\n probs = torch.sigmoid(logits)\n dice = dice_coef_metric(probs, targets, self.threshold)\n iou = jaccard_coef_metric(probs, targets, self.threshold)\n \n self.dice_scores.append(dice)\n self.iou_scores.append(iou)\n \n def get_metrics(self) -> np.ndarray:\n \"\"\"\n Returns: the average of the accumulated dice and iou scores.\n \"\"\"\n dice = np.mean(self.dice_scores)\n iou = np.mean(self.iou_scores)\n return dice, iou\n \n\nclass DiceLoss(nn.Module):\n \"\"\"Calculate dice loss.\"\"\"\n def __init__(self, eps: float = 1e-9):\n super(DiceLoss, self).__init__()\n self.eps = eps\n \n def forward(self,\n logits: torch.Tensor,\n targets: torch.Tensor) -> torch.Tensor:\n \n num = targets.size(0)\n probability = torch.sigmoid(logits)\n probability = probability.view(num, -1)\n targets = targets.view(num, -1)\n assert(probability.shape == targets.shape)\n \n intersection = 2.0 * (probability * targets).sum()\n union = probability.sum() + targets.sum()\n dice_score = (intersection + self.eps) / union\n #print(\"intersection\", intersection, union, dice_score)\n return 1.0 - dice_score\n \n \nclass BCEDiceLoss(nn.Module):\n \"\"\"Compute objective loss: BCE loss + DICE loss.\"\"\"\n def __init__(self):\n super(BCEDiceLoss, self).__init__()\n self.bce = nn.BCEWithLogitsLoss()\n self.dice = DiceLoss()\n \n def forward(self, \n logits: torch.Tensor,\n targets: torch.Tensor) -> torch.Tensor:\n assert(logits.shape == targets.shape)\n dice_loss = self.dice(logits, targets)\n bce_loss = self.bce(logits, targets)\n \n return bce_loss + dice_loss\n","metadata":{"execution":{"iopub.status.busy":"2024-01-08T07:49:50.497298Z","iopub.execute_input":"2024-01-08T07:49:50.497709Z","iopub.status.idle":"2024-01-08T07:49:50.530616Z","shell.execute_reply.started":"2024-01-08T07:49:50.49767Z","shell.execute_reply":"2024-01-08T07:49:50.529864Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{}},{"cell_type":"code","source":"model = Unet('efficientnet-b2', encoder_weights=\"imagenet\", classes=3, activation=None)","metadata":{"id":"UWec2CrXUPjC","_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-01-08T07:49:50.53187Z","iopub.execute_input":"2024-01-08T07:49:50.532301Z","iopub.status.idle":"2024-01-08T07:49:50.767473Z","shell.execute_reply.started":"2024-01-08T07:49:50.532264Z","shell.execute_reply":"2024-01-08T07:49:50.766684Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train Process","metadata":{"id":"PWUHmzvbaKo0"}},{"cell_type":"code","source":"class Trainer:\n \"\"\"\n Factory for training proccess.\n Args:\n display_plot: if True - plot train history after each epoch.\n net: neural network for mask prediction.\n criterion: factory for calculating objective loss.\n optimizer: optimizer for weights updating.\n phases: list with train and validation phases.\n dataloaders: dict with data loaders for train and val phases.\n imgs_dir: path to folder with images.\n masks_dir: path to folder with imasks.\n path_to_csv: path to csv file.\n meter: factory for storing and updating metrics.\n batch_size: data batch size for one step weights updating.\n num_epochs: num weights updation for all data.\n accumulation_steps: the number of steps after which the optimization step can be taken\n (https://www.kaggle.com/c/understanding_cloud_organization/discussion/105614).\n lr: learning rate for optimizer.\n scheduler: scheduler for control learning rate.\n losses: dict for storing lists with losses for each phase.\n jaccard_scores: dict for storing lists with jaccard scores for each phase.\n dice_scores: dict for storing lists with dice scores for each phase.\n \"\"\"\n def __init__(self,\n net: nn.Module,\n criterion: nn.Module,\n lr: float,\n accumulation_steps: int,\n batch_size: int,\n num_epochs: int,\n imgs_dir: str,\n masks_dir: str,\n path_to_csv: str,\n display_plot: bool = True\n ):\n\n \"\"\"Initialization.\"\"\"\n self.device = 'cuda' if torch.cuda.is_available() else 'cpu'\n print(\"device:\", self.device)\n self.display_plot = display_plot\n self.net = net\n self.net = self.net.to(self.device)\n self.criterion = criterion\n self.optimizer = Adam(self.net.parameters(), lr=lr)\n self.scheduler = ReduceLROnPlateau(self.optimizer, mode=\"min\",\n patience=3, verbose=True)\n self.accumulation_steps = accumulation_steps // batch_size\n self.phases = [\"train\", \"val\"]\n self.num_epochs = num_epochs\n\n self.dataloaders = {\n phase: get_dataloader(\n imgs_dir = imgs_dir,\n masks_dir = masks_dir,\n path_to_csv = path_to_csv,\n phase = phase,\n batch_size = 8,\n num_workers = 6\n )\n for phase in self.phases\n }\n self.best_loss = float(\"inf\")\n self.losses = {phase: [] for phase in self.phases}\n self.dice_scores = {phase: [] for phase in self.phases}\n self.jaccard_scores = {phase: [] for phase in self.phases}\n \n def _compute_loss_and_outputs(self,\n images: torch.Tensor,\n targets: torch.Tensor):\n images = images.to(self.device)\n targets = targets.to(self.device)\n logits = self.net(images)\n loss = self.criterion(logits, targets)\n return loss, logits\n \n def _do_epoch(self, epoch: int, phase: str):\n print(f\"{phase} epoch: {epoch} | time: {time.strftime('%H:%M:%S')}\")\n\n self.net.train() if phase == \"train\" else self.net.eval()\n meter = Meter()\n dataloader = self.dataloaders[phase]\n total_batches = len(dataloader)\n running_loss = 0.0\n self.optimizer.zero_grad()\n for itr, (images, targets) in enumerate(dataloader):\n loss, logits = self._compute_loss_and_outputs(images, targets)\n loss = loss / self.accumulation_steps\n if phase == \"train\":\n loss.backward()\n if (itr + 1) % self.accumulation_steps == 0:\n self.optimizer.step()\n self.optimizer.zero_grad()\n running_loss += loss.item()\n meter.update(logits.detach().cpu(),\n targets.detach().cpu()\n )\n \n epoch_loss = (running_loss * self.accumulation_steps) / total_batches\n epoch_dice, epoch_iou = meter.get_metrics()\n \n self.losses[phase].append(epoch_loss)\n self.dice_scores[phase].append(epoch_dice)\n self.jaccard_scores[phase].append(epoch_iou)\n\n return epoch_loss\n \n def train(self):\n for epoch in range(self.num_epochs):\n self._do_epoch(epoch, \"train\")\n with torch.no_grad():\n val_loss = self._do_epoch(epoch, \"val\")\n self.scheduler.step(val_loss)\n if self.display_plot:\n self._plot_train_history()\n \n if val_loss < self.best_loss:\n print(f\"\\n{'#'*20}\\nSaved new checkpoint\\n{'#'*20}\\n\")\n self.best_loss = val_loss\n torch.save(self.net.state_dict(), \"best_model.pth\")\n print()\n self._save_train_history()\n \n def _plot_train_history(self):\n data = [self.losses, self.dice_scores, self.jaccard_scores]\n colors = ['deepskyblue', \"crimson\"]\n labels = [\n f\"\"\"\n train loss {self.losses['train'][-1]}\n val loss {self.losses['val'][-1]}\n \"\"\",\n \n f\"\"\"\n train dice score {self.dice_scores['train'][-1]}\n val dice score {self.dice_scores['val'][-1]} \n \"\"\", \n \n f\"\"\"\n train jaccard score {self.jaccard_scores['train'][-1]}\n val jaccard score {self.jaccard_scores['val'][-1]}\n \"\"\",\n ]\n \n clear_output(True)\n with plt.style.context(\"seaborn-dark-palette\"):\n fig, axes = plt.subplots(3, 1, figsize=(8, 10))\n for i, ax in enumerate(axes):\n ax.plot(data[i]['val'], c=colors[0], label=\"val\")\n ax.plot(data[i]['train'], c=colors[-1], label=\"train\")\n ax.set_title(labels[i])\n ax.legend(loc=\"upper right\")\n \n plt.tight_layout()\n plt.show()\n \n def load_predtrain_model(self,\n state_path: str):\n self.net.load_state_dict(torch.load(state_path))\n print(\"Predtrain model loaded\")\n \n def _save_train_history(self):\n \"\"\"writing model weights and training logs to files.\"\"\"\n torch.save(self.net.state_dict(),\n f\"last_epoch_model.pth\")\n\n logs_ = [self.losses, self.dice_scores, self.jaccard_scores]\n log_names_ = [\"_loss\", \"_dice\", \"_jaccard\"]\n logs = [logs_[i][key] for i in list(range(len(logs_)))\n for key in logs_[i]]\n log_names = [key+log_names_[i] \n for i in list(range(len(logs_))) \n for key in logs_[i]\n ]\n pd.DataFrame(\n dict(zip(log_names, logs))\n ).to_csv(\"train_log.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2024-01-08T07:49:50.769095Z","iopub.execute_input":"2024-01-08T07:49:50.769464Z","iopub.status.idle":"2024-01-08T07:49:50.813066Z","shell.execute_reply.started":"2024-01-08T07:49:50.769413Z","shell.execute_reply":"2024-01-08T07:49:50.8121Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"trainer = Trainer(net=model,\n criterion=BCEDiceLoss(),\n lr=8e-5,\n accumulation_steps=32,\n batch_size=8,\n num_epochs=1,\n imgs_dir = config.path_to_imgs_dir,\n masks_dir = config.path_to_masks_dir,\n path_to_csv = config.path_to_csv,)\n\nif config.pretrained_model_path is not None:\n trainer.load_predtrain_model(config.pretrained_model_path)\n \n # if need - load the logs. \n train_logs = pd.read_csv(config.train_logs_path)\n trainer.losses[\"train\"] = train_logs.loc[:, \"train_loss\"].to_list()\n trainer.losses[\"val\"] = train_logs.loc[:, \"val_loss\"].to_list()\n trainer.dice_scores[\"train\"] = train_logs.loc[:, \"train_dice\"].to_list()\n trainer.dice_scores[\"val\"] = train_logs.loc[:, \"val_dice\"].to_list()\n trainer.jaccard_scores[\"train\"] = train_logs.loc[:, \"train_jaccard\"].to_list()\n trainer.jaccard_scores[\"val\"] = train_logs.loc[:, \"val_jaccard\"].to_list()","metadata":{"id":"ULnA0lkgUPmI","outputId":"d83b2393-ca73-40dc-cd12-ab02b735e240","execution":{"iopub.status.busy":"2024-01-08T07:49:50.81449Z","iopub.execute_input":"2024-01-08T07:49:50.814892Z","iopub.status.idle":"2024-01-08T07:49:51.120136Z","shell.execute_reply.started":"2024-01-08T07:49:50.814855Z","shell.execute_reply":"2024-01-08T07:49:51.119139Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ntrainer.train()","metadata":{"id":"iM-3o86EUPre","outputId":"34dd86f5-6f20-4a41-ae37-e17954ce21d4","execution":{"iopub.status.busy":"2024-01-08T07:49:51.121473Z","iopub.execute_input":"2024-01-08T07:49:51.121754Z","iopub.status.idle":"2024-01-08T08:03:07.3156Z","shell.execute_reply.started":"2024-01-08T07:49:51.121724Z","shell.execute_reply":"2024-01-08T08:03:07.314724Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Experiments and Results","metadata":{"id":"okfuiTuAaGLp"}},{"cell_type":"code","source":"val_dataloader = get_dataloader(\n imgs_dir=config.path_to_imgs_dir,\n masks_dir=config.path_to_masks_dir,\n path_to_csv=config.path_to_csv,\n phase = \"val\",\n batch_size = 8,\n num_workers = 6,\n test_size = 0.2,\n)","metadata":{"id":"H0AgOf_SbgYF","execution":{"iopub.status.busy":"2024-01-08T08:03:07.317437Z","iopub.execute_input":"2024-01-08T08:03:07.317823Z","iopub.status.idle":"2024-01-08T08:03:07.357443Z","shell.execute_reply.started":"2024-01-08T08:03:07.317778Z","shell.execute_reply":"2024-01-08T08:03:07.356818Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndice_scores_per_classes, iou_scores_per_classes = compute_scores_per_classes(\n model, val_dataloader, ['lung', 'heart', 'trachea']\n )","metadata":{"id":"TG9fX_mzaNS5","outputId":"438b6e3d-5172-4d08-fa65-cc19b955268a","execution":{"iopub.status.busy":"2024-01-08T08:03:07.35868Z","iopub.execute_input":"2024-01-08T08:03:07.358929Z","iopub.status.idle":"2024-01-08T08:04:12.150155Z","shell.execute_reply.started":"2024-01-08T08:03:07.358904Z","shell.execute_reply":"2024-01-08T08:04:12.149175Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dice_df = pd.DataFrame(dice_scores_per_classes)\ndice_df.columns = ['lung dice', 'heart dice', 'trachea dice']\n\niou_df = pd.DataFrame(iou_scores_per_classes)\niou_df.columns = ['lung jaccard', 'heart jaccard', 'trachea jaccard']\nval_metics_df = pd.concat([dice_df, iou_df], axis=1, sort=True)\nval_metics_df = val_metics_df.loc[:, ['lung dice', 'lung jaccard', \n 'heart dice', 'heart jaccard', \n 'trachea dice', 'trachea jaccard']]\nval_metics_df","metadata":{"id":"J0SRSJrLaNad","outputId":"bff0ea2a-274c-48a2-920c-aa95c68502ff","execution":{"iopub.status.busy":"2024-01-08T08:04:12.151829Z","iopub.execute_input":"2024-01-08T08:04:12.152154Z","iopub.status.idle":"2024-01-08T08:04:12.189902Z","shell.execute_reply.started":"2024-01-08T08:04:12.152119Z","shell.execute_reply":"2024-01-08T08:04:12.189094Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"colors = ['#35FCFF', '#FF355A', '#96C503', '#C5035B', '#28B463', '#35FFAF']\npalette = sns.color_palette(colors, 6)\n\nfig, ax = plt.subplots(figsize=(12, 6));\nsns.barplot(x=val_metics_df.mean().index, y=val_metics_df.mean(), palette=palette, ax=ax);\nax.set_xticklabels(val_metics_df.columns, fontsize=14, rotation=15);\nax.set_title(\"Dice and Jaccard Coefficients from Validation\", fontsize=20)\n\nfor idx, p in enumerate(ax.patches):\n percentage = '{:.1f}%'.format(100 * val_metics_df.mean().values[idx])\n x = p.get_x() + p.get_width() / 2 - 0.15\n y = p.get_y() + p.get_height()\n ax.annotate(percentage, (x, y), fontsize=15, fontweight=\"bold\")\n\nfig.savefig(\"result1.png\", format=\"png\", pad_inches=0.2, transparent=False, bbox_inches='tight')\nfig.savefig(\"result1.svg\", format=\"svg\", pad_inches=0.2, transparent=False, bbox_inches='tight')","metadata":{"id":"PVbmrufYaNYh","outputId":"8785b132-f120-4421-a397-7cdc1268b07b","execution":{"iopub.status.busy":"2024-01-08T08:04:12.191207Z","iopub.execute_input":"2024-01-08T08:04:12.191468Z","iopub.status.idle":"2024-01-08T08:04:12.634685Z","shell.execute_reply.started":"2024-01-08T08:04:12.191441Z","shell.execute_reply":"2024-01-08T08:04:12.633835Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"colors = ['#35FCFF', '#FF355A', '#28B463', '#35FFAF', '#96C503', '#C5035B']\npalette = sns.color_palette(colors[1::], 3)\n\nfig, ax = plt.subplots(1, 2, figsize=(20, 5))\nsns.boxplot(data=dice_df, palette=palette, ax=ax[0])\nax[0].set_ylabel(\"Dice coefficients for 3342 slices\", fontsize=14)\nax[0].set_title(\"Dice coefficients from Validation\", fontsize=20)\nax[0].set_xticklabels(dice_df.columns, fontsize=14)\n\nsns.boxplot(data=iou_df, palette=palette, ax=ax[1])\nax[1].set_ylabel(\"Jaccard coefficients for 3342 slices\", fontsize=14)\nax[1].set_title(\"Jaccard coefficients from Validation\", fontsize=20)\nax[1].set_xticklabels(iou_df.columns, fontsize=14)\nplt.tight_layout()\n\nfig.savefig(\"result2.png\", format=\"png\", pad_inches=0.2, transparent=False, bbox_inches='tight')\nfig.savefig(\"result2.svg\", format=\"svg\", pad_inches=0.2, transparent=False, bbox_inches='tight')","metadata":{"id":"IxOrlMixjApG","outputId":"77687e65-d2c7-4ebd-d7b3-a1205eee4433","execution":{"iopub.status.busy":"2024-01-08T08:04:12.636338Z","iopub.execute_input":"2024-01-08T08:04:12.636723Z","iopub.status.idle":"2024-01-08T08:04:13.619429Z","shell.execute_reply.started":"2024-01-08T08:04:12.636682Z","shell.execute_reply":"2024-01-08T08:04:13.618405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"and train history logs ","metadata":{"id":"RCFfMqRcjaTU"}},{"cell_type":"code","source":"train_logs = pd.read_csv(config.train_logs_path)\ntrain_logs.head(5)","metadata":{"id":"Ph3v04BCja3L","outputId":"59125857-f0c6-4af8-f855-8a1c15ec0024","execution":{"iopub.status.busy":"2024-01-08T08:04:13.6209Z","iopub.execute_input":"2024-01-08T08:04:13.621354Z","iopub.status.idle":"2024-01-08T08:04:13.644822Z","shell.execute_reply.started":"2024-01-08T08:04:13.621305Z","shell.execute_reply":"2024-01-08T08:04:13.64362Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"colors = ['#C042FF', '#03C576FF', '#FF355A', '#03C5BF', '#96C503', '#C5035B']\npalettes = [sns.color_palette(colors, 2),\n sns.color_palette(colors, 4), \n sns.color_palette(colors[:2]+colors[-2:] + colors[2:-2], 6)]\n \nfig, ax = plt.subplots(1, 3, figsize=(22, 4))\n\nsns.lineplot(data=train_logs.iloc[:, :2], palette=palettes[0], markers=True, ax=ax[0], linewidth=2.5,)\nax[0].set_title(\"Loss Function during Model Training\", fontsize=14)\nax[0].set_xlabel(\"Epoch\", fontsize=14)\n\nsns.lineplot(data=train_logs.iloc[:, 2:], palette=palettes[1], markers=True, ax=ax[1], linewidth=2.5, legend=\"full\")\nax[1].set_title(\"Dice and Jaccard Coefficients during Model Training\", fontsize=14)\nax[1].set_xlabel(\"Epoch\", fontsize=14)\n\nsns.boxplot(data=val_metics_df.iloc[:,:], palette=palettes[2], ax=ax[2])\nax[2].set_title(\"Dice and Jaccard Coefficients for each Label from Validation\", fontsize=14)\nax[2].set_xticklabels(val_metics_df.columns, fontsize=10, rotation=15)\n\nplt.tight_layout()\nfig.savefig(\"result3.png\", format=\"png\", pad_inches=0.2, transparent=False, bbox_inches='tight')\nfig.savefig(\"result3.svg\", format=\"svg\", pad_inches=0.2, transparent=False, bbox_inches='tight')","metadata":{"id":"aPCFHGIkja6k","outputId":"6eeaa91e-9720-49bc-ff09-35876ace4a5c","execution":{"iopub.status.busy":"2024-01-08T08:04:13.646648Z","iopub.execute_input":"2024-01-08T08:04:13.647083Z","iopub.status.idle":"2024-01-08T08:04:15.555012Z","shell.execute_reply.started":"2024-01-08T08:04:13.647012Z","shell.execute_reply":"2024-01-08T08:04:15.554245Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Now let's make a video with overlapped masks for each slice of one id CT ","metadata":{"id":"v_o71Xz4j5qL"}},{"cell_type":"code","source":"df = pd.read_csv(config.path_to_csv)\ndf[\"Id\"] = df['ImageId'].apply(lambda x: x.split(\"_\")[0])\n\nid_ = 'ID00400637202305055099402'\nfull_scan_example = df.loc[df['Id'] == id_].reset_index(drop=True)\nfull_scan_example ","metadata":{"id":"jKRO64tRjAmC","outputId":"dc6b0851-5cb9-4e45-f253-232a450fc0c8","execution":{"iopub.status.busy":"2024-01-08T08:04:15.55632Z","iopub.execute_input":"2024-01-08T08:04:15.556649Z","iopub.status.idle":"2024-01-08T08:04:15.619477Z","shell.execute_reply.started":"2024-01-08T08:04:15.55662Z","shell.execute_reply":"2024-01-08T08:04:15.618529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"get_color_info()","metadata":{"execution":{"iopub.status.busy":"2024-01-08T08:04:15.621268Z","iopub.execute_input":"2024-01-08T08:04:15.621659Z","iopub.status.idle":"2024-01-08T08:04:15.992398Z","shell.execute_reply.started":"2024-01-08T08:04:15.621617Z","shell.execute_reply":"2024-01-08T08:04:15.991496Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Ground Truth","metadata":{"id":"MGE1R-8ZuFw2"}},{"cell_type":"code","source":"PATH_TO_SAVE = id_ + \"_ground_truth\"\n\nif not os.path.exists(PATH_TO_SAVE):\n os.mkdir(PATH_TO_SAVE)\n print(f\"Folder {PATH_TO_SAVE} created.\")\n\nget_overlaid_masks_on_full_ctscan(ct_scan_id_df=full_scan_example,\n path_to_save=\"./\" +PATH_TO_SAVE,\n root_imgs_dir = '../input/chest-ct-segmentation/images/images/', \n root_masks_dir = '../input/chest-ct-segmentation/masks/masks/')\n","metadata":{"id":"ihOjemlbaNWA","execution":{"iopub.status.busy":"2024-01-08T08:04:15.994163Z","iopub.execute_input":"2024-01-08T08:04:15.994546Z","iopub.status.idle":"2024-01-08T08:05:27.951426Z","shell.execute_reply.started":"2024-01-08T08:04:15.994506Z","shell.execute_reply":"2024-01-08T08:05:27.950515Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ncreate_video(path_to_imgs=PATH_TO_SAVE, video_name=id_+\"_ground_truth\", framerate=30)","metadata":{"id":"_wgi6MDjUPpJ","outputId":"7294f634-c5db-4138-8c48-f811edece77a","_kg_hide-output":false,"execution":{"iopub.status.busy":"2024-01-08T08:05:27.952765Z","iopub.execute_input":"2024-01-08T08:05:27.953218Z","iopub.status.idle":"2024-01-08T08:05:30.568091Z","shell.execute_reply.started":"2024-01-08T08:05:27.953167Z","shell.execute_reply":"2024-01-08T08:05:30.567272Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# install any fonts\n!wget -O bitwise.zip https://www.1001freefonts.com/d/8190/bitwise.zip\n!unzip bitwise.zip","metadata":{"_kg_hide-output":true,"_kg_hide-input":false,"execution":{"iopub.status.busy":"2024-01-08T08:05:30.569334Z","iopub.execute_input":"2024-01-08T08:05:30.569619Z","iopub.status.idle":"2024-01-08T08:05:33.316183Z","shell.execute_reply.started":"2024-01-08T08:05:30.569589Z","shell.execute_reply":"2024-01-08T08:05:33.315095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ls -l\n","metadata":{"execution":{"iopub.status.busy":"2024-01-08T08:05:33.317701Z","iopub.execute_input":"2024-01-08T08:05:33.318004Z","iopub.status.idle":"2024-01-08T08:05:34.348605Z","shell.execute_reply.started":"2024-01-08T08:05:33.317972Z","shell.execute_reply":"2024-01-08T08:05:34.347576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import filecmp\n\nfile1 = 'new_transcoded_video.mp4'\nfile2 = 'transcoded_video1.mp4'\n\ncomparison = filecmp.cmp(file1, file2)\nif comparison:\n print(\"这两个文件相同\")\nelse:\n print(\"这两个文件不同\")\n","metadata":{"execution":{"iopub.status.busy":"2024-01-08T08:05:34.349995Z","iopub.execute_input":"2024-01-08T08:05:34.350283Z","iopub.status.idle":"2024-01-08T08:05:34.360884Z","shell.execute_reply.started":"2024-01-08T08:05:34.350254Z","shell.execute_reply":"2024-01-08T08:05:34.359956Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%bash\n\n# to play in google colab had to recode\n#https://ottverse.com/ffmpeg-drawtext-filter-dynamic-overlays-timecode-scrolling-text-credits/\nffmpeg -i 'ID00400637202305055099402_ground_truth.avi' -strict -2 -y 'new_transcoded_video.mp4'\n","metadata":{"id":"GxDMwTMuuJ3m","_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-01-08T08:05:34.362127Z","iopub.execute_input":"2024-01-08T08:05:34.362399Z","iopub.status.idle":"2024-01-08T08:05:38.717945Z","shell.execute_reply.started":"2024-01-08T08:05:34.362372Z","shell.execute_reply":"2024-01-08T08:05:38.71688Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"show_video(\"transcoded_video1.mp4\")","metadata":{"id":"i3Sqb1kYuJ0-","outputId":"b0886607-87b2-4885-c3d3-770725b180a0","execution":{"iopub.status.busy":"2024-01-08T08:05:38.719667Z","iopub.execute_input":"2024-01-08T08:05:38.719978Z","iopub.status.idle":"2024-01-08T08:05:38.841168Z","shell.execute_reply.started":"2024-01-08T08:05:38.719945Z","shell.execute_reply":"2024-01-08T08:05:38.840125Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Prediction","metadata":{"id":"F32sZOILuXKl"}},{"cell_type":"code","source":"imgs, predictions = get_id_predictions(net=model,\n ct_scan_id_df=full_scan_example,\n root_imgs_dir=config.path_to_imgs_dir)","metadata":{"id":"lU3dE5LmuJv6","outputId":"7908369a-a1bb-47ce-f527-cc618e1e1f71","execution":{"iopub.status.busy":"2024-01-08T08:05:38.842547Z","iopub.execute_input":"2024-01-08T08:05:38.842847Z","iopub.status.idle":"2024-01-08T08:05:49.132201Z","shell.execute_reply.started":"2024-01-08T08:05:38.842817Z","shell.execute_reply":"2024-01-08T08:05:49.131071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nPATH_TO_SAVE = id_ + \"_predictions\"\n\nif not os.path.exists(PATH_TO_SAVE):\n os.mkdir(PATH_TO_SAVE)\n print(f\"Folder {PATH_TO_SAVE} created.\")\n\n_= [\n get_overlaid_masks_on_image(one_slice_image=image,\n one_slice_mask=mask, \n write=True,\n path_to_save=PATH_TO_SAVE,\n name_to_save= str(i_name)\n ) \n for i_name, (image, mask) in enumerate(zip(imgs, predictions))\n ]","metadata":{"id":"SjzuZ_a9uYDJ","outputId":"62680016-1cef-4bbe-9d5c-c68e45f5e9fc","execution":{"iopub.status.busy":"2024-01-08T08:05:49.133527Z","iopub.execute_input":"2024-01-08T08:05:49.133817Z","iopub.status.idle":"2024-01-08T08:06:58.240914Z","shell.execute_reply.started":"2024-01-08T08:05:49.133787Z","shell.execute_reply":"2024-01-08T08:06:58.239985Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ncreate_video(path_to_imgs=PATH_TO_SAVE, video_name=id_+\"_predictions\", framerate=30)","metadata":{"id":"ZFLexbXiuYIC","outputId":"5c93b9f8-089f-483f-ffd0-779249576efb","execution":{"iopub.status.busy":"2024-01-08T08:06:58.242307Z","iopub.execute_input":"2024-01-08T08:06:58.242613Z","iopub.status.idle":"2024-01-08T08:07:00.808265Z","shell.execute_reply.started":"2024-01-08T08:06:58.242583Z","shell.execute_reply":"2024-01-08T08:07:00.807485Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\n\nfile_path = '/kaggle/input/text12/Bitwise.ttf' # 替换为你的字体文件路径\n\nif os.path.exists(file_path):\n print(f\"文件 '{file_path}' 存在\")\nelse:\n print(f\"文件 '{file_path}' 不存在\")\n","metadata":{"execution":{"iopub.status.busy":"2024-01-08T08:07:00.809486Z","iopub.execute_input":"2024-01-08T08:07:00.809767Z","iopub.status.idle":"2024-01-08T08:07:00.818744Z","shell.execute_reply.started":"2024-01-08T08:07:00.809738Z","shell.execute_reply":"2024-01-08T08:07:00.817884Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%bash\nffmpeg -i 'ID00400637202305055099402_predictions.avi' -vf \"drawtext=text='Prediction':x=195:y=8:fontsize=24:fontfile=/kaggle/input/text12/Bitwise.ttf:fontcolor=#FFFFFF\" -strict -2 -y 'transcoded_video2.mp4'\n","metadata":{"id":"mciRdYbIuYAo","_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-01-08T08:07:00.823059Z","iopub.execute_input":"2024-01-08T08:07:00.823351Z","iopub.status.idle":"2024-01-08T08:07:04.909808Z","shell.execute_reply.started":"2024-01-08T08:07:00.823322Z","shell.execute_reply":"2024-01-08T08:07:04.908659Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"show_video(\"transcoded_video2.mp4\")","metadata":{"id":"IYyUAwIvulLj","outputId":"4feeb8eb-36bc-4667-f3ae-c596bca0387d","execution":{"iopub.status.busy":"2024-01-08T08:07:04.912073Z","iopub.execute_input":"2024-01-08T08:07:04.912495Z","iopub.status.idle":"2024-01-08T08:07:05.029258Z","shell.execute_reply.started":"2024-01-08T08:07:04.912449Z","shell.execute_reply":"2024-01-08T08:07:05.028444Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Merging video with ground truth slices and video with predicted slices","metadata":{"id":"LJigaNjiuojR"}},{"cell_type":"code","source":"%%bash\n# https://unix.stackexchange.com/questions/233832/merge-two-video-clips-into-one-placing-them-next-to-each-other\nffmpeg \\\n -i transcoded_video1.mp4 \\\n -i transcoded_video2.mp4 \\\n -filter_complex '[0:v]pad=iw*2:ih[int];[int][1:v]overlay=W/2:0[vid]' \\\n -map [vid] \\\n -c:v libx264 \\\n -crf 23 \\\n -preset veryfast \\\n result.mp4","metadata":{"id":"mY7OYIX8ulJE","_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-01-08T08:07:05.030521Z","iopub.execute_input":"2024-01-08T08:07:05.030815Z","iopub.status.idle":"2024-01-08T08:07:05.245261Z","shell.execute_reply.started":"2024-01-08T08:07:05.030786Z","shell.execute_reply":"2024-01-08T08:07:05.243308Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"show_video(\"result.mp4\")","metadata":{"id":"ba-hcM-PuX-T","outputId":"939630c3-4f8e-45e9-a2fb-3f1ed8a98986","execution":{"iopub.status.busy":"2024-01-08T08:07:05.246499Z","iopub.status.idle":"2024-01-08T08:07:05.246931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!rm -r ID00400637202305055099402_ground_truth\n!rm -r ID00400637202305055099402_predictions","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-01-08T08:07:05.248139Z","iopub.status.idle":"2024-01-08T08:07:05.248758Z"},"trusted":true},"execution_count":null,"outputs":[]}]}