If you like this notebook, please give it an Upvote!
"},{"metadata":{"trusted":true},"cell_type":"code","source":"import sys\nsys.path.append(\"../input/timm-pytorch-image-models/pytorch-image-models-master\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport warnings\n\nimport cv2\nfrom tqdm.notebook import tqdm\n\nfrom albumentations import (\n HorizontalFlip, VerticalFlip, IAAPerspective, ShiftScaleRotate, CLAHE, RandomRotate90,\n Transpose, ShiftScaleRotate, Blur, OpticalDistortion, GridDistortion, HueSaturationValue,\n IAAAdditiveGaussianNoise, GaussNoise, MotionBlur, MedianBlur, IAAPiecewiseAffine, RandomResizedCrop,\n IAASharpen, IAAEmboss, RandomBrightnessContrast, Flip, OneOf, Compose, Normalize, Cutout, CoarseDropout, ShiftScaleRotate, CenterCrop, Resize\n)\n\nfrom albumentations.pytorch import ToTensorV2\n\nimport timm\n\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.utils.data import DataLoader, Dataset\nfrom torch.cuda.amp import autocast, GradScaler\nfrom torch.nn.modules.loss import _WeightedLoss\nfrom torch.optim.lr_scheduler import ReduceLROnPlateau, CosineAnnealingWarmRestarts\n\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import StratifiedKFold\n\nwarnings.simplefilter(\"ignore\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Config:\n CFG = {\n 'img_size': 384,\n }","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def plot_results(train_acc, valid_acc, train_loss, valid_loss, nb_epochs):\n epochs = [i for i in range(nb_epochs)]\n \n fig, ax = plt.subplots(1, 2)\n fig.set_size_inches(20, 10)\n \n ax[0].plot(epochs, train_acc, 'go-', label='Training Accuracy')\n ax[0].plot(epochs, valid_acc, 'ro-', label='Validation Accuracy')\n ax[0].set_title('Training & Validation Accuracy')\n ax[0].legend()\n ax[0].set_xlabel('Epochs')\n ax[0].set_ylabel('Accuracy')\n \n ax[1].plot(epochs, train_loss, 'go-', label='Training Loss')\n ax[1].plot(epochs, valid_loss, 'ro-', label='Validation Loss')\n ax[1].set_title('Training & Validation Loss')\n ax[1].legend()\n ax[1].set_xlabel('Epochs')\n ax[1].set_ylabel('Loss')\n \n plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Augments:\n \"\"\"\n Contains Train, Validation and Testing Augments\n \"\"\"\n train_augments = Compose([\n RandomResizedCrop(Config.CFG['img_size'], Config.CFG['img_size']),\n Transpose(p=0.5),\n HorizontalFlip(p=0.5),\n VerticalFlip(p=0.5),\n ShiftScaleRotate(p=0.5),\n Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], max_pixel_value=255.0, p=1.0),\n CoarseDropout(p=0.5),\n Cutout(p=0.5),\n ToTensorV2(p=1.0),\n ],p=1.)\n \n valid_augments = Compose([\n CenterCrop(Config.CFG['img_size'], Config.CFG['img_size'], p=1.),\n Resize(Config.CFG['img_size'], Config.CFG['img_size']),\n Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], max_pixel_value=255.0, p=1.0),\n ToTensorV2(p=1.0),\n ], p=1.)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class ResNextModel(nn.Module):\n \"\"\"\n Model Class for ResNext Model Architectures\n \"\"\"\n def __init__(self, num_classes=11, model_name='resnext50d_32x4d', pretrained=True):\n super(ResNextModel, self).__init__()\n self.model = timm.create_model(model_name, pretrained=pretrained)\n self.model.fc = nn.Linear(self.model.fc.in_features, num_classes)\n \n def forward(self, x):\n x = self.model(x)\n return x\n\nclass ResNetModel(nn.Module):\n \"\"\"\n Model Class for ResNet Models\n \"\"\"\n def __init__(self, num_classes=11, model_name='resnet18', pretrained=True):\n super(ResNetModel, self).__init__()\n self.model = timm.create_model(model_name, pretrained=pretrained)\n self.model.fc = nn.Linear(self.model.fc.in_features, num_classes)\n \n def forward(self, x):\n x = self.model(x)\n return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class RANCZRData(Dataset):\n def __init__(self, df, num_classes=5, is_train=True, augments=None, img_size=Config.CFG['img_size'], img_path=\"../input/ranzcr-clip-catheter-line-classification/train\"):\n super().__init__()\n self.df = df.sample(frac=1).reset_index(drop=True)\n self.num_classes = num_classes\n self.is_train = is_train\n self.augments = augments\n self.img_size = img_size\n self.img_path = img_path\n# img_path=\"../input/ranzcr-clip-catheter-line-classification/train\"\n \n # Add the Right Image Path\n# self.df['StudyInstanceUID'] = self.df['StudyInstanceUID'].apply(lambda x: os.path.join(self.img_path, x + \".jpg\"))\n \n def __getitem__(self, idx):\n image_id = self.df['StudyInstanceUID'].values[idx]\n image = cv2.imread(os.path.join(self.img_path, image_id + \".jpg\"))\n image = image[:, :, ::-1]\n \n # Augments must be albumentations\n if self.augments:\n img = self.augments(image=image)['image']\n \n if self.is_train:\n label = self.df[self.df['StudyInstanceUID'] == image_id].values.tolist()[0][1:-1]\n return img, torch.tensor(label)\n \n return img\n \n def __len__(self):\n return len(self.df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Trainer:\n def __init__(self, train_dataloader, valid_dataloader, model, optimizer, loss_fn, val_loss_fn, scheduler, device=\"cuda:0\", plot_results=True):\n \"\"\"\n TODO: Implement the ROC-AUC Scheduler stuff\n \"\"\"\n self.train = train_dataloader\n self.valid = valid_dataloader\n self.optim = optim\n self.loss_fn = loss_fn\n self.val_loss_fn = val_loss_fn\n self.scheduler = scheduler\n self.device = device\n self.plot_results = plot_results\n \n def train_one_cycle(self):\n \"\"\"\n Runs one epoch of training, backpropagation, optimization and gets train accuracy\n \"\"\"\n model.train()\n train_prog_bar = tqdm(self.train, total=len(self.train))\n\n all_train_labels = []\n all_train_preds = []\n \n running_loss = 0\n \n for xtrain, ytrain in train_prog_bar:\n xtrain = xtrain.to(device).float()\n ytrain = ytrain.to(device).float()\n \n with autocast():\n # Get predictions\n z = model(xtrain)\n\n # Training\n train_loss = self.loss_fn(z, ytrain)\n scaler.scale(train_loss).backward()\n \n scaler.step(self.optim)\n scaler.update()\n self.optim.zero_grad()\n\n # For averaging and reporting later\n running_loss += train_loss\n\n # Convert the predictions and corresponding labels to right form\n train_predictions = torch.argmax(z, 1).detach().cpu().numpy()\n train_labels = ytrain.detach().cpu().numpy()\n\n # Append current predictions and current labels to a list\n all_train_labels += [train_predictions]\n all_train_preds += [train_labels]\n\n # Show the current loss to the progress bar\n train_pbar_desc = f'loss: {train_loss.item():.4f}'\n train_prog_bar.set_description(desc=train_pbar_desc)\n \n # After all the batches are done, calculate the training accuracy\n# all_train_preds = np.concatenate(all_train_preds)\n# all_train_labels = np.concatenate(all_train_labels)\n \n# train_acc = (all_train_preds == all_train_labels).mean()\n# print(f\"Training Accuracy: {train_acc:.4f}\")\n \n # Now average the running loss over all batches and return\n train_running_loss = running_loss / len(self.train)\n print(f\"Final Training Loss: {train_running_loss:.4f}\")\n \n # Free up memory\n del all_train_labels, all_train_preds, train_predictions, train_labels, xtrain, ytrain, z\n \n return train_running_loss\n\n def valid_one_cycle(self):\n \"\"\"\n Runs one epoch of prediction and validation accuracy calculation\n \"\"\" \n model.eval()\n \n valid_prog_bar = tqdm(self.valid, total=len(self.valid))\n \n with torch.no_grad():\n all_valid_labels = []\n all_valid_preds = []\n \n running_loss = 0\n \n for xval, yval in valid_prog_bar:\n xval = xval.to(device).float()\n yval = yval.to(device).float()\n \n val_z = model(xval)\n \n val_loss = self.val_loss_fn(val_z, yval)\n \n running_loss += val_loss.item()\n \n val_pred = torch.argmax(val_z, 1).detach().cpu().numpy()\n val_label = yval.detach().cpu().numpy()\n \n all_valid_labels += [val_label]\n all_valid_preds += [val_pred]\n \n # Show the current loss\n valid_pbar_desc = f\"loss: {val_loss.item():.4f}\"\n valid_prog_bar.set_description(desc=valid_pbar_desc)\n \n # Get the final loss\n final_loss_val = running_loss / len(self.valid)\n \n # Get Validation Accuracy\n all_valid_labels = np.concatenate(all_valid_labels)\n all_valid_preds = np.concatenate(all_valid_preds)\n \n# val_accuracy = (all_valid_preds == all_valid_labels).mean()\n print(f\"Final Validation Loss: {final_loss_val:.4f}\")\n \n # Free up memory\n del all_valid_labels, all_valid_preds, val_label, val_pred, xval, yval, val_z\n \n return (final_loss_val, model)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"nb_epochs = 10\ndevice = torch.device(\"cuda\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = pd.read_csv(\"../input/ranzcr-clip-catheter-line-classification/train.csv\")\ndata = data.sample(frac=1).reset_index(drop=True)\n\n# 27,583 in Train, 2500 in Valid\ntrain_split = data[2500:]\nvalid_split = data[:2500]\n\nprint(train_split.shape, valid_split.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_set = RANCZRData(df=train_split, augments=Augments.train_augments)\nvalid_set = RANCZRData(df=valid_split, augments=Augments.valid_augments)\n\ntrain = DataLoader(\n train_set,\n batch_size=16,\n shuffle=True,\n pin_memory=False,\n drop_last=False,\n num_workers=8\n)\n\nvalid = DataLoader(\n valid_set,\n batch_size=32,\n shuffle=False,\n pin_memory=False,\n num_workers=8\n)\n\nmodel = ResNetModel().to(device)\noptim = torch.optim.AdamW(model.parameters(), lr=1e-4, weight_decay=0.001)\nloss_fn_train = nn.BCEWithLogitsLoss()\nloss_fn_val = nn.BCEWithLogitsLoss()\n\ntrainer = Trainer(\n train_dataloader=train,\n valid_dataloader=valid,\n model=model,\n optimizer=optim,\n loss_fn=loss_fn_train,\n val_loss_fn=loss_fn_val,\n scheduler=None,\n device=device,\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# train_accs = []\n# valid_accs = []\ntrain_losses = []\nvalid_losses = []\n\nscaler = GradScaler()\n\nfor epoch in range(nb_epochs):\n print(f\"{'-'*20} EPOCH: {epoch+1}/{nb_epochs} {'-'*20}\")\n\n # Run one training epoch\n current_train_loss = trainer.train_one_cycle()\n# train_accs.append(current_train_acc)\n train_losses.append(current_train_loss)\n\n # Run one validation epoch\n current_val_loss, op_model = trainer.valid_one_cycle()\n# valid_accs.append(current_val_acc)\n valid_losses.append(current_val_loss)\n\n # Empty CUDA cache\n torch.cuda.empty_cache()\n \n # Save the model every epoch\n print(f\"Saving Model for this epoch...\")\n torch.save(op_model.state_dict(), f\"resnet18_model.pth\")\n \n# del train_set, valid_set, train, valid, model, optim, loss_fn, loss_fn_val, trainer, scaler\n# torch.cuda.empty_cache()\n\n# plot_results(train_accs, valid_accs, train_losses, valid_losses, nb_epochs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# plt.figure(figsize=(10))\nplt.plot(train_losses, 'go-')\nplt.plot(valid_losses, 'ro-')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}