{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"colab":{"machine_shape":"hm","gpuType":"T4"},"accelerator":"GPU","kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":20270,"databundleVersionId":1222630,"sourceType":"competition"},{"sourceId":9797223,"sourceType":"datasetVersion","datasetId":982170},{"sourceId":265829014,"sourceType":"kernelVersion"}],"dockerImageVersionId":31090,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import sys\nsys.path.append(\"../input/tez-lib/\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:24:41.144862Z","iopub.execute_input":"2025-09-09T06:24:41.145141Z","iopub.status.idle":"2025-09-09T06:24:41.149338Z","shell.execute_reply.started":"2025-09-09T06:24:41.145122Z","shell.execute_reply":"2025-09-09T06:24:41.148622Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# import timm\n# from pprint import pprint\n# model_names = timm.list_models(pretrained=True)\n# pprint(model_names)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:31:24.757576Z","iopub.execute_input":"2025-09-09T06:31:24.758251Z","iopub.status.idle":"2025-09-09T06:31:24.761386Z","shell.execute_reply.started":"2025-09-09T06:31:24.758225Z","shell.execute_reply":"2025-09-09T06:31:24.760629Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import random\nimport numpy as np\nimport torch\nimport os\n\ndef seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    \nseed_everything(42)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:24:41.796277Z","iopub.execute_input":"2025-09-09T06:24:41.796642Z","iopub.status.idle":"2025-09-09T06:24:41.80599Z","shell.execute_reply.started":"2025-09-09T06:24:41.796619Z","shell.execute_reply":"2025-09-09T06:24:41.80541Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch.nn as nn\n\nfrom tez import Tez, TezConfig\nimport tez\nimport albumentations\nimport pandas as pd\nimport cv2\nimport numpy as np\nimport timm\nimport torch.nn as nn\nfrom sklearn import metrics\nimport torch\nfrom tez.callbacks import EarlyStopping\nfrom tqdm import tqdm","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:24:42.346696Z","iopub.execute_input":"2025-09-09T06:24:42.347353Z","iopub.status.idle":"2025-09-09T06:24:44.837495Z","shell.execute_reply.started":"2025-09-09T06:24:42.347331Z","shell.execute_reply":"2025-09-09T06:24:44.83689Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class args:\n    batch_size = 8\n    image_size = 384\n    epochs = 10\n    fold = 0","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:24:44.838601Z","iopub.execute_input":"2025-09-09T06:24:44.839062Z","iopub.status.idle":"2025-09-09T06:24:44.842804Z","shell.execute_reply.started":"2025-09-09T06:24:44.839042Z","shell.execute_reply":"2025-09-09T06:24:44.842174Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class CustomDataset:\n    def __init__(self, image_paths, dense_features, targets, augmentations):\n        self.image_paths = image_paths\n        self.dense_features = dense_features\n        self.targets = targets\n        self.augmentations = augmentations\n        \n    def __len__(self):\n        return len(self.image_paths)\n    \n    def __getitem__(self, item):\n        image = cv2.imread(self.image_paths[item])\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        \n        if self.augmentations is not None:\n            augmented = self.augmentations(image=image)\n            image = augmented[\"image\"]\n            \n        image = np.transpose(image, (2, 0, 1)).astype(np.float32)\n        \n        features = self.dense_features[item, :]\n        targets = self.targets[item]\n        \n        return {\n            \"image\": torch.tensor(image, dtype=torch.float),\n            \"features\": torch.tensor(features, dtype=torch.float),\n            \"targets\": torch.tensor(targets, dtype=torch.long), # CHANGED dtype to torch.long for classification\n        }","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:24:44.843633Z","iopub.execute_input":"2025-09-09T06:24:44.843957Z","iopub.status.idle":"2025-09-09T06:24:44.859207Z","shell.execute_reply.started":"2025-09-09T06:24:44.843932Z","shell.execute_reply":"2025-09-09T06:24:44.858627Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# class PawpularModel(tez.Model):\nclass CustomModel(nn.Module):\n    def __init__(self):\n        super().__init__()        \n        self.model = timm.create_model(\"resnet50\", pretrained=True, in_chans=3)#resnet50#resnet101#eca_nfnet_l1#resnest101e\n\n        \n        self.dropout = nn.Dropout(0.5)\n        # self.out = nn.Linear(1280+12, 1)\n        self.out = nn.Linear(1000, 1)\n        # self.out_final = nn.Linear(512, 1)\n        \n        self.step_scheduler_after = \"epoch\"\n\n\n    def monitor_metrics(self, outputs, targets, loss):\n        probs = torch.sigmoid(outputs).cpu().detach().numpy()\n        targets_np = targets.cpu().detach().numpy()\n        \n        try:\n            auc = metrics.roc_auc_score(targets_np, probs)\n        except ValueError:\n            auc = 0.5 \n            \n        auc_tensor = torch.tensor(auc, dtype=torch.float)\n            \n        return {\"auc\": auc_tensor} \n\n    def optimizer_scheduler(self):\n        opt = torch.optim.AdamW(self.parameters(), lr=2.5e-05, weight_decay=0.01)\n        sch = torch.optim.lr_scheduler.CosineAnnealingWarmRestarts(\n            opt, T_0=10, T_mult=1, eta_min=1e-6, last_epoch=-1\n        )\n        return opt,sch\n\n    def forward(self, image, features, targets=None):\n\n        x = self.model(image)\n        x = self.dropout(x)\n        # x = torch.cat([x, features], dim=1)\n        # x = self.dropout(x)\n        x = self.out(x)\n        # x = self.dropout(x)\n        # x = self.out_final(x)\n\n        if targets is not None:\n            # targets.view(-1, 1).float() ensures targets are (batch_size, 1) and float type\n            loss = nn.BCEWithLogitsLoss()(x, targets.view(-1, 1).float()) \n            metrics = self.monitor_metrics(x, targets, loss)\n            return x, loss, metrics\n        return x, 0, {}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:37:54.586973Z","iopub.execute_input":"2025-09-09T06:37:54.58724Z","iopub.status.idle":"2025-09-09T06:37:54.594198Z","shell.execute_reply.started":"2025-09-09T06:37:54.587221Z","shell.execute_reply":"2025-09-09T06:37:54.593631Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_aug = albumentations.Compose(\n    [\n        albumentations.LongestMaxSize(args.image_size, p=1),\n        albumentations.PadIfNeeded(args.image_size,args.image_size, p=1,border_mode=0),\n        \n       albumentations.HorizontalFlip(p=0.5),\n       albumentations.VerticalFlip(p=0.1),\n       albumentations.Rotate(limit=180, p=0.5),\n       albumentations.ShiftScaleRotate(\n                shift_limit=0.1, scale_limit=0.1, rotate_limit=45, p=0.5\n            ),\n        \n        albumentations.HueSaturationValue(\n            hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.5\n        ),\n        albumentations.RandomBrightnessContrast(\n            brightness_limit=(-0.1, 0.1), contrast_limit=(-0.1, 0.1), p=0.5\n        ),\n        albumentations.Normalize(\n            mean=[0.485, 0.456, 0.406],\n            std=[0.229, 0.224, 0.225],\n            max_pixel_value=255.0,\n            p=1.0,\n        ),\n    ],\n    p=1.0,\n)\n\nvalid_aug = albumentations.Compose(\n    [\n#         albumentations.Resize(args.image_size, args.image_size, p=1),\n        albumentations.LongestMaxSize(args.image_size, p=1),\n        albumentations.PadIfNeeded(args.image_size,args.image_size, p=1,border_mode=0),\n        albumentations.Normalize(\n            mean=[0.485, 0.456, 0.406],\n            std=[0.229, 0.224, 0.225],\n            max_pixel_value=255.0,\n            p=1.0,\n        ),\n    ],\n    p=1.0,\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:37:57.576245Z","iopub.execute_input":"2025-09-09T06:37:57.577037Z","iopub.status.idle":"2025-09-09T06:37:57.58831Z","shell.execute_reply.started":"2025-09-09T06:37:57.577007Z","shell.execute_reply":"2025-09-09T06:37:57.587602Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/dharma-srujan-reddy-23bcs10107/train_5folds.csv\")\ndf.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:37:58.793488Z","iopub.execute_input":"2025-09-09T06:37:58.79402Z","iopub.status.idle":"2025-09-09T06:37:58.822413Z","shell.execute_reply.started":"2025-09-09T06:37:58.793999Z","shell.execute_reply":"2025-09-09T06:37:58.821866Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"i=0\nprint(f'training fold: {i} start')\nargs.fold = 0\ndf_train = df[df.kfold != args.fold].reset_index(drop=True)\ndf_valid = df[df.kfold == args.fold].reset_index(drop=True)\ndense_features = [\n   \n]\ntrain_img_paths = [f\"/kaggle/input/siim-isic-melanoma-classification/jpeg/train/{x}.jpg\" for x in df_train[\"image_name\"].values]\nvalid_img_paths = [f\"/kaggle/input/siim-isic-melanoma-classification/jpeg/train/{x}.jpg\" for x in df_valid[\"image_name\"].values]\ntrain_dataset = CustomDataset(\n    image_paths=train_img_paths,\n    dense_features=df_train[dense_features].values,\n    targets=df_train.target.values,\n    augmentations=train_aug,\n)\n\nvalid_dataset = CustomDataset(\n    image_paths=valid_img_paths,\n    dense_features=df_valid[dense_features].values,\n    targets=df_valid.target.values,\n    augmentations=valid_aug,\n)\n\nmodel = CustomModel()\nmodel = Tez(model)\nconfig = TezConfig(\n    training_batch_size=args.batch_size,\n    validation_batch_size=2 * args.batch_size,\n    epochs=args.epochs,\n    step_scheduler_after=\"epoch\",\n    step_scheduler_metric=\"valid_auc\",\n    fp16=True,\n    # fp16=False,\n    val_strategy=\"batch\",\n    val_steps=900,\n)\n\nes = EarlyStopping(\n    monitor=\"valid_auc\",\n    model_path=f\"model_f{args.fold}.bin\",\n    patience=4,\n    mode=\"max\",\n    save_weights_only=True,\n)\n\nmodel.fit(\n    train_dataset,\n    valid_dataset=valid_dataset,\n    callbacks=[es],\n    config=config,\n)\nprint(f'training fold: {i} complete')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-09T06:37:59.036698Z","iopub.execute_input":"2025-09-09T06:37:59.03702Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}