{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"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"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":112509,"databundleVersionId":14254895,"isSourceIdPinned":false,"sourceType":"competition"},{"sourceId":271757195,"sourceType":"kernelVersion"}],"dockerImageVersionId":31154,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import timm\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nfrom PIL import Image\nimport torchvision.transforms as T\nimport pytorch_lightning as pl\nimport random\nimport os\nimport numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import KFold\n\n# ======== Seed ========\ndef seed_everything(seed: int = 42):\n    pl.seed_everything(seed, workers=True)\n    random.seed(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed_all(seed)\n    os.environ[\"PYTHONHASHSEED\"] = str(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = False\n\nseed_everything(42)\n\n# ======== Weighted R2 Metric (added missing function) ========\nfrom sklearn.metrics import r2_score\n\ndef weighted_r2_score(y_true, y_pred):\n    \"\"\"Computes weighted and per-target R².\"\"\"\n    r2s = [r2_score(y_true[:, i], y_pred[:, i]) for i in range(y_true.shape[1])]\n    weights = np.array([1, 1, 1, 2, 2])  # example weighting; adjust if known\n    weighted_r2 = np.average(r2s, weights=weights)\n    return weighted_r2, r2s\n\n# ======== Dataset ========\nclass InferenceDataset(Dataset):\n    def __init__(self, df, transform=None):\n        self.df = df\n        self.transform = transform\n\n    def __len__(self):\n        return len(self.df)\n\n    def __getitem__(self, idx):\n        row = self.df.iloc[idx]\n        img_path = os.path.join(\"/kaggle/input/csiro-biomass\", row[\"image_path\"])\n        image = Image.open(img_path).convert(\"RGB\")\n        if self.transform:\n            image = self.transform(image)\n        return image\n\n# ======== Model ========\nclass MultiRegressionModel(pl.LightningModule):\n    def __init__(self, model_name=\"efficientnet_b0\", pretrained=False, lr=1e-4, output_dim=5):\n        super().__init__()\n        self.save_hyperparameters()\n        self.model = timm.create_model(model_name, pretrained=pretrained, num_classes=output_dim)\n        self.criterion = nn.MSELoss()\n        self.val_outputs = []\n\n    def forward(self, x):\n        return self.model(x)\n\n    def training_step(self, batch, batch_idx):\n        x, y = batch\n        y_hat = self(x)\n        loss = self.criterion(y_hat, y)\n        self.log(\"train_loss\", loss, on_step=False, on_epoch=True)\n        return loss\n\n    def validation_step(self, batch, batch_idx):\n        x, y = batch\n        y_hat = self(x)\n        loss = self.criterion(y_hat, y)\n        self.val_outputs.append((y_hat.detach().cpu(), y.detach().cpu()))\n        self.log(\"val_loss\", loss, on_step=False, on_epoch=True)\n        return loss\n\n    def on_validation_epoch_end(self):\n        if not self.val_outputs:\n            self.log(\"val_weighted_r2\", 0.0, prog_bar=True)\n            for name in [\"Dry_Green_g\", \"Dry_Dead_g\", \"Dry_Clover_g\", \"GDM_g\", \"Dry_Total_g\"]:\n                self.log(f\"val_r2_{name}\", 0.0)\n            return\n\n        preds, trues = zip(*self.val_outputs)\n        preds = torch.cat(preds).numpy()\n        trues = torch.cat(trues).numpy()\n        weighted_r2, r2s = weighted_r2_score(trues, preds)\n        self.log(\"val_weighted_r2\", weighted_r2, prog_bar=True)\n        for i, name in enumerate([\"Dry_Green_g\", \"Dry_Dead_g\", \"Dry_Clover_g\", \"GDM_g\", \"Dry_Total_g\"]):\n            self.log(f\"val_r2_{name}\", r2s[i])\n        self.val_outputs.clear()\n\n    def configure_optimizers(self):\n        optimizer = torch.optim.AdamW(self.parameters(), lr=self.hparams.lr)\n        scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)\n        return {\"optimizer\": optimizer, \"lr_scheduler\": scheduler}\n\n# ======== TTA ========\ndef tta_inference(model, images):\n    preds = model(images)\n    preds_lr = model(torch.flip(images, dims=[3]))\n    preds_ud = model(torch.flip(images, dims=[2]))\n    preds_lrud = model(torch.flip(images, dims=[2, 3]))\n    preds_mean = (preds + preds_lr + preds_ud + preds_lrud) / 4.0\n    return preds_mean\n\n# ======== Utils ========\ndef get_id(x):\n    return x.split('_')[0]\n\n# ======== Transform ========\nimg_size = 1000\ninfer_transform = T.Compose([\n    T.Resize((img_size, img_size)),\n    T.ToTensor(),\n    T.Normalize([0.485, 0.456, 0.406],\n                [0.229, 0.224, 0.225])\n])\n\n# ======== DataLoader ========\ntest_df = pd.read_csv('/kaggle/input/csiro-biomass/test.csv')\ntest_df = test_df[~test_df['image_path'].duplicated()][['sample_id', 'image_path']].reset_index(drop=True)\ntest_df['sample_id'] = test_df['sample_id'].apply(get_id)\ndataset = InferenceDataset(test_df, transform=infer_transform)\ndataloader = DataLoader(dataset, batch_size=8, shuffle=False, num_workers=2, pin_memory=True)\n\n# ======== Inference ========\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\nresults_dict = {}\n\nfor fold in range(3):\n    model_path = f\"/kaggle/input/csiro-img2bio-training-notebook/model_fold{fold}.pth\"\n    model = MultiRegressionModel(model_name=\"efficientnet_b2\", pretrained=False)\n    state_dict = torch.load(model_path, map_location=device)\n    model.load_state_dict(state_dict)\n    model.to(device)\n    model.eval()\n\n    results = []\n    with torch.no_grad():\n        for images in dataloader:\n            images = images.to(device)\n            preds = tta_inference(model, images)\n            preds = preds.cpu().numpy()\n            results.append(preds)\n    results_dict[fold] = np.concatenate(results)\n\n# ======== Submission ========\nmean_preds = np.mean([results_dict[fold] for fold in range(3)], axis=0)\nresult_df = pd.DataFrame(mean_preds, columns=[\"Dry_Green_g\", \"Dry_Dead_g\", \"Dry_Clover_g\", \"GDM_g\", \"Dry_Total_g\"])\nresult_df['sample_id'] = test_df['sample_id']\nresult_df = pd.melt(result_df, id_vars='sample_id',\n                    value_vars=[\"Dry_Green_g\", \"Dry_Dead_g\", \"Dry_Clover_g\", \"GDM_g\", \"Dry_Total_g\"],\n                    value_name='target')\nresult_df['sample_id'] = result_df['sample_id'] + '__' + result_df['variable']\nresult_df['target'] = result_df['target'].clip(0, 200)\nresult_df[['sample_id', 'target']].to_csv('submission.csv', index=False)\nprint(\"✅ submission.csv saved.\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-29T12:31:32.606288Z","iopub.execute_input":"2025-10-29T12:31:32.606958Z","iopub.status.idle":"2025-10-29T12:31:52.237206Z","shell.execute_reply.started":"2025-10-29T12:31:32.606901Z","shell.execute_reply":"2025-10-29T12:31:52.236250Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}