{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":127713,"databundleVersionId":15291341,"sourceType":"competition"}],"dockerImageVersionId":31259,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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,"execution":{"iopub.status.busy":"2026-01-20T12:15:49.937392Z","iopub.execute_input":"2026-01-20T12:15:49.937634Z","iopub.status.idle":"2026-01-20T12:15:57.510690Z","shell.execute_reply.started":"2026-01-20T12:15:49.937604Z","shell.execute_reply":"2026-01-20T12:15:57.509673Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport pandas as pd\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torch.utils.data import Dataset, DataLoader\nfrom torchvision import transforms, models\nfrom PIL import Image\nfrom sklearn.model_selection import train_test_split\nfrom tqdm import tqdm\n\n# --- 1. AUTOMATIC PATH DETECTION ---\n# This block searches for the dataset so you don't have to guess the path\nDATA_DIR = None\nTRAIN_CSV_PATH = None\nTEST_CSV_PATH = None\n\nprint(\"Searching for dataset...\")\nfor root, dirs, files in os.walk('/kaggle/input'):\n    if 'train.csv' in files:\n        DATA_DIR = root\n        TRAIN_CSV_PATH = os.path.join(root, \"train.csv\")\n        TEST_CSV_PATH = os.path.join(root, \"test.csv\")\n        print(f\"✅ Dataset found at: {DATA_DIR}\")\n        break\n\nif DATA_DIR is None:\n    raise FileNotFoundError(\"Could not find 'train.csv' in /kaggle/input. Please check the dataset is added to the notebook.\")\n\n# Define image directories based on the found root\n# Note: Sometimes images are in a subfolder, sometimes in the same root. \n# We assume standard structure based on description:\nTRAIN_IMG_DIR = os.path.join(DATA_DIR, \"train_images\")\nTEST_IMG_DIR = os.path.join(DATA_DIR, \"test_images\")\n\n# --- 2. CONFIGURATION ---\nBATCH_SIZE = 32\nLEARNING_RATE = 0.001\nEPOCHS = 5 # Increase this to 10-15 for better results if time permits\nDEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"\nprint(f\"Using Device: {DEVICE}\")\n\n# --- 3. CUSTOM DATASET CLASS ---\nclass AnimeDataset(Dataset):\n    def __init__(self, df, img_dir, transform=None, is_test=False):\n        self.df = df\n        self.img_dir = img_dir\n        self.transform = transform\n        self.is_test = is_test\n\n    def __len__(self):\n        return len(self.df)\n\n    def __getitem__(self, idx):\n        row = self.df.iloc[idx]\n        img_name = row['id']\n        img_path = os.path.join(self.img_dir, img_name)\n        \n        # Error handling if a specific image is missing\n        if not os.path.exists(img_path):\n             # Fallback: return a black image or skip (simplified here)\n             # In competitions, usually all images exist.\n             print(f\"Warning: Image not found {img_path}\")\n        \n        image = Image.open(img_path).convert(\"RGB\")\n        \n        if self.transform:\n            image = self.transform(image)\n        \n        if self.is_test:\n            return image, img_name\n        else:\n            label = torch.tensor(row['label'], dtype=torch.float32)\n            return image, label\n\n# --- 4. AUGMENTATION & DATALOADERS ---\nimagenet_stats = ([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n\ntrain_transforms = transforms.Compose([\n    transforms.Resize((224, 224)),\n    transforms.RandomHorizontalFlip(p=0.5), # Essential for faces\n    transforms.RandomRotation(15),\n    transforms.ColorJitter(brightness=0.2, contrast=0.2),\n    transforms.ToTensor(),\n    transforms.Normalize(*imagenet_stats)\n])\n\nval_transforms = transforms.Compose([\n    transforms.Resize((224, 224)),\n    transforms.ToTensor(),\n    transforms.Normalize(*imagenet_stats)\n])\n\n# Load Data\nfull_df = pd.read_csv(TRAIN_CSV_PATH)\n\n# Split 80/20 for local validation\ntrain_df, val_df = train_test_split(full_df, test_size=0.2, random_state=42, stratify=full_df['label'])\n\ntrain_dataset = AnimeDataset(train_df, TRAIN_IMG_DIR, transform=train_transforms)\nval_dataset = AnimeDataset(val_df, TRAIN_IMG_DIR, transform=val_transforms)\n\ntrain_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)\nval_loader = DataLoader(val_dataset, batch_size=BATCH_SIZE, shuffle=False, num_workers=2)\n\n# --- 5. MODEL SETUP (Transfer Learning) ---\nmodel = models.resnet18(pretrained=True)\n\n# Replace the last layer for Binary Classification\nnum_ftrs = model.fc.in_features\nmodel.fc = nn.Linear(num_ftrs, 1)\nmodel = model.to(DEVICE)\n\ncriterion = nn.BCEWithLogitsLoss()\noptimizer = optim.Adam(model.parameters(), lr=LEARNING_RATE)\n\n# --- 6. TRAINING LOOP ---\nprint(\"Starting Training...\")\n\nfor epoch in range(EPOCHS):\n    model.train()\n    running_loss = 0.0\n    \n    # Training Phase\n    for images, labels in tqdm(train_loader, desc=f\"Epoch {epoch+1}/{EPOCHS}\"):\n        images, labels = images.to(DEVICE), labels.to(DEVICE).unsqueeze(1)\n        \n        optimizer.zero_grad()\n        outputs = model(images)\n        loss = criterion(outputs, labels)\n        loss.backward()\n        optimizer.step()\n        \n        running_loss += loss.item()\n    \n    # Validation Phase\n    model.eval()\n    correct = 0\n    total = 0\n    with torch.no_grad():\n        for images, labels in val_loader:\n            images, labels = images.to(DEVICE), labels.to(DEVICE).unsqueeze(1)\n            outputs = model(images)\n            # Apply Sigmoid to convert logits to probabilities\n            probs = torch.sigmoid(outputs)\n            predicted = (probs > 0.5).float()\n            \n            total += labels.size(0)\n            correct += (predicted == labels).sum().item()\n            \n    epoch_loss = running_loss / len(train_loader)\n    val_acc = correct / total\n    print(f\"Epoch {epoch+1} | Loss: {epoch_loss:.4f} | Val Acc: {val_acc:.4f}\")\n\n# --- 7. INFERENCE & SUBMISSION ---\nprint(\"Generating predictions on Test Set...\")\n\ntest_df = pd.read_csv(TEST_CSV_PATH)\ntest_dataset = AnimeDataset(test_df, TEST_IMG_DIR, transform=val_transforms, is_test=True)\ntest_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=False, num_workers=2)\n\nmodel.eval()\npredictions = []\nimage_ids = []\n\nwith torch.no_grad():\n    for images, ids in tqdm(test_loader, desc=\"Inference\"):\n        images = images.to(DEVICE)\n        outputs = model(images)\n        \n        # Convert logits -> probability -> binary label (0 or 1)\n        preds = (torch.sigmoid(outputs) > 0.5).long().cpu().numpy().flatten()\n        \n        predictions.extend(preds)\n        image_ids.extend(ids)\n\n# Create submission file\nsubmission_df = pd.DataFrame({'id': image_ids, 'label': predictions})\nsubmission_df.to_csv(\"submission.csv\", index=False)\n\nprint(f\"✅ Saved {len(submission_df)} predictions to submission.csv\")\nprint(\"You can now submit this file to the leaderboard!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-20T12:18:33.199366Z","iopub.execute_input":"2026-01-20T12:18:33.199710Z","iopub.status.idle":"2026-01-20T12:52:20.394133Z","shell.execute_reply.started":"2026-01-20T12:18:33.199688Z","shell.execute_reply":"2026-01-20T12:52:20.392417Z"}},"outputs":[],"execution_count":null}]}