{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.12.12"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"competition","sourceId":25563,"databundleVersionId":2094376},{"sourceType":"datasetVersion","sourceId":15616925,"datasetId":9994860,"databundleVersionId":16551011},{"sourceType":"datasetVersion","sourceId":15621425,"datasetId":9998029,"databundleVersionId":16555739}],"dockerImageVersionId":31329,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Assignment: Kaggle Competition — Plant Pathology 2021\n\n**Competition:** [Plant Pathology 2021 - FGVC8](https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8)  \n**Task:** Classify diseases in apple leaf images (multi-label classification)  \n**Metric:** Mean F1-Score (higher = better)\n\n---\n\n## Before you start — complete these steps in order\n\n**Step 1 — Create a Kaggle account** (free): [https://www.kaggle.com](https://www.kaggle.com)\n\n**Step 2 — Accept the competition rules:**  \nGo to → [https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8/rules](https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8/rules)  \nScroll to the bottom → click **\"I Understand and Accept\"**  \n⚠️ You cannot access the data or submit without accepting first.\n\n**Step 3 — Open the competition notebook:**  \nGo to the competition page → click **\"Code\"** tab → click **\"New Notebook\"**. Then, Click **\"File\"** and **\"Import\"** this notebook.\nThe dataset attaches automatically. No download needed.\n\n---\n\n## ⚠️ Important: This competition requires Internet OFF\n\nKaggle re-runs your notebook on a hidden test set to generate your score.  \nThis competition **does not allow internet access** during that re-run.\n\n**What this means for you:**\n- The notebook must run completely **without downloading anything from the internet**\n- `weights=\"imagenet\"` will **fail** because it tries to download the weights\n- You must upload the model weights as a Kaggle Dataset and load them offline\n\n---\n\n## How to upload offline model weights (do this once)\n\n**Part A — Get the weights file**\n\nOption 1 — Download directly (paste this URL in your browser):\n```\nhttps://storage.googleapis.com/tensorflow/keras-applications/efficientnet_v2/efficientnetv2-b0_notop.h5\n```\nThis downloads a file called `efficientnetv2-b0_notop.h5` (~29 MB).\n\nOption 2 — Run this on your local machine or in a Kaggle notebook with internet ON:\n```python\nimport tensorflow as tf\nm = tf.keras.applications.EfficientNetV2B0(include_top=False, weights=\"imagenet\")\nm.save_weights(\"efficientnetv2b0_notop.h5\")\n```\n\n**Part B — Upload as a Kaggle Dataset**\n1. Click **\"Upload\"** → select your `.h5` file\n2. Give it a name, e.g. `efficientnetv2b0`\n3. Click **\"Create\"** → wait for upload to finish\n\n---\n\n## How to submit\n\nThis competition uses **Notebook submission** — you do NOT upload a CSV file manually.\n\n1. Make sure **Internet is OFF** in Settings (right panel → Settings → Internet → OFF)\n2. Click **\"Save & Run All (Commit)\"** — top right button\n3. Wait for the notebook to finish running (~15–25 min with GPU)\n4. Once done → click **\"Submit to Competition\"** button that appears (at the bottom of right panel)\n5. Kaggle re-runs your notebook privately and extracts `submission.csv` from the output\n\n---\n\n## What to submit on Canvas\n\n1. Your Kaggle notebook **public URL** (Settings → Sharing → Public)\n2. **Screenshot** of the leaderboard showing your username and score\n3. Your **public Mean F1 score**","metadata":{}},{"cell_type":"markdown","source":"## Step 1: Imports","metadata":{}},{"cell_type":"code","source":"import os\nos.environ[\"TF_CPP_MIN_LOG_LEVEL\"] = \"2\"\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom sklearn.preprocessing import MultiLabelBinarizer\nfrom sklearn.model_selection import train_test_split\n\ntf.get_logger().setLevel('ERROR')\n\nprint(\"TensorFlow:\", tf.__version__)\nprint(\"GPU available:\", len(tf.config.list_physical_devices('GPU')) > 0)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T03:58:34.493357Z","iopub.execute_input":"2026-04-14T03:58:34.494437Z","iopub.status.idle":"2026-04-14T03:58:34.500557Z","shell.execute_reply.started":"2026-04-14T03:58:34.494396Z","shell.execute_reply":"2026-04-14T03:58:34.499578Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 2: Set Paths","metadata":{}},{"cell_type":"code","source":"# Competition data\nBASE_DIR   = \"/kaggle/input/competitions/plant-pathology-2021-fgvc8\"\nTRAIN_DIR  = os.path.join(BASE_DIR, \"train_images\")\nTEST_DIR   = os.path.join(BASE_DIR, \"test_images\")\n\n# Offline weights — uploaded as a Kaggle Dataset (see setup instructions above)\n# Change the filename below if yours is named differently\n# 如果你的文件名不同，请将下面的文件名更改为你的文件名\nWEIGHTS_PATH = \"/kaggle/input/efficientnetv2b0-weights/efficientnetv2b0_notop.h5\"\n\nprint(\"Train images:\", TRAIN_DIR)\nprint(\"Test  images:\", TEST_DIR)\nprint(\"Weights file exists:\", os.path.exists(WEIGHTS_PATH))\nprint(\"Sample train files:\", os.listdir(TRAIN_DIR)[:3])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T03:58:44.915474Z","iopub.execute_input":"2026-04-14T03:58:44.916318Z","iopub.status.idle":"2026-04-14T03:58:45.251375Z","shell.execute_reply.started":"2026-04-14T03:58:44.916286Z","shell.execute_reply":"2026-04-14T03:58:45.250563Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 3: Load and Explore the Data\n\nThis is a **multi-label** problem — one leaf can have multiple diseases at the same time.  \nLabels are stored as space-separated strings, e.g. `\"scab frog_eye_leaf_spot\"`.","metadata":{}},{"cell_type":"code","source":"train_df  = pd.read_csv(os.path.join(BASE_DIR, \"train.csv\"))\nsample_df = pd.read_csv(os.path.join(BASE_DIR, \"sample_submission.csv\"))\n\nprint(\"Train shape:\", train_df.shape)\nprint(train_df.head())\n\nALL_LABELS  = ['complex', 'frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\nNUM_CLASSES = len(ALL_LABELS)\nprint(\"\\nClasses:\", ALL_LABELS)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T03:58:56.829694Z","iopub.execute_input":"2026-04-14T03:58:56.830388Z","iopub.status.idle":"2026-04-14T03:58:56.877055Z","shell.execute_reply.started":"2026-04-14T03:58:56.830247Z","shell.execute_reply":"2026-04-14T03:58:56.876474Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Show label distribution\nlabel_counts = train_df['labels'].value_counts().head(10)\n\nplt.figure(figsize=(10, 4))\nlabel_counts.plot(kind='bar')\nplt.title(\"Top 10 Label Combinations\")\nplt.xticks(rotation=30, ha='right')\nplt.tight_layout()\nplt.show()\n\nprint(\"\\nUnique label combinations:\", train_df['labels'].nunique())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T03:59:10.065588Z","iopub.execute_input":"2026-04-14T03:59:10.066128Z","iopub.status.idle":"2026-04-14T03:59:10.334406Z","shell.execute_reply.started":"2026-04-14T03:59:10.066100Z","shell.execute_reply":"2026-04-14T03:59:10.333623Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 4: Show Sample Images","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(16, 4))\nfor i in range(8):\n    row   = train_df.iloc[i]\n    path  = os.path.join(TRAIN_DIR, row['image'])\n    image = tf.keras.utils.load_img(path, target_size=(128, 128))\n    image = tf.keras.utils.img_to_array(image).astype(\"uint8\")\n    plt.subplot(1, 8, i + 1)\n    plt.imshow(image)\n    plt.title(row['labels'], fontsize=6)\n    plt.axis(\"off\")\nplt.suptitle(\"Sample Training Images\", fontsize=13)\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T03:59:20.008222Z","iopub.execute_input":"2026-04-14T03:59:20.008717Z","iopub.status.idle":"2026-04-14T03:59:21.251327Z","shell.execute_reply.started":"2026-04-14T03:59:20.008688Z","shell.execute_reply":"2026-04-14T03:59:21.250578Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 5: Encode Labels\n\nWe convert space-separated label strings into **binary vectors** of length 6.  \nExample: `\"scab frog_eye_leaf_spot\"` → `[0, 1, 0, 0, 0, 1]`  \nThis is called **multi-hot encoding** — multiple positions can be 1 at the same time.","metadata":{}},{"cell_type":"code","source":"train_df['label_list'] = train_df['labels'].apply(lambda x: x.split())\n\nmlb   = MultiLabelBinarizer(classes=ALL_LABELS)\ny_all = mlb.fit_transform(train_df['label_list']).astype('float32')\n\nprint(\"Label matrix shape:\", y_all.shape)   # (18632, 6)\nprint(\"Classes:\", mlb.classes_)\nprint(\"\\nExample — label:\", train_df['labels'].iloc[0], \"→ encoded:\", y_all[0])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T03:59:31.742720Z","iopub.execute_input":"2026-04-14T03:59:31.743149Z","iopub.status.idle":"2026-04-14T03:59:31.977449Z","shell.execute_reply.started":"2026-04-14T03:59:31.743122Z","shell.execute_reply":"2026-04-14T03:59:31.976722Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 6: Build the tf.data Pipeline","metadata":{}},{"cell_type":"code","source":"IMG_SIZE   = 224\nBATCH_SIZE = 32\nAUTOTUNE   = tf.data.AUTOTUNE\n\nX_train, X_val, y_train, y_val = train_test_split(\n    train_df['image'].values, y_all,\n    test_size=0.2, random_state=42\n)\nprint(f\"Train: {len(X_train)} | Val: {len(X_val)}\")\n\n\ndef load_image(path, label):\n    full_path = tf.strings.join([TRAIN_DIR + \"/\", path])\n    image = tf.io.read_file(full_path)\n    image = tf.image.decode_jpeg(image, channels=3)\n    image = tf.image.resize(image, (IMG_SIZE, IMG_SIZE))\n    image = tf.cast(image, tf.float32) / 255.0\n    return image, label\n\ndef load_test_image(path):\n    full_path = tf.strings.join([TEST_DIR + \"/\", path])\n    image = tf.io.read_file(full_path)\n    image = tf.image.decode_jpeg(image, channels=3)\n    image = tf.image.resize(image, (IMG_SIZE, IMG_SIZE))\n    image = tf.cast(image, tf.float32) / 255.0\n    return image\n\n\ntrain_ds = (\n    tf.data.Dataset.from_tensor_slices((X_train, y_train))\n    .shuffle(2000)\n    .map(load_image, num_parallel_calls=AUTOTUNE)\n    .batch(BATCH_SIZE)\n    .prefetch(AUTOTUNE)\n)\n\nval_ds = (\n    tf.data.Dataset.from_tensor_slices((X_val, y_val))\n    .map(load_image, num_parallel_calls=AUTOTUNE)\n    .batch(BATCH_SIZE)\n    .prefetch(AUTOTUNE)\n)\n\ntest_paths = sample_df['image'].values\ntest_ds = (\n    tf.data.Dataset.from_tensor_slices(test_paths)\n    .map(load_test_image, num_parallel_calls=AUTOTUNE)\n    .batch(BATCH_SIZE)\n    .prefetch(AUTOTUNE)\n)\n\nprint(\"Pipelines ready!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:00:21.216187Z","iopub.execute_input":"2026-04-14T04:00:21.216898Z","iopub.status.idle":"2026-04-14T04:00:21.278001Z","shell.execute_reply.started":"2026-04-14T04:00:21.216870Z","shell.execute_reply":"2026-04-14T04:00:21.277448Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 7: Define Augmentation Blocks\n\nCombined geometric + color augmentation from Lectures 11a and 11b.","metadata":{}},{"cell_type":"code","source":"# Geometric augmentation\ngeometric_augmentation = tf.keras.Sequential([\n    tf.keras.layers.RandomFlip(\"horizontal\"),\n    tf.keras.layers.RandomRotation(factor=0.05),\n    tf.keras.layers.RandomZoom(height_factor=(-0.1, 0.1), width_factor=(-0.1, 0.1)),\n    tf.keras.layers.RandomTranslation(height_factor=0.1, width_factor=0.1),\n], name=\"geometric_augmentation\")\n\n\n# Color augmentation custom layers\nclass RandomBrightnessLayer(tf.keras.layers.Layer):\n    def __init__(self, max_delta=0.2, **kwargs):\n        super().__init__(**kwargs)\n        self.max_delta = max_delta\n    def call(self, x, training=False):\n        if training:\n            x = tf.image.random_brightness(x, self.max_delta)\n            x = tf.clip_by_value(x, 0.0, 1.0)\n        return x\n\nclass RandomContrastLayer(tf.keras.layers.Layer):\n    def __init__(self, lower=0.7, upper=1.3, **kwargs):\n        super().__init__(**kwargs)\n        self.lower, self.upper = lower, upper\n    def call(self, x, training=False):\n        if training:\n            x = tf.image.random_contrast(x, self.lower, self.upper)\n            x = tf.clip_by_value(x, 0.0, 1.0)\n        return x\n\nclass RandomSaturationLayer(tf.keras.layers.Layer):\n    def __init__(self, lower=0.6, upper=1.4, **kwargs):\n        super().__init__(**kwargs)\n        self.lower, self.upper = lower, upper\n    def call(self, x, training=False):\n        if training:\n            x = tf.image.random_saturation(x, self.lower, self.upper)\n            x = tf.clip_by_value(x, 0.0, 1.0)\n        return x\n\nclass RandomHueLayer(tf.keras.layers.Layer):\n    def __init__(self, max_delta=0.1, **kwargs):\n        super().__init__(**kwargs)\n        self.max_delta = max_delta\n    def call(self, x, training=False):\n        if training:\n            x = tf.image.random_hue(x, self.max_delta)\n            x = tf.clip_by_value(x, 0.0, 1.0)\n        return x\n\ncolor_augmentation = tf.keras.Sequential([\n    RandomBrightnessLayer(max_delta=0.2),\n    RandomContrastLayer(lower=0.7, upper=1.3),\n    RandomSaturationLayer(lower=0.6, upper=1.4),\n    RandomHueLayer(max_delta=0.1),\n], name=\"color_augmentation\")\n\nprint(\"Augmentation blocks ready!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:00:28.318874Z","iopub.execute_input":"2026-04-14T04:00:28.319137Z","iopub.status.idle":"2026-04-14T04:00:28.351472Z","shell.execute_reply.started":"2026-04-14T04:00:28.319116Z","shell.execute_reply":"2026-04-14T04:00:28.350848Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 8: Build the Model\n\n**Key difference from previous notebooks:**  \nThis is **multi-label** classification:\n- Output activation: `sigmoid` — each of the 6 classes is predicted independently  \n- Loss: `binary_crossentropy` — loss is computed separately per class  \n\n**Offline weights:**  \nWe use `weights=None` and load the `.h5` file manually.  \nThis is required because **internet is OFF** in this competition.","metadata":{}},{"cell_type":"code","source":"inputs = tf.keras.Input(shape=(IMG_SIZE, IMG_SIZE, 3), name=\"input_image\")\n\n# 1) Geometric augmentation\nx = geometric_augmentation(inputs)\n\n# 2) Color augmentation (expects [0,1])\nx = color_augmentation(x)\n\n# 3) Scale back to [0,255] for EfficientNet preprocessing\nx = x * 255.0\nx = tf.keras.applications.efficientnet_v2.preprocess_input(x)\n\n# 4) Backbone — weights=None because internet is OFF\n#    We load the weights manually from our uploaded dataset file\nbase_model = tf.keras.applications.EfficientNetV2B0(\n    include_top=False,\n    weights=None          # do NOT download — we load from file below\n)\nbase_model.load_weights(\"/kaggle/input/datasets/tct666/efficientnetv2b0-notop-h5/efficientnetv2-b0_notop.h5\",\n                        by_name=True, skip_mismatch=True)\nprint(\"Weights loaded from:\", WEIGHTS_PATH)\n\nbase_model.trainable = False   # freeze backbone for first training phase\nx = base_model(x, training=False)\n\n# 5) Classification head — sigmoid for multi-label\nx = tf.keras.layers.GlobalAveragePooling2D()(x)\nx = tf.keras.layers.Dropout(0.3)(x)\noutputs = tf.keras.layers.Dense(\n    NUM_CLASSES, activation=\"sigmoid\", name=\"predictions\"\n)(x)\n\nmodel = tf.keras.Model(inputs, outputs, name=\"plant_pathology_model\")\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:01:12.967467Z","iopub.execute_input":"2026-04-14T04:01:12.968117Z","iopub.status.idle":"2026-04-14T04:01:16.081069Z","shell.execute_reply.started":"2026-04-14T04:01:12.968086Z","shell.execute_reply":"2026-04-14T04:01:16.080494Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 9: Compile and Train (Frozen Backbone)","metadata":{}},{"cell_type":"code","source":"model.compile(\n    optimizer=tf.keras.optimizers.Adam(learning_rate=1e-3),\n    loss=\"binary_crossentropy\",\n    metrics=[\"accuracy\"]\n)\n\nprint(\"Training frozen backbone (5 epochs)...\")\nhistory = model.fit(\n    train_ds,\n    validation_data=val_ds,\n    epochs=5\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:01:37.890336Z","iopub.execute_input":"2026-04-14T04:01:37.891126Z","iopub.status.idle":"2026-04-14T04:25:16.886505Z","shell.execute_reply.started":"2026-04-14T04:01:37.891095Z","shell.execute_reply":"2026-04-14T04:25:16.885842Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 10: Fine-Tune the Backbone (improves score)\n\nUnfreeze the backbone and retrain with a smaller learning rate.  \nThis usually gives a significant improvement in F1 score.","metadata":{}},{"cell_type":"code","source":"base_model.trainable = True\n\nmodel.compile(\n    optimizer=tf.keras.optimizers.Adam(learning_rate=1e-4),  # lower LR for fine-tuning\n    loss=\"binary_crossentropy\",\n    metrics=[\"accuracy\"]\n)\n\nprint(\"Fine-tuning full model (5 epochs)...\")\nprint(\"微调完整模型（5 个周期）...\")\nhistory_ft = model.fit(\n    train_ds,\n    validation_data=val_ds,\n    epochs=5\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:25:30.830958Z","iopub.execute_input":"2026-04-14T04:25:30.831635Z","iopub.status.idle":"2026-04-14T04:51:30.100569Z","shell.execute_reply.started":"2026-04-14T04:25:30.831605Z","shell.execute_reply":"2026-04-14T04:51:30.099926Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 11: Make Predictions on Test Set\n\n**Threshold = 0.5** — if probability > 0.5 we predict that class.  \nIf no class passes the threshold, we pick the highest probability class.","metadata":{}},{"cell_type":"code","source":"# 在验证集上寻找最佳阈值\nfrom sklearn.metrics import f1_score\n\n# 获取验证集预测概率\nval_preds = model.predict(val_ds, verbose=1)\n\n# 尝试不同的阈值\nbest_threshold = 0.5\nbest_score = 0.0\n\nfor thresh in np.arange(0.3, 0.7, 0.05):\n    pred_labels = (val_preds >= thresh).astype(int)\n    score = f1_score(y_val, pred_labels, average='micro')\n    if score > best_score:\n        best_score = score\n        best_threshold = thresh\n\nprint(f\"最佳阈值: {best_threshold:.2f}, 验证集 F1: {best_score:.4f}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:54:20.968106Z","iopub.execute_input":"2026-04-14T04:54:20.968822Z","iopub.status.idle":"2026-04-14T04:55:17.423035Z","shell.execute_reply.started":"2026-04-14T04:54:20.968789Z","shell.execute_reply":"2026-04-14T04:55:17.422434Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"preds = model.predict(test_ds, verbose=1)   # shape: (N, 6)\n\nTHRESHOLD = 0.4\n\ndef probs_to_label(prob_row, threshold=THRESHOLD):\n    selected = [ALL_LABELS[i] for i, p in enumerate(prob_row) if p >= threshold]\n    if len(selected) == 0:\n        selected = [ALL_LABELS[np.argmax(prob_row)]]\n    return \" \".join(selected)\n\npredicted_labels = [probs_to_label(row) for row in preds]\n\nprint(\"Sample predictions:\")\nfor i in range(3):\n    print(f\"  {test_paths[i]}  →  {predicted_labels[i]}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:56:00.187800Z","iopub.execute_input":"2026-04-14T04:56:00.188071Z","iopub.status.idle":"2026-04-14T04:56:02.894922Z","shell.execute_reply.started":"2026-04-14T04:56:00.188049Z","shell.execute_reply":"2026-04-14T04:56:02.894334Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 12: Save submission.csv","metadata":{}},{"cell_type":"code","source":"submission = pd.DataFrame({\n    'image':  test_paths,\n    'labels': predicted_labels\n})\n\nsubmission.to_csv('submission.csv', index=False)\n\nprint(\"submission.csv saved!\")\nprint(submission.head())\nprint(\"Shape:\", submission.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-14T04:56:07.330693Z","iopub.execute_input":"2026-04-14T04:56:07.331342Z","iopub.status.idle":"2026-04-14T04:56:07.343863Z","shell.execute_reply.started":"2026-04-14T04:56:07.331313Z","shell.execute_reply":"2026-04-14T04:56:07.342930Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Step 13: Submit to Kaggle\n\nThis competition uses **Notebook submission** — you do NOT upload the CSV file manually.\n\n### How to submit\n\n1. Make sure **Internet is OFF**  \n   → Right panel → **Settings** → **Internet** → toggle OFF\n\n2. Click **\"Save & Run All (Commit)\"** — top right button  \n   → This runs the full notebook from top to bottom  \n   → Wait ~15–25 minutes for it to finish\n\n3. Once the commit is done → click **\"Submit to Competition\"**  \n   → Kaggle re-runs your notebook privately on the hidden test set  \n   → It reads `submission.csv` from the output and scores it\n\n4. Check your score at the leaderboard:  \n   [https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8/leaderboard](https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8/leaderboard)\n\n---\n\n### Checklist before committing\n\n| Item | Check |\n|---|---|\n| Internet toggle is OFF | ☐ |\n| Weights dataset is attached | ☐ |\n| `weights=None` in model code | ☐ |\n| `load_weights(WEIGHTS_PATH)` is in model code | ☐ |\n| `submission.csv` is saved in the last cell | ☐ |\n| All cells run without errors | ☐ |","metadata":{}},{"cell_type":"markdown","source":"## Step 14: Share on Canvas\n\n**Make your notebook public:**  \nIn your Kaggle notebook → **Settings** → **Sharing** → set to **Public**\n\n**Submit on Canvas:**\n1. Your Kaggle notebook public URL\n2. Screenshot of the leaderboard showing your username and score\n3. Your public Mean F1 score\n\n---\n\n## How to improve your score\n\n| Idea | Expected gain |\n|---|---|\n| Fine-tune the backbone (Step 10) | +5–10% |\n| Use a larger model (EfficientNetV2B2 or B3) | +3–5% |\n| Tune the threshold (try 0.3, 0.4, 0.5) | +1–3% |\n| Train more epochs | +2–5% |\n| Add stronger augmentation | +1–3% |\n\nBaseline score with this notebook: **~0.75–0.82 Mean F1**","metadata":{}}]}