{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":31012,"isInternetEnabled":true,"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 os\nimport zipfile\nimport shutil\nimport random\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.applications import VGG16, VGG19\nfrom tensorflow.keras import layers, models\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.preprocessing import image\n\n# Step 1: Unzip dataset\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\", 'r') as zip_ref:\n    zip_ref.extractall(\"/kaggle/working/train_data\")\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\", 'r') as zip_ref:\n    zip_ref.extractall(\"/kaggle/working/test_data\")\n\n# Step 2: Prepare directories\nbase_dir = '/kaggle/working/cats_vs_dogs_small'\ntrain_dir = os.path.join(base_dir, 'train')\nvalidation_dir = os.path.join(base_dir, 'validation')\n\nfor category in ['Cat', 'Dog']:\n    os.makedirs(os.path.join(train_dir, category), exist_ok=True)\n    os.makedirs(os.path.join(validation_dir, category), exist_ok=True)\n\n# Step 3: Split into train and val\ntrain_data_path = \"/kaggle/working/train_data/train\"\nall_images = os.listdir(train_data_path)\nrandom.shuffle(all_images)\n\nsplit_index = int(0.8 * len(all_images))\ntrain_images = all_images[:split_index]\nval_images = all_images[split_index:]\n\nfor fname in train_images:\n    label = 'Dog' if 'dog' in fname else 'Cat'\n    shutil.copy(os.path.join(train_data_path, fname),\n                os.path.join(train_dir, label, fname))\n\nfor fname in val_images:\n    label = 'Dog' if 'dog' in fname else 'Cat'\n    shutil.copy(os.path.join(train_data_path, fname),\n                os.path.join(validation_dir, label, fname))\n\n# Step 4: Data generators\nIMAGE_SIZE = (150, 150)\nBATCH_SIZE = 32\n\ntrain_datagen = ImageDataGenerator(rescale=1./255, rotation_range=20, zoom_range=0.2, horizontal_flip=True)\nval_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_gen = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary'\n)\n\nval_gen = val_datagen.flow_from_directory(\n    validation_dir,\n    target_size=IMAGE_SIZE,\n    batch_size=BATCH_SIZE,\n    class_mode='binary'\n)\n\n# Step 5: VGG16 Model\ndef build_model(base_model):\n    base_model.trainable = False\n    model = models.Sequential([\n        base_model,\n        layers.Flatten(),\n        layers.Dense(256, activation='relu'),\n        layers.Dropout(0.5),\n        layers.Dense(1, activation='sigmoid')\n    ])\n    return model\n\nvgg16_base = VGG16(weights='imagenet', include_top=False, input_shape=(150, 150, 3))\nvgg16_model = build_model(vgg16_base)\n\nvgg16_model.compile(optimizer=Adam(learning_rate=0.0001),\n                    loss='binary_crossentropy',\n                    metrics=['accuracy'])\n\nprint(\"\\n🔧 Training VGG16...\")\nvgg16_model.fit(train_gen, validation_data=val_gen, epochs=3)\n\n# Step 6: VGG19 Model\nvgg19_base = VGG19(weights='imagenet', include_top=False, input_shape=(150, 150, 3))\nvgg19_model = build_model(vgg19_base)\n\nvgg19_model.compile(optimizer=Adam(learning_rate=0.0001),\n                    loss='binary_crossentropy',\n                    metrics=['accuracy'])\n\nprint(\"\\n🔧 Training VGG19...\")\nvgg19_model.fit(train_gen, validation_data=val_gen, epochs=3)\n\n# Step 7: Prediction on test images\ntest_dir = \"/kaggle/working/test_data/test1\"\ntest_images = [os.path.join(test_dir, fname) for fname in os.listdir(test_dir)[:10]]\n\ndef predict_images(model, image_paths, name=\"Model\"):\n    print(f\"\\n🔍 Predictions by {name}:\")\n    class_names = ['Cat', 'Dog']\n    for img_path in image_paths:\n        img = image.load_img(img_path, target_size=IMAGE_SIZE)\n        img_array = image.img_to_array(img) / 255.0\n        img_array = np.expand_dims(img_array, axis=0)\n\n        prediction = model.predict(img_array)[0][0]\n        label = class_names[int(prediction > 0.5)]\n        print(f\"{os.path.basename(img_path)} -> Predicted: {label} (Score: {prediction:.4f})\")\n\npredict_images(vgg16_model, test_images, \"VGG16\")\npredict_images(vgg19_model, test_images, \"VGG19\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}