{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Data Processing and EDA","metadata":{}},{"cell_type":"markdown","source":"First unzipping files","metadata":{}},{"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)\nimport zipfile\nimport matplotlib.pyplot as plt\nimport cv2\nimport random\nimport pickle\nfrom tqdm import tqdm\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_count":null,"outputs":[]},{"cell_type":"code","source":"zip_ref = zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip', 'r')\nzip_ref.extractall()\nzip_ref.close()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"zip_ref = zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', 'r')\nzip_ref.extractall()\nzip_ref.close()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Visualizing 6 images","metadata":{}},{"cell_type":"code","source":"PATH = '/kaggle/working/train'\nfilename = os.listdir(PATH)\nIMG_SIZE = 100\n\nplt.figure(figsize=(10, 10))\nfor i in range(6):  # showing 6 images\n    img_array = cv2.imread(os.path.join(PATH, filename[i]))\n    resize_image = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))\n    plt.subplot(3, 3, i + 1)  # Increment i by 1 for subplot numbering\n    image = cv2.cvtColor(resize_image, cv2.COLOR_BGR2RGB)\n    plt.axis('off')\n    plt.imshow(image)\n\nplt.tight_layout()\nplt.show() ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport cv2\nfrom tqdm import tqdm  # Import tqdm for the progress bar\n\ntraining_data = []\nIMG_SIZE = 100\npath = '/kaggle/working/train'\nfilenames = os.listdir('/kaggle/working/train')\n\nfor img in tqdm(filenames):\n    try:\n        if 'cat' in img:\n            category = 1  # Cat category\n        else:\n            category = 0  # Dog category\n        \n        img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)\n        new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))\n        training_data.append([new_array, category])\n    except Exception as e:\n        pass\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# visualize training data\nplt.figure(figsize=(10,10))\nfor i in range(1, 7):\n    plt.subplot(3,3,i)\n    plt.axis('off')\n    if training_data[10+i][1] == 0:\n        plt.title('Dog')\n    else:\n        plt.title('Cat')\n    plt.imshow(training_data[10+i][0], cmap='gray_r')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"testing_data = []\nIMG_SIZE = 100\npath = '/kaggle/working/test'\nfilenames = os.listdir('/kaggle/working/test')\n\nfor img in tqdm(filenames):\n    try:\n        img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)\n        new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))\n        testing_data.append([new_array])\n    except Exception as e:\n        pass\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(training_data)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = []\ny = []\n\nfor features, label  in training_data:\n    X.append(features)\n    y.append(label)\n    \nX = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pickle\n\n# Saving X and y using pickle\nwith open(\"X.pickle\", \"wb\") as pickle_out:\n    pickle.dump(X, pickle_out)\n\nwith open(\"y.pickle\", \"wb\") as pickle_out:\n    pickle.dump(y, pickle_out)\n\n# Loading X and y using pickle\nwith open(\"X.pickle\", \"rb\") as pickle_in:\n    X = pickle.load(pickle_in)\n\nwith open(\"y.pickle\", \"rb\") as pickle_in:\n    y = pickle.load(pickle_in)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = X/255.0\n\nX = np.array(X)\ny = np.array(y)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(len(X))\nprint(len(y))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nX_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=50)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# CNN Models","metadata":{}},{"cell_type":"markdown","source":"## Model 1","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Activation\n\nmodel = Sequential()\n\nmodel.add(Conv2D(256, (3, 3), input_shape=X_train.shape[1:]))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(256, (3, 3)))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Flatten())  # This converts our 3D feature maps to 1D feature vectors\n\nmodel.add(Dense(64, activation='relu'))\nmodel.add(Dense(1, activation='sigmoid'))  # Binary classification output\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'],)\n\nhistory = model.fit(X_train, y_train, batch_size=32, epochs=15, validation_data = (x_test, y_test))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"score = model.evaluate(x_test, y_test, verbose=0)\nprint('Test Loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Plotting our loss charts\n# Use the history object we created to get our saved performance results.\nhistory_dict = history.history\n\n# Extract the loss and validation losses\nloss_values = history_dict['loss']\nval_loss_values = history_dict['val_loss']\n\nepochs = range(1, len(loss_values) + 1)\n\nline1 = plt.plot(epochs, val_loss_values, label='Validation/Test Loss')\nline2 = plt.plot(epochs, loss_values, label='Training Loss')\nplt.setp(line1, linewidth=2.0, marker='+', markersize=10.0)\nplt.setp(line2, linewidth=2.0, marker='4', markersize=10.0)\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.title('Training and Validation Loss')\nplt.legend()\nplt.grid(True)\nplt.show()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nhistory_dict = history.history\n\nacc_values = history_dict['accuracy']\nval_acc_values = history_dict['val_accuracy']\nepochs = range(1, len(acc_values) + 1)\n\nline1 = plt.plot(epochs, val_acc_values, label='Validation/Test Accuracy')\nline2 = plt.plot(epochs, acc_values, label='Training Accuracy')\n\nplt.setp(line1, linewidth=2.0, marker='+', markersize=10.0)\nplt.setp(line2, linewidth=2.0, marker\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMG_SIZE = 100\ntest = []\n\nfor features  in testing_data:\n    test.append(features)\n    \ntest = np.array(test).reshape(-1, IMG_SIZE, IMG_SIZE, 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = test/255.0\n\ntest = np.array(test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction = model.predict(test) ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"my_submission = pd.read_csv('/kaggle/input/dogs-vs-cats-redux-kernels-edition/sample_submission.csv')\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"my_submission['label'] = prediction\nmy_submission['label'] = my_submission['label'].map(lambda x: 1 if x >= 0.5 else 0 )\nmy_submission['label'] = my_submission['label'].round(1)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"my_submission.to_csv('my_submission.csv', index=False)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Model 2","metadata":{}},{"cell_type":"code","source":"from keras import layers\nfrom tensorflow.keras.optimizers import RMSprop\n\nmodel2 = Sequential()\nmodel2.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(100, 100, 1)))\nmodel2.add(layers.MaxPooling2D(2, 2))\nmodel2.add(layers.Conv2D(64, (3,3), activation='relu'))\nmodel2.add(layers.MaxPooling2D(2,2))\nmodel2.add(layers.Conv2D(128, (3,3), activation='relu'))\nmodel2.add(layers.MaxPooling2D(2,2))\n\nmodel2.add(layers.Flatten())\nmodel2.add(layers.Dense(512, activation='relu'))\nmodel2.add(layers.Dense(1, activation='sigmoid'))\n\nmodel2.compile(loss='binary_crossentropy',\n            optimizer=RMSprop(learning_rate=1e-4),\n            metrics=['accuracy'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model2.fit(X_train, y_train, batch_size=32, epochs=15, validation_data = (x_test, y_test))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"score = model2.evaluate(x_test, y_test, verbose=0)\nprint('Test Loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Plotting our loss charts\n# Use the history object we created to get our saved performance results.\nhistory_dict = history.history\n\n# Extract the loss and validation losses\nloss_values = history_dict['loss']\nval_loss_values = history_dict['val_loss']\n\nepochs = range(1, len(loss_values) + 1)\n\nline1 = plt.plot(epochs, val_loss_values, label='Validation/Test Loss')\nline2 = plt.plot(epochs, loss_values, label='Training Loss')\nplt.setp(line1, linewidth=2.0, marker='+', markersize=10.0)\nplt.setp(line2, linewidth=2.0, marker='4', markersize=10.0)\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.title('Training and Validation Loss')\nplt.legend()\nplt.grid(True)\nplt.show()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nhistory_dict = history.history\n\nacc_values = history_dict['accuracy']\nval_acc_values = history_dict['val_accuracy']\nepochs = range(1, len(acc_values) + 1)\n\nline1 = plt.plot(epochs, val_acc_values, label='Validation/Test Accuracy')\nline2 = plt.plot(epochs, acc_values, label='Training Accuracy')\n\nplt.setp(line1, linewidth=2.0, marker='+', markersize=10.0)\nplt.setp(line2, linewidth=2.0, marker","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMG_SIZE = 100\ntest = []\n\nfor features  in testing_data:\n    test.append(features)\n    \ntest = np.array(test).reshape(-1, IMG_SIZE, IMG_SIZE, 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = test/255.0\n\ntest = np.array(test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction = model2.predict(test) ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"my_submission = pd.read_csv('/kaggle/input/dogs-vs-cats-redux-kernels-edition/sample_submission.csv')\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"my_submission['label'] = prediction\nmy_submission['label'] = my_submission['label'].map(lambda x: 1 if x >= 0.5 else 0 )\nmy_submission['label'] = my_submission['label'].round(1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"my_submission.to_csv('my_submission_2.csv', index=False)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Hyperparam Tuning","metadata":{}},{"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Activation, Flatten, Dense\nfrom tensorflow.keras.optimizers import RMSprop\nfrom kerastuner.tuners import RandomSearch\nfrom kerastuner.engine.hyperparameters import HyperParameters\n\n# Assuming you have your data (X_train, y_train, X_val, y_val) ready\n\ndef build_model(hp):\n    model = Sequential()\n    model.add(Conv2D(hp.Int('conv1_filters', min_value=16, max_value=128, step=16), (3, 3), activation='relu', input_shape=(100, 100, 1)))\n    model.add(MaxPooling2D(2, 2))\n    model.add(Conv2D(hp.Int('conv2_filters', min_value=32, max_value=256, step=32), (3, 3), activation='relu'))\n    model.add(MaxPooling2D(2, 2))\n    model.add(Conv2D(hp.Int('conv3_filters', min_value=64, max_value=512, step=64), (3, 3), activation='relu'))\n    model.add(MaxPooling2D(2, 2))\n    model.add(Flatten())\n    model.add(Dense(512, activation='relu'))\n    model.add(Dense(1, activation='sigmoid'))\n\n    optimizer = RMSprop(learning_rate=hp.Choice('learning_rate', values=[1e-3, 1e-4, 1e-5]))\n    model.compile(optimizer=optimizer, loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n\ntuner = RandomSearch(\n    build_model,\n    objective='val_accuracy',\n    max_trials=10,\n    executions_per_trial=1,\n    directory='hyperparam_tuning',\n    project_name='cnn_tuning'\n)\n\ntuner.search(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=32)\n\n# Get the best model\nbest_model = tuner.get_best_models()[0]\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"best_model.summary()\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_loss, test_accuracy = best_model.evaluate(X_test, y_test)\nprint(f\"Test Loss: {test_loss:.4f}, Test Accuracy: {test_accuracy:.4f}\")\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"best_hp = tuner.get_best_hyperparameters()[0]\nprint(f\"Best Hyperparameters: {best_hp.values}\")\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Model 3","metadata":{}}]}