{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n\nimport os\nimport cv2\nfrom tqdm import tqdm\n\nfrom sklearn.model_selection import train_test_split\n\nimport keras\nfrom keras import layers\nfrom keras.layers import Conv2D, Conv2DTranspose, MaxPooling2D, Dense, Dropout, Flatten\nfrom keras.models import Sequential","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train_dir = '../input/train/'\ntrain_images = []\ntrain_labels = []\n\nfor img in tqdm(os.listdir(train_dir)):\n    try:\n        img_r = cv2.imread(os.path.join(train_dir, img), cv2.IMREAD_GRAYSCALE)\n        train_images.append(np.array(cv2.resize(img_r, (50, 50), interpolation=cv2.INTER_CUBIC)))\n        if 'dog' in img:\n            train_labels.append(1)\n        else:\n            train_labels.append(0)\n    except Exception as e:\n        print('these are damaged images')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Visualising the image\n\nplt.title(train_labels[0])\n_ = plt.imshow(train_images[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(train_images, train_labels, test_size=0.3, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = np.array(x_train)\nx_test = np.array(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Train Shape:\" + str(x_train.shape))\nprint(\"Test Shape:\" + str(x_test.shape))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.title(y_train[0])\n_ = plt.imshow(x_train[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def baseline_model():\n    model = Sequential()\n    \n    model.add(Conv2D(32, (3, 3), input_shape=(50, 50, 1), activation='relu'))\n    model.add(Conv2D(32, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2, 2)))\n    \n    model.add(Conv2D(64, (3, 3), activation='relu'))\n    model.add(Conv2D(64, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2, 2)))\n    \n    model.add(Conv2D(128, (3, 3), activation='relu'))\n    model.add(Conv2D(128, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2, 2)))\n    \n    model.add(Dropout(0.2))\n\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu'))\n    \n    model.add(Dropout(0.2))\n    \n    model.add(Dense(1, activation='sigmoid'))\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = baseline_model()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.reshape(-1, 50, 50, 1)\nx_test = x_test.reshape(-1, 50, 50, 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(np.array(x_train), y_train, validation_data=(np.array(x_test), y_test), epochs=10, verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"hist = history.history","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(hist['loss'], 'green', label='Training Loss')\nplt.plot(hist['val_loss'], 'blue', label='Validation Loss')\n_ = plt.legend()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(hist['acc'], 'green', label='Training Accuracy')\nplt.plot(hist['val_acc'], 'blue', label='Validation Accuracy')\n_ = plt.legend()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dir = '../input/test/'\ntest_images = []\n\nfor img in tqdm(os.listdir(test_dir)):\n    try:\n        img_r = cv2.imread(os.path.join(test_dir, img), cv2.IMREAD_GRAYSCALE)\n        test_images.append(np.array(cv2.resize(img_r, (50, 50), interpolation=cv2.INTER_CUBIC)))\n    except Exception as e:\n        print('damaged image')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"_ = plt.imshow(test_images[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images = np.array(test_images)\ntest_images = test_images.reshape(-1, 50, 50, 1)\npredictions = model.predict(test_images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions.shape","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}