{"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":"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\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport os\nimport cv2\nfrom tqdm import tqdm\nfrom random import shuffle\n\nimport tensorflow as tf\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\n# import os\n# for 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":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense\nfrom tensorflow.keras.callbacks import TensorBoard\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"base_dir = \"../input/dogs-vs-cats-redux-kernels-edition\"\ntrain_dir = os.path.join(base_dir, \"train.zip\")\ntest_dir = os.path.join(base_dir, \"test.zip\")\n\n# ../input/dogs-vs-cats-redux-kernels-edition/test.zip","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import zipfile\nwith zipfile.ZipFile(train_dir,\"r\") as z:\n z.extractall()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with zipfile.ZipFile(test_dir,\"r\") as z:\n z.extractall()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(os.listdir(\"../working/\"))\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dir  = \"../working/train\"\ntest_dir  = \"../working/test\"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_size = 50 \nl_rate = 0.001\n\nMODEL_NAME = 'dogsvscats-{}-{}.model'.format(l_rate,'2conv-basic')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def label_img(img):\n    word_label = img.split('.')[-3] # returns cat(-3).1000(-2).jpeg(-1) after split\n    if word_label == 'cat':\n        return[1,0]\n    elif word_label == 'dog':\n        return[0,1]\n    \n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def create_train_data():\n    training_data = []\n    for img in tqdm(os.listdir(train_dir)):\n        label = label_img(img)\n        path =  os.path.join(train_dir,img)\n        img = cv2.resize(cv2.imread(path,cv2.IMREAD_GRAYSCALE),(img_size,img_size))\n        training_data.append([np.array(img),np.array(label)])\n    shuffle(training_data)\n    np.save('train_data.npy',training_data)\n    return training_data","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def process_test_data():\n    testing_data = []\n    for img in tqdm(os.listdir(test_dir)):\n        path = os.path.join(test_dir,img)\n        img_num = img.split('.')[0]\n        img = cv2.resize(cv2.imread(path,cv2.IMREAD_GRAYSCALE),(img_size,img_size))\n        testing_data.append([np.array(img),np.array(img_num)])\n        \n    np.save('test_data.npy',testing_data)\n    return testing_data","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data =  create_train_data()\n### if already saved as numpy array\n# train_data =  np.load('train_data.npy')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(train_data)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# random.shuffle(train_data)\n\n# for sample in train_data[:10]:\n#     print(sample[1])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_clf= Sequential()\n# Convolution, Activation,Maxpooling -1\nmodel_clf.add(Conv2D(32,(3,3),input_shape=(img_size,img_size,1),activation = 'relu'))\nmodel_clf.add(MaxPooling2D(pool_size=(2,2),strides=1)) # Change later\n# Convolution, Activation,Maxpooling -2\nmodel_clf.add(Conv2D(64,(3,3),activation = 'relu'))\nmodel_clf.add(MaxPooling2D(pool_size=(2,2),strides=1))\n#Flatten\nmodel_clf.add(Flatten())\n## FF NN\nmodel_clf.add(Dense(units=128,activation='relu'))\n# Sigmoid output probability\nmodel_clf.add(Dense(units=1,activation='sigmoid'))\n\n#DEfine Optimizer \nadam = tf.keras.optimizers.Adam(lr=l_rate)\n#Model Compile\n# Sigmoid\nmodel_clf.compile(optimizer=adam,loss='binary_crossentropy',metrics=['accuracy'])\n#tensorboard = TensorBoard(log_dir=\"logs/{}\".format(time()))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_clf.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#training the model\n# history = model_clf.fit(x = training_set, validation_data = testing_set, epochs = 25)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}