{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# https://www.kaggle.com/ruchibahl18/cats-vs-dogs-basic-cnn-tutorial\n\n# 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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n#import cv2\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Flatten, Dropout, Activation, Conv2D, MaxPooling2D","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2\nmain_dir = \"../input/\"\ntrain_dir = \"train/train\"\npath = os.path.join(main_dir, train_dir)\n\nfor p in os.listdir(path):\n    category = p.split(\".\")[1]\n    img_array = cv2.imread(os.path.join(path,p),cv2.IMREAD_GRAYSCALE )\n    new_img_array = cv2.resize(img_array,dsize=(90,90))\n    plt.imshow(new_img_array,cmap=\"gray\")\n    break","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = []\nY = []\n\nconvert = lambda category : int(category == 'dog')\n\ndef create_test_data(path):\n    for p in os.listdir(path):\n        category = p.split(\".\")[0]\n        category  = convert(category)\n        img_array = cv2.imread(os.path.join(path,p), cv2.IMREAD_GRAYSCALE)\n        new_img_array = cv2.resize(img_array,dsize=(80,80))\n        X.append(new_img_array)\n        Y.append(category)\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"create_test_data(path)\nX = np.array(X).reshape(-1, 80,80,1)\nY = np.array(Y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pickle\n\npickle.dump( X, open( \"train_x\", \"wb\" ) )\npickle.dump( Y, open( \"train_y\", \"wb\" ) )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loaded_model = pickle.load(open(\"train_x\", 'rb'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loaded_model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Normalize data\nX = X/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n# Adds a densely-connected layer with 64 units to the model:\nmodel.add(Conv2D(64,(3,3), activation = 'relu', input_shape = X.shape[1:]))\nmodel.add(MaxPooling2D(pool_size = (2,2)))\n# Add another:\nmodel.add(Conv2D(64,(3,3), activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size = (2,2)))\n# Add another one\nmodel.add(Conv2D(128,(3,3), activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size = (2,2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(64, activation='relu'))\n\n# Add a softmax layer with 10 output units:\nmodel.add(Dense(1, activation='sigmoid'))\n\nmodel.compile(optimizer=\"adam\", loss='binary_crossentropy', metrics=['accuracy'])\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X, Y, epochs=10, batch_size=32, validation_split=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# preporcessing our test data\n\ntrain_dir = \"test1/test1\"\npath = os.path.join(main_dir,train_dir)\n#os.listdir(path)\n\nX_test = []\nid_line = []\ndef create_test1_data(path):\n    for p in os.listdir(path):\n        id_line.append(p.split(\".\")[0])\n        img_array = cv2.imread(os.path.join(path,p),cv2.IMREAD_GRAYSCALE)\n        new_img_array = cv2.resize(img_array, dsize=(80, 80))\n        X_test.append(new_img_array)\ncreate_test1_data(path)\nX_test = np.array(X_test).reshape(-1,80,80,1)\nX_test = X_test/255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predicted_val = [int(round(p[0])) for p in predictions]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(predicted_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = pd.DataFrame({'id':id_line, 'label':predicted_val})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}