{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 os\nimport matplotlib.pyplot as plt\nfrom zipfile import ZipFile\nimport cv2\n#Extracting zip files \nzf = ZipFile('../input/dogs-vs-cats/train.zip', 'r')\nzf1 = ZipFile('../input/dogs-vs-cats/test1.zip', 'r')\nzf.extractall('../kaggle/working/Temp')\nzf.close()\nzf1.extractall('../kaggle/working/Temp')\nzf1.close()\nmain = \"../kaggle/working/Temp/\"\ntrain_dir=\"train\"\np=os.path.join(main,train_dir)\np\nos.listdir(p)\nexample_pic='dog.890.jpg'\npath_example=p+'/'+example_pic\nX=[]\nY=[]\nconvert = lambda category : int(category == 'dog')  #Function to convert the dogs name as 0 and cat as 1\nfor file in os.listdir(p):\n    category=file.split('.')[0]\n    category=convert(category)\n        \n    img_array=cv2.imread(os.path.join(p,file))\n    new_array = cv2.resize(img_array, dsize=(80, 80))\n    X.append(new_array)\n    Y.append(category)\nY\nX=X[:10000] #Taking 10000 images as training set\nY=Y[:10000]\nY\nX=np.array(X).reshape(-1,80,80,3) ##reshaping the array with image_width,image_size and channels to provide in conv2d\nY=np.array(Y)\nY.shape\nX.shape\nX=X/255\n#Printing an example Image\nfrom keras.preprocessing.image import load_img,ImageDataGenerator,img_to_array\nimg=load_img(path_example)\nplt.imshow(img)\nfrom keras.utils import to_categorical\nY=to_categorical(Y)\nY\nY.shape\nfrom keras.layers import Dense, Conv2D,Dropout,Flatten,MaxPool2D,GlobalAveragePooling2D\nfrom keras.models import Sequential,Model\nfrom keras.callbacks import EarlyStopping,ReduceLROnPlateau\nearly_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=20, verbose=1, mode='auto')\n#Using pretraine Inception v3 model\nfrom keras.applications.inception_v3 import InceptionV3, preprocess_input\ninc_model = InceptionV3(weights='imagenet',\n                        include_top=False,\n                        input_shape=(80,80,3))\n                       \n\nprint(\"number of layers:\", len(inc_model.layers))\ninc_model.summary()\n#Adding custom layers\nx = inc_model.output\nx = GlobalAveragePooling2D()(x)\nx = Dense(128, activation=\"relu\")(x)\nx = Dropout(0.5)(x)\nx = Dense(64, activation=\"relu\")(x)\npredictions = Dense(2, activation=\"softmax\")(x)\nmodel_ = Model(inputs=inc_model.input, outputs=predictions)\n#Lock initial layers to not be trained\nfor layer in model_.layers[:52]:\n    layer.trainable=False\nmodel_.compile(optimizer='Adam',loss='categorical_crossentropy',metrics=['accuracy'])\nmodel_.fit(X,Y,validation_split=0.2,batch_size=32,epochs=30,callbacks=[early_stopping])\n#Preprocessing test set\nmain = \"../kaggle/working/Temp/\"\ntest_dir=\"test1\"\np=os.path.join(main,test_dir)\np\ntest_filename=os.listdir(\"../kaggle/working/Temp/test1\")\ntest_filename\nx_test=[]\nname=[]\nfor path in os.listdir(p):\n    name.append(path.split(\".\")[0])\n    img_array = cv2.imread(os.path.join(p,path))\n    new_img_array = cv2.resize(img_array, dsize=(80, 80))\n    x_test.append(new_img_array)\nlen(x_test)    \nx_test = np.array(x_test)\nx_test.shape\nx_test=x_test.reshape(-1,80,80,3)\nx_test.shape\nx_test = x_test/255\nx_test\npred=model_.predict(x_test)\n#Showing first 5 test images\nf, ax = plt.subplots(1,5)\nf.set_size_inches(80, 40)\nplt.title('Actual testing set')\nfor i in range(5):\n    ax[i].imshow(x_test[i])\nplt.show()\n\npredicted_val = [int(round(p[0])) for p in pred]\npredicted_val\n#Submission Dataframe\nsubmission_df = pd.DataFrame({'id':name, 'label':predicted_val})\nsubmission_df.head(10)\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}