{"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)\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        \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","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from tqdm import tqdm\nimport zipfile\nimport cv2\nimport random\nfrom sklearn.model_selection import train_test_split \nTrainFile='../working/train/train/'\nTestFile='/dev/shm/test'\nIMG_SIZE=128\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"numImages=25000\nnH = IMG_SIZE\nnW = IMG_SIZE\nnC = 3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nunzp=!  unzip ../input/dogs-vs-cats-redux-kernels-edition/train.zip -d train\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def findLabel(title):\n    if title=='dog':\n        return 0\n    else :\n        return 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def trainPrep(TrainFile): \n    train_data=[]\n    for file in tqdm(os.listdir(TrainFile)):\n        label,name,_=file.split('.')\n\n        y=findLabel(label)\n        img= os.path.join(TrainFile,file)\n        x=cv2.imread(img)\n\n        imgArr = cv2.resize(x, (IMG_SIZE,IMG_SIZE))\n        \n        train_data.append([imgArr,y])\n\n    random.shuffle(train_data)\n    \n    #np.save('train_data.npy',train_data)\n    return np.array(train_data)\n\n\n\n    \n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data=trainPrep(TrainFile)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#os.listdir('../working/train/train/')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data=train_data.T","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from matplotlib.pyplot import imshow\n\nimshow(train_data[0][600])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y=train_data[1]\ny=y.reshape(numImages,1)\ny.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X= np.array([i for i in train_data[0]]).reshape(-1,nH,nW,nC)\nX.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D,Flatten,Dropout,MaxPooling2D\nfrom keras.optimizers import adam\nfrom keras.initializers import random_normal\nimport keras","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"stride=2\nmpstride=2\nkernelM=(3,3)\nkernelC=(4,4)\nnF=16\nfor i in [1]:\n    print('for stride: ', i)\n    \n    model = Sequential()\n    \n    model.add(Conv2D(nF,kernel_size=kernelC,strides = stride,activation='relu',padding='same', input_shape=(nH,nW,nC)))\n    model.add(MaxPooling2D(pool_size=kernelM,strides=mpstride,padding='same'))\n    \n    model.add(Conv2D(nF*2,kernel_size=3,strides = stride,padding='same',activation='relu'))\n    model.add(MaxPooling2D(pool_size=2,strides=mpstride,padding='same'))\n    \n    \n    model.add(Flatten())\n    \n    model.add(Dense(500,kernel_initializer=random_normal(),activation='relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(200,kernel_initializer=random_normal(),activation='relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(70 ,kernel_initializer=random_normal(),activation='relu'))\n    #model.add(Dense(55,activation='relu'))\n    model.add(Dense(1,activation='sigmoid'))\n\n    model.compile(loss=keras.losses.BinaryCrossentropy(), optimizer=adam(learning_rate=0.0001),metrics=['accuracy'])\n\n    model.fit(X,y,batch_size=16,epochs=20,validation_split = 0.07)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\nclass FixedImageDataGenerator(ImageDataGenerator):\n    def standardize(self, x):\n        if self.featurewise_center:\n            x = ((x/255.) - 0.5) * 2.\n        return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = FixedImageDataGenerator(horizontal_flip = True,\n                                 \n                             width_shift_range = 0.1,\n                             height_shift_range = 0.1,\n                                                         \n                            )\nvaldatagen = FixedImageDataGenerator()\nit = datagen.flow(X_train,y_train)\nitval= valdatagen.flow(X_val,y_val)\n'''steps_per_epoch=25000//16,'''\nmodel.fit_generator(it,epochs=20,steps_per_epoch=50,validation_data=itval)","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}