{"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 in \n#!unzip ../input/dogs-vs-cats-redux-kernels-edition/train.zip -d train !unzip ../input/dogs-vs-cats-redux-kernels-edition/test.zip -d test\n\nimport cv2\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 all files under the input directory\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nimport os\nimport random\nimport gc\ntrain_dir = '../working/train/train'\ntest_dir = '../working/test/test'\n\ntrain_dogs = ['../working/train/train/{}'.format(i) for i in os.listdir(train_dir) if 'dog' in i]\ntrain_cats = ['../working/train/train/{}'.format(i) for i in os.listdir(train_dir) if 'cat' in i]\n\ntest_imgs = ['../working/test/test/{}'.format(i) for i in os.listdir(test_dir)]\n\ntrain_imgs = train_dogs[:2000]+train_cats[:2000]\n\nrandom.shuffle(train_imgs)\n\ndel train_dogs\ndel train_cats\ngc.collect()\n\nimport matplotlib.image as mpimg\nfor ima in train_imgs[0:3]:\n    img=mpimg.imread(ima)\n    imgplot=plt.imshow(img)\n    plt.show\n\nnrows = 150\nncolumns = 150\nchannels = 3\n\ndef read_and_process_image(list_of_images):\n    x = []\n    y = []\n    \n    for image in list_of_images:\n        x.append(cv2.resize(cv2.imread(image, cv2.IMREAD_COLOR), (nrows,ncolumns),interpolation=cv2.INTER_CUBIC))\n        if 'dog' in image:\n            y.append(1)\n        elif 'cat' in image:\n            y.append(0)\n    return x,y\nx, y = read_and_process_image(train_imgs)\ndel train_imgs\ngc.collect()\n\nplt.figure(figsize=(20,10))\ncolumns = 5\nfor i in range(columns):\n        plt.subplot(5 / columns + 1 , columns , i+1)\n        plt.imshow(x[i])\n\nx = np.array(x)\ny = np.array(y)\n\nfrom sklearn.model_selection import train_test_split\nx_train, x_val,y_train,y_val = train_test_split(x , y, test_size = 0.20 , random_state = 2)\n#print(x_train.shape,x_val.shape,y_train.shape,y_val.shape)\nntrain=len(x_train)\nnval=len(x_val)\n\nbatch_size = 8\ndel x,y\ngc.collect()\n\nfrom keras import layers\nfrom keras import models\nfrom keras import optimizers\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.preprocessing.image import img_to_array, load_img\n\nmodel = models.Sequential()\nmodel.add(layers.Conv2D(32,(3,3), activation='relu', input_shape=(150, 150, 3)))\nmodel.add(layers.MaxPooling2D(2,2))\nmodel.add(layers.Conv2D(64,(3,3), activation='relu'))\nmodel.add(layers.MaxPooling2D(2,2))\nmodel.add(layers.Conv2D(128,(3,3), activation='relu'))\nmodel.add(layers.MaxPooling2D(2,2))\nmodel.add(layers.Conv2D(128 ,(3,3), activation='relu'))\nmodel.add(layers.MaxPooling2D(2,2))\nmodel.add(layers.Flatten())\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(512, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))\n#model.summary()\nmodel.compile(loss = 'binary_crossentropy', optimizer = optimizers.RMSprop(lr=1e-4), metrics= ['acc'])\n\ntrain_datagen = ImageDataGenerator(rescale=1./255,  \n                                    rotation_range=40,\n                                    width_shift_range=0.2,\n                                    height_shift_range=0.2,\n                                    shear_range=0.2,\n                                    zoom_range=0.2,\n                                    horizontal_flip=True,)\n\nval_datagen = ImageDataGenerator(rescale=1./255) \n\ntrain_generator = train_datagen.flow(x_train, y_train, batch_size=batch_size)\nval_generator = val_datagen.flow(x_val, y_val, batch_size=batch_size)\n\nhistory = model.fit_generator(train_generator,\n                             steps_per_epoch = ntrain // batch_size,\n                             epochs = 128 ,\n                             validation_data = val_generator,\n                             validation_steps = nval // batch_size) \n\nmodel.save_weights('model_weights.h5')\nmodel.save('model_keras.h5')\n\nacc = history.history['acc']\nval_acc = history.history['val_acc']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\nepochs = range(1, len(acc) + 1)\n\nplt.plot(epochs, acc, 'b', label='Training Accuracy')\nplt.plot(epochs, val_acc, 'r', label='Validation Accuracy')\nplt.title('Training and Validation Accuracy')\nplt.legend()\nplt.figure()\n\nplt.plot(epochs, loss, 'b', label='Training Loss')\nplt.plot(epochs, val_loss, 'r', label='Validation Loss')\nplt.title('Training and Validation Loss')\nplt.legend()\nplt.show()\n\nx_test, y_test = read_and_process_image(test_imgs[0:10])\nx = np.array(x_test)\ntest_datagen = ImageDataGenerator(rescale =  1./255)\n\ni = 0\ntext_labels = []\nplt.figure(figsize = (30,20))\nfor batch in test_datagen.flow(x, batch_size = 1):\n    pred = model.predict(batch)\n    if pred > 0.5:\n        text_labels.append('dog')\n    else:\n        text_labels.append('cat')\n    plt.subplot(5 / columns + 1 , columns , i+1)\n    plt.title('This is a ' + text_labels[i])\n    imgplot = plt.imshow(batch[0])\n#    i-=-1\n    i+=1\n    if i % 10 == 0:\n        break\nplt.show()\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"","_uuid":"","trusted":true},"cell_type":"code","source":"import pandas as pd\nsample_submission = pd.read_csv(\"../input/dogs-vs-cats-redux-kernels-edition/sample_submission.csv\")","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}