{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"\n#Import some packages to use\nimport cv2\nimport numpy as np\nimport pandas as pd\nfrom subprocess import check_output\n\nimport matplotlib.pyplot as plt\n%matplotlib inline \n\n#To see our directory\nimport os\nimport random\nimport gc   #Gabage collector for cleaning deleted data from memory","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_dir = '../input/dogs-vs-cats-redux-kernels-edition/train'\ntest_dir = '../input/dogs-vs-cats-redux-kernels-edition/test'\n\ntrain_dogs = ['../input/dogs-vs-cats-redux-kernels-edition/train/{}'.format(i) for i in os.listdir(train_dir) if 'dog' in i]  #get dog images\ntrain_cats = ['../input/dogs-vs-cats-redux-kernels-edition/train/{}'.format(i) for i in os.listdir(train_dir) if 'cat' in i]  #get cat images\nprint(train_dogs[0])\nprint(train_cats[0])\ntest_imgs = ['../input/dogs-vs-cats-redux-kernels-edition/test/{}'.format(i) for i in os.listdir(test_dir)] #get test images\n\ntrain_imgs = train_dogs[:2000] + train_cats[:2000]  # slice the dataset and use 2000 in each class\nrandom.shuffle(train_imgs)  # shuffle it randomly\n\n#Clear list that are useless\ndel train_dogs\ndel train_cats\ngc.collect()   #collect garbage to save memory","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":" import matplotlib.image as mpimg\n for ima in train_imgs[900:903]:\n     img=mpimg.imread(ima)\n     imgplot = plt.imshow(img)\n     plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Lets declare our image dimensions\n#we are using coloured images. \nnrows = 150\nncolumns = 150\nchannels = 3  #change to 1 if you want to use grayscale image\n\n\n#A function to read and process the images to an acceptable format for our model\ndef read_and_process_image(list_of_images):\n    \"\"\"\n    Returns two arrays: \n        X is an array of resized images\n        y is an array of labels\n    \"\"\"\n    X = [] # images\n    y = [] # labels\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        #Read the image\n        #get the labels\n        if 'dog' in image[-15::]:\n            y.append(1)\n        elif 'cat' in image[-15::]:\n            y.append(0)\n    \n    return X, y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#get the train and label data\nX, y = read_and_process_image(train_imgs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Lets view some of the pics\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])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\ndel train_imgs\ngc.collect()\n\n#Convert list to numpy array\nX = np.array(X)\ny = np.array(y)\n\n#Lets plot the label to be sure we just have two class\nsns.countplot(y)\nplt.title('Labels for Cats and Dogs')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Shape of train images is:\", X.shape)\nprint(\"Shape of labels is:\", y.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Lets split the data into train and test set\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\nprint(\"Shape of train images is:\", X_train.shape)\nprint(\"Shape of validation images is:\", X_val.shape)\nprint(\"Shape of labels is:\", y_train.shape)\nprint(\"Shape of labels is:\", y_val.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#clear memory\ndel X\ndel y\ngc.collect()\n\n#get the length of the train and validation data\nntrain = len(X_train)\nnval = len(X_val)\n\n#We will use a batch size of 32. Note: batch size should be a factor of 2.***4,8,16,32,64...***\nbatch_size = 32","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from 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))  #Dropout for regularization\nmodel.add(layers.Dense(512, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))  #Sigmoid function at the end because we have just two classes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Lets see our model\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#We'll use the RMSprop optimizer with a learning rate of 0.0001\n#We'll use binary_crossentropy loss because its a binary classification\nmodel.compile(loss='binary_crossentropy', optimizer=optimizers.RMSprop(lr=1e-4), metrics=['acc'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Lets create the augmentation configuration\n#This helps prevent overfitting, since we are using a small dataset\ntrain_datagen = ImageDataGenerator(rescale=1./255,   #Scale the image between 0 and 1\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)  #We do not augment validation data. we only perform rescale","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Create the image generators\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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#The training part\n#We train for 64 epochs with about 100 steps per epoch\nhistory = model.fit_generator(train_generator,\n                              steps_per_epoch=ntrain // batch_size,\n                              epochs=64,\n                              validation_data=val_generator,\n                              validation_steps=nval // batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Save the model\nmodel.save_weights('model_wieghts.h5')\nmodel.save('model_keras.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#lets plot the train and val curve\n#get the details form the history object\nacc = history.history['acc']\nval_acc = history.history['val_acc']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs = range(1, len(acc) + 1)\n\n#Train and validation accuracy\nplt.plot(epochs, acc, 'b', label='Training accurarcy')\nplt.plot(epochs, val_acc, 'r', label='Validation accurarcy')\nplt.title('Training and Validation accurarcy')\nplt.legend()\n\nplt.figure()\n#Train and validation loss\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()\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Now lets predict on the first 10 Images of the test set\nX_test, y_test = read_and_process_image(test_imgs[0:10]) #Y_test in this case will be empty.\nx = np.array(X_test)\ntest_datagen = ImageDataGenerator(rescale=1./255)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"i = 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    if i % 10 == 0:\n        break\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#lets save our prediction and submit\n# counter = range(1, len(test_imgs) + 1)\n# df_solution = pd.DataFrame({\"id\": counter, \"label\":list(pred)})\n# cols = ['label']\n\n# for col in cols:\n#     df_solution[col] = df_solution[col].map(lambda x: str(x).lstrip('[').rstrip(']')).astype(float)\n\n# df_solution.to_csv(\"submissiondogsVScats.csv\", index = False)","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":1}