{"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\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 some packages to use\nimport cv2\nimport numpy as np\nimport pandas as pd\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":{"trusted":true,"_uuid":"49ebee813499ec21851661acadaa7195dd3bf061"},"cell_type":"code","source":"train_dir = '../input/train'\ntest_dir = '../input/test'\n\ntrain_dogs = ['../input/train/{}'.format(i) for i in os.listdir(train_dir) if 'dog' in i]  #get dog images\ntrain_cats = ['../input/train/{}'.format(i) for i in os.listdir(train_dir) if 'cat' in i]  #get cat images\n\ntest_imgs = ['../input/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,"_uuid":"5c9e94b7f625b5da3541f1785040e6fef4aed67d"},"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))  #Read the image\n        #get the labels\n        if 'dog' in image:\n            y.append(1)\n        elif 'cat' in image:\n            y.append(0)\n    \n    return X, y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"fac97176adcf320cbba366b8216f019a0aa153dc"},"cell_type":"code","source":"\n#get the train and label data\nX, y = read_and_process_image(train_imgs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b4c2ef043a0358b19b0721eb5d8a00d0667da4ba"},"cell_type":"code","source":"\n#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,"_uuid":"23e4ba8daa246e6ab30f51404dfc84c9e6195aff"},"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')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"49a81aa45a3a6f7b998f1cf30fc0c6dccade0e6e"},"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,"_uuid":"36797e588493ea810007692fba4165f019e0a38e"},"cell_type":"code","source":"\n#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,"_uuid":"6422f5c996fae4f4f2ba17a9df495dd5f89bc77f"},"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,"_uuid":"da2ab1e59e59061e2eed9e9c2a7b2ed8ea006a3e"},"cell_type":"code","source":"from keras.applications import InceptionResNetV2\nconv_base = InceptionResNetV2(weights = 'imagenet', include_top = False, input_shape = (150,150,3))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f62c88222d675ac9df3c1d94b9e799b8ea33cc0b"},"cell_type":"code","source":"conv_base.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3fcc9f8ce19890170d95900265618827261a0e09"},"cell_type":"code","source":"from keras import layers\nfrom keras import models\nmodel = models.Sequential()\nmodel.add(conv_base)\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(256, activation  = 'relu'))\nmodel.add(layers.Dense(1, activation = 'sigmoid'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b19b2928499ca29554dfa7f32b84baa8bac2389a"},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d5f96836b8fbc0cb29ef119ac94595db5da37080"},"cell_type":"code","source":"print ('No of trainable weights before freezing the conv_layers:', len(model.trainable_weights))\nconv_base.trainable = False\nprint ('No of trainable weights after freezing the conv_layers:', len(model.trainable_weights))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"923d0bc2ba01161f696f028a6921b0d98bba2320"},"cell_type":"code","source":"from keras import optimizers\nmodel.compile(loss='binary_crossentropy', optimizer = optimizers.RMSprop(lr = 2e-5), metrics = ['acc'])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"534f21a81ffb9a71ef9b2258e8c24b49e4473a37"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f82a435acee51c8a4d9c39d0d8871185ffde350f"},"cell_type":"code","source":"#Lets create the augmentation configuration\n#This helps prevent overfitting, since we are using a small dataset\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.preprocessing.image import img_to_array, load_img\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,"_uuid":"ac3d64f97f5d68bd69e826602cf5f769abf8c9af"},"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,"_uuid":"be544e41f99eb940be3ba2ada291b579ff2380c2"},"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=20,\n                              validation_data=val_generator,\n                              validation_steps=nval // batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"648d3ac28a1dd468cb3180ffc9aa9ed72361b206"},"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,"_uuid":"43ff9b617c8020af6fb8103f25e1b78207dae578"},"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,"_uuid":"608b691b1d0db0a5e3388f19d5924abda665cfa1"},"cell_type":"code","source":"\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    if i % 10 == 0:\n        break\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2b2de40e794393fbd20181d2fa38dc25d3303ad8"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}