{"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 \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 the files in the input directory\n\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nimport os\nimport random\nimport gc\nprint(os.listdir(\"../input\"))\n\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6f6ac3caf65a375ef89f39e53a4e53ba9edf8a1c"},"cell_type":"code","source":"\ntrain_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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"44b033c3b916a1a395083924cca8874b8287a2a7"},"cell_type":"code","source":"\n#Clear list that are useless\ndel train_dogs\ndel train_cats\n\ngc.collect()  #collect garbage to save memory\n\n\n#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\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\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b904a756961c23b89f502546aca430556ece7f63"},"cell_type":"code","source":"X,y = read_and_process_image(train_imgs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"970faf3cfc26446ef484af861785fd0b4ddfba94"},"cell_type":"code","source":"import matplotlib.image as mping\nfor ima in train_imgs[0:3]:\n    img = mping.imread(ima)\n    imgplot = plt.imshow(img)\n    plt.show()\n    ","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"X[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true,"_uuid":"9e2325d4dce6d2efa2501dee2d9b8a61a83d065e"},"cell_type":"code","source":"y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8ff2c4df9d6e2cb150acd584aba3f3edf23630a2"},"cell_type":"code","source":"plt.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    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"38bd49dbddc1d354421d2a593f1d0b3dd3b60c56"},"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":"a5b0d219e31a585ce4eaede691849961ca6a66f6"},"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":"75da8d45730f340d17deef60b7a5f93739feed16"},"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)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"50fbd1e20fb79a11e8b45b60bbdb751f825f3f04"},"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":"45bbe325f2d12cfe7e4fb990ba09ba3297568a27"},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"562311ce1dfba1f92997360d44f4496944e2417c"},"cell_type":"code","source":"model = 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\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0105cebc2af1232607006942ce9eafd21f8e95a9"},"cell_type":"code","source":"#Lets see our model\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"fc5c943c6cb7ec3ef28d094114f20297e4cb4ebb"},"cell_type":"code","source":"#We'll use the RMSprop optimizer with a learing 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'])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"36b01e46975e33c4ee369573811780d212683d2b"},"cell_type":"code","source":"#Lets create the alugmentation 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,)\nval_datagen = ImageDataGenerator(rescale=1./255)  #We do not augment validation data. we only perform rescale\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d4caa4d69d374c3e784a4c4bdcdef91758cd0915"},"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)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2093c86754436a250f9697477141b52ca073f867"},"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,"_uuid":"d6591524ede2f127a2c2c49c36dd6d4d8c536711"},"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,"_uuid":"28a5788187ec5c1b075747874b97d935d35c153d"},"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#Trailn 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()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"87d838e181431388f6e4ad74685b8e3e313377a6"},"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)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"905362f74591dfb16e71ca94fa3021e1247269e5"},"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":{"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}