{"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        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":{"trusted":true},"cell_type":"code","source":"import pandas as pd \nimport numpy as np ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import Dense,Dropout,Input,MaxPooling2D,ZeroPadding2D,Conv2D,Flatten,BatchNormalization\nfrom keras.models import Sequential\nfrom keras.losses import categorical_crossentropy\nfrom keras.optimizers import Adam,SGD\nfrom keras.preprocessing.image import img_to_array,load_img,ImageDataGenerator\nfrom keras.utils import to_categorical\n\nimport sys\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\npd.options.display.max_colwidth=150","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df1=pd.read_csv('../input/dog-breed-identification/labels.csv')\ndf1.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# path of the dogs images\nimg_file='../input/dog-breed-identification/train/'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df=df1.assign(img_path=lambda x: img_file + x['id'] +'.jpg')\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_pixel=np.array([img_to_array(dtype='int8',img=load_img(img, target_size=(128, 128))) for img in df['img_path'].values.tolist()])\nsys.getsizeof(img_pixel)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_label=df.breed\nimg_label=pd.get_dummies(df.breed).astype('int8')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X=img_pixel\ny=img_label.values\nprint(X.shape)\nprint(y.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)\nprint(X_train.shape)\nprint(y_train.shape)\nprint(X_test.shape)\nprint(y_test.shape)\n\ndel df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n    width_shift_range=0.25,\n    height_shift_range=0.25,\n    rotation_range=30,\n    rescale=1./255,\n    shear_range=0.2,\n    zoom_range=0.1,\n    horizontal_flip=True)\n\ntest_datagen=ImageDataGenerator(rescale=1./255)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"training_set=train_datagen.flow(X_train,y=y_train,batch_size=32)\ntesting_set=test_datagen.flow(X_test,y=y_test,batch_size=32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_model(optimizer):    \n    model=Sequential()\n    model.add(Conv2D(32,input_shape=(128,128,3),kernel_size=(3,3),activation='relu',padding='same'))\n    model.add(MaxPooling2D((4,4)))\n    model.add(BatchNormalization())\n    model.add(Conv2D(64,kernel_size=(3,3),activation='relu',padding='same'))\n    model.add(MaxPooling2D((4,4)))\n    model.add(BatchNormalization())\n    model.add(Conv2D(128,kernel_size=(3,3),activation='relu',padding='same'))\n    model.add(MaxPooling2D((2,2)))\n    model.add(BatchNormalization())\n    model.add(Conv2D(256,kernel_size=(3,3),activation='relu',padding='same'))\n    model.add(MaxPooling2D((2,2)))\n    model.add(BatchNormalization())\n    model.add(Conv2D(512,kernel_size=(3,3),activation='relu',padding='same'))\n    model.add(MaxPooling2D((2,2)))\n    model.add(Flatten())\n    model.add(Dense(120,activation='softmax'))\n    model.compile(optimizer=optimizer,\n              loss='categorical_crossentropy', \n               metrics=['accuracy'])\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\noptimizers = ['Adadelta', 'RMSprop', 'Adam', 'Adamax', 'Nadam', 'SGD']\naccuracies = {}\nfor optimizer in optimizers:\n    model = create_model(optimizer)\n    print(optimizer)\n    \n    history=model.fit_generator(training_set,\n                          steps_per_epoch = X_train.shape[0]/64,\n                          validation_data = testing_set,\n                          validation_steps = 4,\n                          epochs = 2,\n                          verbose = 0)\n    \n    accuracies[optimizer] = history.history['accuracy']\n    print(optimizer + ' done')\n    \n    tf.keras.backend.clear_session()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for optimizer, results in accuracies.items():\n    plt.plot(results)\n\nplt.title('Optimizers')\nplt.legend(optimizers)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history=model.fit_generator(training_set,\n                      steps_per_epoch = X_train.shape[0]/64,\n                      validation_data = testing_set,\n                      validation_steps = 4,\n                      epochs = 50,\n                      verbose = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# \"Train accuracy\"\nimport matplotlib.pyplot as plt\nplt.plot(history.history['accuracy'])\nplt.title('Adam Maxpool 4/4')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.optimizers import Adadelta, RMSprop, Adam, Adamax, Nadam, SGD\noptimizers = ['Adadelta', 'RMSprop', 'Adam', 'Adamax', 'Nadam', 'SGD']\naccuracies = {}\nfor optimizer in optimizers:\n    model=model.fit_generator(training_set,\n                          steps_per_epoch = X_train.shape[0]/64,\n                          validation_data = testing_set,\n                          validation_steps = 4,\n                          epochs = 50,\n                          verbose = 1)\n    \n    accuracies[optimizer] = model.history['accuracy']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}