{"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)\nimport tensorflow as tf\nimport zipfile\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.model_selection import train_test_split\nfrom keras.preprocessing.image import ImageDataGenerator, load_img\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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"local_zip = '/kaggle/input/dogs-vs-cats/train.zip'\n\nzip_ref = zipfile.ZipFile(local_zip, 'r')\n\nzip_ref.extractall('/kaggle/output/kaggle/working/dogs-vs-cats')\nzip_ref.close()\n\nsave_dir = \"/kaggle/output/kaggle/working/dogs-vs-cats/saved_history\"\n# os.mkdir(save_dir+\"/saved_history\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_dir = \"/kaggle/output/kaggle/working/dogs-vs-cats/train\"\nfilenames = os.listdir(\"/kaggle/output/kaggle/working/dogs-vs-cats/train\")\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"category = []\n\nfor i in filenames:\n    s= i.split(\".\")\n    category.append(s[0])\n\ndf = pd.DataFrame({\"filename\": filenames, \"Category\": category})\ndf[\"Category\"].unique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(5,5))\nax.hist(df[\"Category\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = df.sample(frac=1).reset_index(drop=True)\ndf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"smple = np.random.choice(df[\"filename\"])\nimg = load_img(img_dir+\"/\"+smple, target_size = (150,150))\nplt.imshow(img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train, df_test = train_test_split(df, test_size=.2)\ndf_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator( rotation_range=15,\n    rescale=1./255,\n    shear_range=0.1,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    width_shift_range=0.1,\n    height_shift_range=0.1 )\ntest_datagen = ImageDataGenerator( rotation_range=15,\n    rescale=1./255,\n    shear_range=0.1,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    width_shift_range=0.1,\n    height_shift_range=0.1 )\n\ntrain_generator = train_datagen.flow_from_dataframe(df_train, img_dir, target_size=(150,150),\n                                                   x_col= \"filename\", y_col= \"Category\",\n                                                   class_mode= \"categorical\",\n                                                   batch_size=15)\n\ntest_generator = test_datagen.flow_from_dataframe(df_test, img_dir, target_size=(150,150),\n                                                   x_col= \"filename\", y_col= \"Category\",\n                                                   class_mode= \"categorical\",\n                                                   batch_size=15)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau\n\nearly_stop = EarlyStopping(patience=10)\n\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_accuracy',patience=2,verbose=1, \n                                            factor=0.5, min_lr=0.00001)\n\ncsv_logger = tf.keras.callbacks.CSVLogger(save_dir+\"/training_log\", separator=\",\", append=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.layers import BatchNormalization, Dropout\n\nmodel = tf.keras.models.Sequential([\n    tf.keras.layers.Conv2D(16,(3,3), input_shape=(150,150,3), activation=\"relu\"),\n    BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    \n    tf.keras.layers.Conv2D(32,(3,3), activation=\"relu\"),\n    BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    \n    tf.keras.layers.Flatten(),\n    tf.keras.layers.Dense(512, \"relu\"),\n    BatchNormalization(),\n    Dropout(0.5),\n    \n    tf.keras.layers.Dense(265, \"relu\"),\n    BatchNormalization(),\n    Dropout(0.5),\n    \n    tf.keras.layers.Dense(2, \"softmax\")\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history= model.fit_generator(train_generator, epochs = 10, validation_data = test_generator,\n                            callbacks = [early_stop, learning_rate_reduction, csv_logger])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history.history","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = np.arange(1,11,1)\ntrain_acc = history.history[\"accuracy\"]\ntest_acc = history.history[\"val_accuracy\"]\ntrain_loss = history.history[\"loss\"]\ntest_loss = history.history[\"val_loss\"]\n\nfig, (ax1, ax2 )= plt.subplots(2,1, figsize= (10,10))\nax1.plot(epochs,train_acc, color=\"r\", label= \"Train_Accuracy\" )\nax1.plot(epochs, test_acc, color=\"b\", label= \"Test_Accuracy\")\nax1.legend(shadow=True, fontsize= 13)\nax1.set_xlabel(\"Epochs\", fontsize=16 )\nax1.set_ylabel(\"Accuracy\", fontsize=16)\n\n\nax2.plot(epochs,train_loss, color=\"r\", label= \"Train_Loss\" )\nax2.plot(epochs, test_loss, color=\"b\", label= \"Test_Loss\")\nax2.legend(shadow=True, fontsize= 13)\nax2.set_xlabel(\"Epochs\", fontsize=16 )\nax2.set_ylabel(\"Loss\", fontsize=16)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nprint(os.listdir(save_dir))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save(save_dir)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"new_model = tf.keras.models.load_model(save_dir)\nnew_model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_log = pd.read_csv(save_dir+\"/training_log\")\ndf_log","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"local_zip = '/kaggle/input/dogs-vs-cats/test1.zip'\n\nzip_ref = zipfile.ZipFile(local_zip, 'r')\n\nzip_ref.extractall('/kaggle/output/kaggle/working/dogs-vs-cats/test1')\nzip_ref.close()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dir = \"/kaggle/output/kaggle/working/dogs-vs-cats/test1/test1\"\n\ntest_list = os.listdir(test_dir)\nlen(test_list)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test = pd.DataFrame({\"filename\": test_list})\ndf_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test2_datagen = ImageDataGenerator(rescale=1/255)\ntest2_generator = test2_datagen.flow_from_dataframe(df_test, test_dir, x_col= \"filename\",\n                                                    target_size=(150,150),class_mode=None)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = model.predict_generator(test2_generator)\npredict","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict_class = predict.argmax(axis = -1)\n\npredict_class","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict_by_name = [\"cat\" if x == 0 else \"dog\" for x in predict_class]\n\npredict_by_name","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator.class_indices","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test.insert(column=\"category_by_name\", value=predict_by_name, loc=1)\ndf_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = np.random.choice(df_test[\"filename\"])\nimg = load_img(test_dir+\"/\"+sample, target_size=(150,150))\nlabel = df_test.loc[(df_test[\"filename\"] == sample)][\"category_by_name\"].item()\nplt.figure(figsize=(10,10))\nplt.imshow(img)\nplt.xlabel(\"{} is a {}\".format(sample, label))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}