{"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 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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# import tensorflow as tf\n\n# print(\"TensorFlow Version:\",tf.__version__)\n\n# # Detect hardware, return appropriate distribution strategy\n# try:\n#     tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # TPU detection. No parameters necessary if TPU_NAME environment variable is set. On Kaggle this is always the case.\n#     print('Running on TPU ', tpu.master())\n# except ValueError:\n#     tpu = None\n    \n# if tpu:\n#     tf.config.experimental_connect_to_cluster(tpu)\n#     tf.tpu.experimental.initialize_tpu_system(tpu)\n#     strategy = tf.distribute.experimental.TPUStrategy(tpu)\n# else:\n#     strategy = tf.distribute.get_strategy() # default distribution strategy in Tensorflow. Works on CPU and single GPU.\n\n# print(\"REPLICAS: \", strategy.num_replicas_in_sync)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### ARCHIVE EXTRACTION\nExtract zipped images into 'input/dogs-vs-cats/'\n\nTraining dataset would be extracted into 'train/' subdirectory\n\nTest dataset would be extracted into 'test1/' subdirectory"},{"metadata":{"trusted":true},"cell_type":"code","source":"from zipfile import ZipFile, is_zipfile\n\nsource = \"../input/dogs-vs-cats/\"\nfor file_ in os.listdir(source):\n    file_path = os.path.join(source, file_)\n    if is_zipfile(file_path):\n        with ZipFile(file_path, 'r') as zipref:\n            zipref.extractall()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# import shutil\n\n# shutil.rmtree('./train/', ignore_errors=True)\n# shutil.rmtree('./test1/', ignore_errors=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"move cats train images to 'train/cat/' and dogs train images to 'train/dogs/' "},{"metadata":{"trusted":true},"cell_type":"code","source":"!mkdir './train/cat'\n!mkdir './train/dog'\n!bash -c 'mv ./train/cat.{0..12499}.jpg ./train/cat/'\n!bash -c 'mv ./train/dog.{0..12499}.jpg ./train/dog/'\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Train dataset contains %i folders: %i cats and %i dogs\" %(len(os.listdir('./train/')),\n                                                                 len(os.listdir('./train/cat')), \n                                                                 len(os.listdir('./train/dog'))))\nprint(\"Test dataset contains %i samples\" %(len(os.listdir('./test1/'))))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Use ImageDataGenerator to quickly convert image data to tensors"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\ntrain_dir = './train'\ntest_dir = './test1'\n\ntrain_cat_dir = train_dir + '/cat'\ntrain_dog_dir = train_dir + '/dog'\n\ntrain_data_generator = ImageDataGenerator(rescale=1./255, validation_split=0.2)\n# add validation split was added train dataset into 'training' and 'validation' subsets\n\ntest_data_generator = ImageDataGenerator(rescale=1./255)\n\nBATCH_SIZE = 20\n\nargs_ = {\"target_size\":(150, 150,),\n         \"batch_size\":BATCH_SIZE,\n         \"class_mode\":'binary'}\ntrain_generator = train_data_generator.flow_from_directory(\n                    train_dir,\n                    subset='training',\n                    **args_)\n\nvalidation_generator = train_data_generator.flow_from_directory(\n                    train_dir,\n                    subset='validation',\n                    **args_)\ntest_generator = test_data_generator.flow_from_directory(\n                    test_dir,\n                    **args_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('data batch shape:', train_generator[0][0].shape)\nprint('labels batch shape:', train_generator[0][1].shape)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Function to build model"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import models, layers, optimizers\n\ndef build_model():\n    model = models.Sequential()\n    model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))\n    model.add(layers.MaxPooling2D((2,2)))\n    model.add(layers.Conv2D(64, (3,3), activation='relu'))\n    model.add(layers.MaxPooling2D((2,2)))\n    model.add(layers.Conv2D(128, (3,3), activation='relu'))\n    model.add(layers.MaxPooling2D((2,2)))\n    model.add(layers.Conv2D(128, (3,3), activation='relu'))\n    model.add(layers.MaxPooling2D((2,2)))\n\n    model.add(layers.Flatten())\n    model.add(layers.Dropout(0.5))\n    model.add(layers.Dense(512, activation='relu'))\n    model.add(layers.Dense(1, activation='sigmoid'))\n\n    model.compile(loss='binary_crossentropy',\n                 optimizer=optimizers.RMSprop(lr=1e-4),\n                 metrics=['acc',])\n\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = build_model()\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Train Model\n\nTrain and validate model on train_generator and validation_generator "},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(train_generator,\n                         steps_per_epoch=train_generator.samples // BATCH_SIZE, \n                         epochs=25,\n                         validation_data=validation_generator,\n                         validation_steps=validation_generator.samples // BATCH_SIZE)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"    Saving the model"},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save('cats and dogs_v1.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# from IPython.display import FileLink\n# FileLink('cats and dogs_v1.h5')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### ACCURACY AND LOSS PLOTS\n\nPlots of accuracies (training accuracy and validation loss) and losses (Training loss and validation loss) are shown below."},{"metadata":{"trusted":true},"cell_type":"code","source":"import plotly.graph_objects as go\nfig1 = go.Figure()\nfig2 = go.Figure()\n\nacc = history.history.get('acc')\nval_acc = history.history.get('val_acc')\nloss = history.history.get('loss')\nval_loss = history.history.get('val_loss')\n\nepochs = list(range(1, len(acc) + 1))\n\nfig1.add_scatter(x=epochs, y=acc, name='Training acc', mode='markers')\nfig1.add_scatter(x=epochs, y=val_acc, name=\"Validation acc\")\nfig1.update_layout(title={\"text\":\"Training and validation Accuracy\", \"x\":0.5}, xaxis_title=\"Epoch\", yaxis_title=\"Accuracy\")\nfig1.show()\n\nfig2.add_scatter(x=epochs, y=loss, name='Training loss', mode='markers')\nfig2.add_scatter(x=epochs, y=val_loss, name=\"Validation loss\")\nfig2.update_layout(title={\"text\":\"Training and validation Loss\", \"x\":0.5}, xaxis_title=\"Epoch\", yaxis_title=\"loss\")\nfig2.show()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### USING Pretrained convnet"},{"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}