{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Import libraries"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport zipfile\nimport numpy as np\nimport pandas as pd\nimport random\nimport tensorflow as tf\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator, load_img\nfrom keras.utils import to_categorical\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Loading data"},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"../input/dogs-vs-cats/train/train\")\nlabels = []\nfor name in filenames:\n    label = name.split('.')[0]\n    if label == 'dog':\n        labels.append(1)\n    else:\n        labels.append(0)\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'label': labels\n})\n\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Build CNN model"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization\nfrom keras.optimizers import RMSprop\n\nmodel = Sequential()\n\nmodel.add(Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid')) \n\nmodel.compile(loss='binary_crossentropy', optimizer=RMSprop(lr=0.001), metrics=['accuracy'])\n\nmodel.summary()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Train - validation set"},{"metadata":{"trusted":true},"cell_type":"code","source":"df['label'] = df['label'].replace({0:'cat', 1:'dog'})\n\ntrain_df, validate_df = train_test_split(df, test_size=0.20, random_state=42)\ntrain_df = train_df.reset_index(drop=True)\nvalidate_df = validate_df.reset_index(drop=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validate_df.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Training generator"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1/255,\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                                  fill_mode='nearest')\n\ntrain_generator = train_datagen.flow_from_dataframe(train_df,\n                                                    '../input/dogs-vs-cats/train/train',\n                                                    x_col = 'filename',\n                                                    y_col = 'label',\n                                                    batch_size=20,\n                                                    class_mode='binary',\n                                                    target_size=(150, 150))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Validation generator"},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_datagen = ImageDataGenerator(rescale=1/255)\n\nvalid_generator = valid_datagen.flow_from_dataframe(validate_df,\n                                                   '../input/dogs-vs-cats/train/train',\n                                                   x_col = 'filename',\n                                                   y_col = 'label',\n                                                   batch_size = 20,\n                                                   class_mode = 'binary',\n                                                   target_size = (150,150))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fit model"},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(train_generator,\n                              validation_data=valid_generator,\n                              steps_per_epoch=100,\n                              epochs=100,\n                              validation_steps=50,\n                              verbose=2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Plot training - validation accuracy & loss"},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib\nfrom matplotlib import pyplot as plt\n\n# Retrieve a list of list results on training and test data sets for each training epoch\nacc      = history.history[     'acc' ]\nval_acc  = history.history[ 'val_acc' ]\nloss     = history.history[    'loss' ]\nval_loss = history.history['val_loss' ]\n\nepochs   = range(len(acc)) # Get number of epochs\n\nplt.plot(epochs, acc, 'r', label='Training accuracy')\nplt.plot(epochs, val_acc, 'b', label='Validation accuracy')\nplt.title('Training and validation accuracy')\n\nplt.figure()\n\nplt.plot(epochs, loss, 'r', label='Training Loss')\nplt.plot(epochs, val_loss, 'b', label='Validation Loss')\nplt.title('Training and validation loss')\nplt.legend()\n\nplt.show()\n\n\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Prepare test set"},{"metadata":{"trusted":true},"cell_type":"code","source":"test_filenames = os.listdir(\"../input/dogs-vs-cats/test1/test1\")\ntest_df = pd.DataFrame({\n    'id': test_filenames\n})\ntest_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test_df, \n    \"../input/dogs-vs-cats/test1/test1/\", \n    x_col='id',\n    y_col=None,\n    class_mode=None,\n    target_size=(150,150),\n    batch_size=20\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = model.predict_generator(test_generator, steps=625) # test shape/ batch_size","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['label'] = (predict > 0.5).astype(int)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['id'] = test_df['id'].str.split('.').str[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.to_csv('submission.csv', index=False)","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":1}