{"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_minor":4,"nbformat":4,"cells":[{"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 20GB 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\n\nimport zipfile\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport random\nimport time\n\nfrom sklearn.model_selection import train_test_split\n\n#from tensorflow.keras.preprocessing.image import ImageDataGenerator\nimport cv2\nimport gc\n\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D\nfrom tensorflow.keras.layers import MaxPool2D\nfrom tensorflow.keras.layers import Flatten\nfrom tensorflow.keras.layers import Dense, Dropout\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Unzip the training dataset\nlocal_zip = '../input/dogs-vs-cats/train.zip'\n\nzip_ref = zipfile.ZipFile(local_zip, 'r')\n#For Kaggle\n#base_dir_zip = '/kaggle/working/'\n#For peronal PC\nbase_dir_zip = '/kaggle/working/'\n\n#Unzip all images\nzip_ref.extractall(base_dir_zip)\n\nzip_ref.close()\n\n# Loop through all the files in the directory\ntrain_dir = os.path.join(base_dir_zip, 'train')\ntrain_img_names = os.listdir(train_dir)\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(train_img_names[:10])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"categories= list()\nyvalues = list()\nfor image in train_img_names:\n    category = image.split(\".\")[0]\n    if category == \"dog\":\n        categories.append(\"dog\")\n        yvalues.append(1)\n    else:\n        categories.append(\"cat\")\n        yvalues.append(0)\ndf= pd.DataFrame({\"Image\":train_img_names, \"Category\": categories, \"yvalue\": yvalues})","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df[\"Category\"].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train,validation= train_test_split(df, test_size=0.1)\ntrain = train.reset_index(drop=True)\nvalidation = validation.reset_index(drop=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[\"Category\"].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validation[\"Category\"].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# MODEL 2","metadata":{}},{"cell_type":"code","source":"size = 150\nbatch_size=128\n#Black and white 1, color 3 (RGB)\ncolortype = 3\n\n\n# All images will be rescaled by 1./255.\ntrain_datagen = ImageDataGenerator( rescale = 1.0/255., horizontal_flip=True)\n\n\n# --------------------\n# Flow training images in batches of 20 using train_datagen generator\n# --------------------\ntrain_generator = train_datagen.flow_from_dataframe(train,\n                                                    directory=train_dir,\n                                                    x_col='Image',\n                                                    y_col='Category',\n                                                    batch_size=batch_size,\n                                                    class_mode='binary',\n                                                    target_size=(size, size))    \n\n\nvalidation_datagen  = ImageDataGenerator( rescale = 1.0/255.)\nvalidation_generator =  validation_datagen.flow_from_dataframe(validation,\n                                                               directory=train_dir,\n                                                               x_col='Image',\n                                                               y_col='Category',\n                                                               batch_size=batch_size,\n                                                               class_mode  = 'binary',\n                                                               target_size=(size, size))\n\nmodel = Sequential()\nmodel.add(Conv2D(filters=32, kernel_size=3,activation=\"relu\", input_shape=(size,size,colortype)))\nmodel.add(MaxPool2D(pool_size=2, strides=2))\nmodel.add(Dropout(0.2))\nmodel.add(Conv2D(filters=64, kernel_size=3,activation=\"relu\"))\nmodel.add(MaxPool2D(pool_size=2, strides=2))\nmodel.add(Dropout(0.2))\nmodel.add(Conv2D(filters=128, kernel_size=3, activation=\"relu\"))\nmodel.add(MaxPool2D(pool_size=2, strides=2))\nmodel.add(Dropout(0.2))\nmodel.add(Flatten())\nmodel.add(Dense(units=512, activation=\"relu\"))\nmodel.add(Dense(units=1, activation=\"sigmoid\"))\nmodel.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"numepochs=1\n\nearly = EarlyStopping(monitor='val_loss', mode='min', patience=10, restore_best_weights=True, verbose=1)\n#checkpoint = ModelCheckpoint(\"best_model.hdf5\", monitor='accuracy', verbose=1, save_best_only=True, mode='auto')\n\nmodel.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n\n# Initial Training of the model...\nstartTime = time.time()\n\nhistory=model.fit(train_generator, validation_data=validation_generator, epochs=numepochs,callbacks=[early])\n\nexecutionTime = (time.time() - startTime)\nprint('Execution time in seconds: ' + str(executionTime))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# TEST RUN","metadata":{}},{"cell_type":"code","source":"#Unzip the training dataset\nlocal_zip = '../input/dogs-vs-cats/test1.zip'\n\nzip_ref = zipfile.ZipFile(local_zip, 'r')\n#For Kaggle\n#base_dir_zip = '/kaggle/working/'\n#For peronal PC\nbase_dir_zip = '/kaggle/working/'\n\n#Unzip all images\nzip_ref.extractall(base_dir_zip)\n\nzip_ref.close()\n\n# Loop through all the files in the directory\ntest_dir = os.path.join(base_dir_zip, 'test1')\ntest_img_names = os.listdir(test_dir)\n\n\n\ntest_df = pd.DataFrame({'Image': test_img_names})\ntest_df.head()\n\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df['id'] = test_df['Image'].apply(lambda x: x.rsplit(\".\", 1)[0])\ntest_df.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\ntest_datagen = ImageDataGenerator(rescale = 1.0/255.)\ntest_generator = test_datagen.flow_from_dataframe(test_df,\n                                                 directory=test_dir,\n                                                 x_col=\"Image\",\n                                                 y_col=None,\n                                                 class_mode  = None,\n                                                 target_size=(size,size),\n                                                 batch_size=batch_size)\n\npredictions = model.predict(test_generator)\npredictions","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df[\"category\"]=pd.DataFrame(predictions, columns=[\"category\"])\n\ndef labelizor(prediction):\n    if prediction > 0.5:\n        return 1\n    else:\n        return 0\n    \ntest_df[\"label\"] = test_df[\"category\"].apply(labelizor)\ntest_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import glob\n\nfiles = glob.glob('/kaggle/working/train/*')\nfor f in files:\n    os.remove(f)\n    \nfiles = glob.glob('/kaggle/working/test1/*')\nfor f in files:\n    os.remove(f)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = test_df[[\"id\", \"label\"]]\nsubmission","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}