{"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 os\nimport zipfile\nimport random\nimport tensorflow as tf\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom shutil import copyfile","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"with zipfile.ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working')\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as zip_ref:\n    zip_ref.extractall('/kaggle/working')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"/kaggle/working/train\")\nfilenames[0]\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"categories = []\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        categories.append('dog')\n    else:\n        categories.append('cat')\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.head()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train,test=train_test_split(df,test_size=0.20, random_state=13)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class myCallback(tf.keras.callbacks.Callback):\n    def on_epoch_end(self, epoch, logs={}):\n        if(logs.get('accuracy')>0.95):\n            print(\"\\nReached 95% accuracy so cancelling training!\")\n            self.model.stop_training = True\n\n  # Your Code\n\ncallbacks = myCallback()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1/255)\nvalidation_datagen = ImageDataGenerator(rescale=1/255)\n\ntrain_generator=train_datagen.flow_from_dataframe(\n    train, \n    \"/kaggle/working/train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=(128,128),\n    class_mode='categorical',\n    batch_size=128)\n\nvalid_generator=validation_datagen.flow_from_dataframe(\n    test, \n    \"/kaggle/working/train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=(128,128),\n    class_mode='categorical',\n    batch_size=128)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.models.Sequential([\n    tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(128, 128,3)),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2, 2),\n\n    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n\n    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n\n    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n\n    tf.keras.layers.Flatten(),\n\n    tf.keras.layers.Dense(512, activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n\n    tf.keras.layers.Dense(2, activation='softmax')\n])\n\nfrom tensorflow.keras.optimizers import RMSprop\n\nmodel.compile(loss='categorical_crossentropy',\n              optimizer=RMSprop(lr=0.001),\n              metrics=['accuracy'])\n\n\nhistory = model.fit(\n      train_generator,  \n      epochs=15,\n      verbose=1,\n      validation_data = valid_generator,\n      callbacks=[callbacks])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames_test = os.listdir(\"/kaggle/working/test1\")\ntest_df = pd.DataFrame({\n    'filename': filenames_test\n})","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    \"/kaggle/working/test1/\", \n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    target_size=(128,128),\n    batch_size=128,\n    shuffle=False\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict=model.predict_generator(test_generator,steps=np.ceil(12500/128))\ntest_df['category'] = np.argmax(predict, axis=-1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = test_df.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['category']\nsubmission_df.drop(['filename', 'category'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","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}