{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import os \nimport zipfile\nlocal_zip = '/kaggle/input/dogs-vs-cats/train.zip'\nzip_ref=zipfile.ZipFile(local_zip, 'r')\nzip_ref.extractall('/kaggle/tmp')\nzip_ref.close()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base_dir = '/kaggle/tmp'\ntrain_dir = os.path.join(base_dir,'train')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dir_frames = os.listdir(train_dir)\nprint(train_dir_frames[:5])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"/kaggle/tmp/train\")\ncategories = []\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        categories.append(1)\n    else:\n        categories.append(0)\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.tail(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"tortal training Images = \",len(os.listdir('/kaggle/tmp/train')))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%matplotlib inline\n\nimport matplotlib.image as mpimg\nimport matplotlib.pyplot as plt\n\nnrow = 4\nncols = 4\npic_index = 0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import load_img, ImageDataGenerator\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import random\nsample = random.choice(filenames)\nprint(sample)\nimg = mpimg.imread('/kaggle/tmp/train/'+sample)\nplt.imshow(img)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.models.Sequential([\n    \n    tf.keras.layers.Conv2D(16,(3,3),activation='relu', input_shape = (150,150,3)),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.25),\n    \n    \n    \n    tf.keras.layers.Conv2D(32,(3,3),activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.20),\n    \n    \n    tf.keras.layers.Conv2D(64,(3,3),activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.25),\n    \n    \n    \n    tf.keras.layers.Conv2D(128,(3,3),activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.20),\n    \n    \n    tf.keras.layers.Conv2D(256,(3,3),activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.MaxPooling2D(3,3),\n    tf.keras.layers.Dropout(0.25),\n    \n    \n    \n    tf.keras.layers.Flatten(),\n    tf.keras.layers.Dense(512,activation='relu'),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Dropout(.50),\n    tf.keras.layers.Dense(1,activation='softmax')\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.optimizers import RMSprop\nmodel.compile(optimizer=RMSprop(lr=0.0001),\n             loss='categorical_crossentropy',metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df.head(10))\ndf['category'] = df['category'].replace({0:'cat',1:'dog'})\nprint(df.head(10))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data , test_data = train_test_split(df, test_size = 0.2,random_state = 30)\n\ntrain_data = train_data.reset_index(drop= True)\ntest_data = test_data.reset_index(drop=True)\nprint(train_data.head(10))\nprint(test_data.head(10))\n\ntrain_data['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_len = train_data.shape[0]\ntest_len = test_data.shape[0]\nbatch_size = 20","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale = 1./255,\n                              rotation_range = 30,\n                              shear_range = .2,\n                              zoom_range = .2,\n                              horizontal_flip = True,\n                              width_shift_range = .15,\n                              height_shift_range = .15)\ntrain_generator = train_datagen.flow_from_dataframe(train_data,'/kaggle/tmp/train/',\n                                                   x_col = 'filename',\n                                                   y_col = 'category',\n                                                   target_size = (150, 150),\n                                                   class_mode = 'categorical',\n                                                   batch_size = batch_size)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_datagen = ImageDataGenerator(rescale = 1./255)\ntest_generator = test_datagen.flow_from_dataframe(test_data, '/kaggle/tmp/train/',\n                                                 x_col = 'filename',\n                                                 y_col = 'category',\n                                                 target_size = (150, 150),\n                                                 class_mode = 'categorical',\n                                                 batch_size = batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"example_data = train_data.sample(n=1).reset_index(drop=True)\nexample_generator = train_datagen.flow_from_dataframe(example_data,'/kaggle/tmp/train',\n                                                     x_col = 'filename',\n                                                     y_col = 'category',\n                                                     target_size = (150, 150),\n                                                     class_mode = 'categorical')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(16,16))\nfor i in range(0,16):\n    plt.subplot(4,4 , i+1)\n    for X_batch, Y_batch in example_generator:\n        image = X_batch[0]\n        plt.imshow(image)\n        break\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fastrun = False \nepochs = 3 if fastrun else 20\nhistory = model.fit_generator(train_generator,\n                             epochs = epochs,\n                             validation_data = test_generator,\n                             validation_steps = test_len//batch_size,\n                             steps_per_epoch = train_len//batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save_weights('model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, (ax1,ax2)=plt.subplots(2,1,figsize=(12,12))\nax1.plot(history.history['loss'], color='b',label = 'Training_loss')\nax1.plot(history.history['val_loss'], color='r',label='validation_loss')\nax1.set_xticks(np.arange(1,epochs,1))\nax1.set_yticks(np.arange(0,1,0.1))\n\n\nax2.plot(history.history['accuracy'],color='b', label = 'Training_accuracy')\nax2.plot(history.history['val_accuracy'], color='r',label='Validation_accuracy')\nax2.set_xticks(np.arange(1,epochs,1))\nlegend = plt.legend(loc='best', shadow=True)\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os \nimport zipfile\nlocal_zip = '/kaggle/input/dogs-vs-cats/test1.zip'\nzip_ref=zipfile.ZipFile(local_zip, 'r')\nzip_ref.extractall('/kaggle/tmp')\nzip_ref.close()\n\nbase_dir = '/kaggle/tmp'\ntest_dir = os.path.join(base_dir,'test1')\n\ntest_dir_frames = os.listdir(test_dir)\nprint(test_dir_frames[:5])\n\ntest_filenames = os.listdir(\"/kaggle/tmp/test1\")\ntest_df = pd.DataFrame({'filename': test_filenames})\nnb_samples = test_df.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale = 1./255)\ntest_generator = test_gen.flow_from_dataframe(test_df, '/kaggle/tmp/test1/',\n                                            x_col = 'filename',\n                                            y_col = None,\n                                            class_mode = None,\n                                            target_size = (150,150),\n                                            batch_size = batch_size,\n                                            shuffle = False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = model.predict_generator(test_generator,steps = np.ceil(nb_samples/batch_size))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['category'] = np.argmax(predict, axis = -1)\nlabel_map = dict((v,k) for k, v in train_generator.class_indices.items())\ntest_df['category'] = test_df['category'].replace(label_map)\ntest_df['category'] =  test_df['category'].replace({'dog':1, 'cat': 0})\ntest_df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_test = test_df.head(18)\nsample_test.head()\nplt.figure(figsize = (12,24))\n\nfor index, row in sample_test.iterrows():\n    filename = row['filename']\n    category = row['category']\n    img = load_img('/kaggle/tmp/test1/'+filename, target_size = (150,150))\n    plt.subplot(6,3, index+1)\n    plt.imshow(img)\n    plt.xlabel(filename + ' ( ' + \" {} \".format(category)+\" ) \" )\nplt.tight_layout()\nplt.show()","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}