{"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":"\n# 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-09-15T20:18:35.957786Z","iopub.execute_input":"2022-09-15T20:18:35.958364Z","iopub.status.idle":"2022-09-15T20:18:35.987402Z","shell.execute_reply.started":"2022-09-15T20:18:35.958238Z","shell.execute_reply":"2022-09-15T20:18:35.986391Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install py7zr","metadata":{"execution":{"iopub.status.busy":"2022-09-15T20:18:35.989447Z","iopub.execute_input":"2022-09-15T20:18:35.990143Z","iopub.status.idle":"2022-09-15T20:18:53.588738Z","shell.execute_reply.started":"2022-09-15T20:18:35.990109Z","shell.execute_reply":"2022-09-15T20:18:53.587545Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Extract Data","metadata":{}},{"cell_type":"code","source":"import shutil\nfrom py7zr import unpack_7zarchive\nshutil.register_unpack_format('7zip',['.7z'],unpack_7zarchive)\nshutil.unpack_archive('../input/cifar-10/train.7z', '/kaggle/temp/')","metadata":{"execution":{"iopub.status.busy":"2022-09-15T20:18:53.591999Z","iopub.execute_input":"2022-09-15T20:18:53.592331Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels = pd.read_csv(\"../input/cifar-10/trainLabels.csv\", header=\"infer\")\n\nclasses = train_labels['label'].unique()\nprint(classes)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Divide the training set into training and validation dataset\n\nif not os.path.exists(\"/kaggle/temp/valid\"):\n    os.mkdir(\"/kaggle/temp/valid\")\n    \nparent_path_train = \"/kaggle/temp/train\"\nparent_path_valid = \"/kaggle/temp/valid\"\nparent_path_test = \"/kaggle/temp/test\"\n\nfor class1 in classes:\n    path_train = os.path.join(parent_path_train,class1)\n    if not os.path.exists(path_train):\n        os.mkdir(path_train)\n    path_valid = os.path.join(parent_path_valid,class1)\n    if not os.path.exists(path_valid):\n        os.mkdir(path_valid)\n        \nfor (int_ind,row) in train_labels.iterrows():\n    id = str(row[\"id\"])+\".png\"\n    source_path = os.path.join(parent_path_train,id)\n    \n    p=np.random.random()\n    if p<=0.8:\n        target_path = os.path.join(parent_path_train,row[\"label\"],id)\n        os.replace(source_path, target_path)\n    else:\n        target_path = os.path.join(parent_path_valid,row[\"label\"],id)\n        os.replace(source_path, target_path)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls /kaggle/temp/valid/airplane/* | wc\n!ls /kaggle/temp/train","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Performing Data Augmentation\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\ntrain_datagen = ImageDataGenerator(featurewise_center=True,\n    featurewise_std_normalization=True,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True,\n    validation_split=0.2)\nvalid_datagen = ImageDataGenerator(featurewise_center=True,\n    featurewise_std_normalization=True,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True,\n    validation_split=0.2)\n\ntrain_generator = train_datagen.flow_from_directory(directory='/kaggle/temp/train/', shuffle=True, target_size=(32,32),batch_size=128)\nvalid_generator = valid_datagen.flow_from_directory(directory='/kaggle/temp/valid/', shuffle=True, target_size=(32,32),batch_size=128)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"type(train_generator)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nimport tensorflow.keras\nfrom tensorflow.keras.layers import ReLU,Dense, MaxPool2D, Conv2D, Dropout, Flatten, GlobalAveragePooling2D, BatchNormalization, Activation, MaxPooling2D\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.regularizers import l2\n\n#Defining the model architecture\ndef define_model():\n    model = Sequential()\n    \n    model.add(Conv2D(filters=64, kernel_size=(3, 3),strides=(1,1), padding='same',use_bias=False, input_shape=(32, 32, 3)))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Dropout(0.5))\n    \n    model.add(Conv2D(filters=92, kernel_size=(3, 3),strides=(1,1), padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPooling2D((2, 2),padding='same'))\n    \n    model.add(Conv2D(filters=128, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    \n    model.add(Conv2D(filters=128, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Dropout(0.2))\n    \n    model.add(Conv2D(filters=128, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPooling2D((2, 2),padding='same'))\n    \n    model.add(Conv2D(filters=256, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    \n    model.add(Conv2D(filters=256, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Dropout(0.3))\n    \n    model.add(Conv2D(filters=256, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\n    model.add(Dropout(0.5))\n    \n    model.add(Conv2D(filters=512, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    \n    model.add(Conv2D(filters=512, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Dropout(0.3))\n    \n    model.add(Conv2D(filters=512, kernel_size=(3, 3),strides=(1,1),  padding='same',use_bias=False))\n    model.add(BatchNormalization())\n    model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\n    model.add(Dropout(0.5))\n    \n    model.add(Flatten())\n    \n    #model.add(Dense(units=2048))\n    #model.add(Dense(units=2048))\n    model.add(Dense(units=512, kernel_initializer='he_uniform', kernel_regularizer=l2(0.001)))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Dropout(0.5))\n    \n    model.add(Dense(units=128))\n    #model.add(Dropout(0.5))\n    model.add(Activation('relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(units=10, activation='softmax'))\n    # compile model\n    #opt = SGD(lr=0.001, momentum=0.9,'adam')\n    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n    return model\n\nmodel = define_model()\nprint('Code Segment Running: 1Done')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Save Model","metadata":{}},{"cell_type":"code","source":"model.fit(train_generator,epochs=100, validation_data=valid_generator,steps_per_epoch=train_generator.n//train_generator.batch_size,\n         validation_steps= valid_generator.n//valid_generator.batch_size,workers=8,use_multiprocessing=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nmodel_path = \"/kaggle/temp/model\"\nif not os.path.exists(model_path):\n    os.mkdir(model_path)\nmodel.save(model_path)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow import keras\nmodel = keras.models.load_model(model_path)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Unpack the test dataset\nshutil.unpack_archive('/kaggle/input/cifar-10/test.7z','/kaggle/temp/test')\nshutil.unregister_unpack_format('7zip')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls /kaggle/temp/test/ |wc -l","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Perform preprocessing on test data\ntest_datagen = ImageDataGenerator(featurewise_center=True,\n    featurewise_std_normalization=True,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True,\n    validation_split=0.2)\n\ntest_gen = test_datagen.flow_from_directory(directory='/kaggle/temp/test',target_size=(32,32),batch_size=128,class_mode=None,shuffle=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_gen.reset()\npredictions_vecs = model.predict(test_gen)\n\npredictions_final = np.argmax(predictions_vecs, axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(type(train_generator.class_indices))\nprint(train_generator.class_indices)\n\nclasses = {value:key for (key,value) in train_generator.class_indices.items()}\nprint(classes)\n\npredicted_classes=np.empty(shape=300000,dtype=np.dtype('U20'))\n\nind=0\nfor i in predictions_final.tolist():\n    predicted_classes[ind]=classes[i]\n    ind=ind+1\n    \nfilenames_wo_ext = []\nfor fname in test_gen.filenames:\n    filenames_wo_ext.append(int(fname.split(sep=\"/\")[1].split(sep=\".\")[0])-1)\n\npredicted_classes_final = np.empty(shape=300000,dtype=np.dtype('U20'))\npredicted_classes_final[filenames_wo_ext]=predicted_classes","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('../input/cifar-10/sampleSubmission.csv',header='infer')\nsub.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub['label'] = predicted_classes_final\nsub.to_csv('submission.csv',index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = pd.read_csv('submission.csv')\nprint(data)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predicted_classes_final[1:10]\nmodel.save('model')","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}