{"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","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":0.039452,"end_time":"2022-04-08T02:32:59.542055","exception":false,"start_time":"2022-04-08T02:32:59.502603","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"! pip install py7zr","metadata":{"papermill":{"duration":16.20513,"end_time":"2022-04-08T02:33:15.770947","exception":false,"start_time":"2022-04-08T02:32:59.565817","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd","metadata":{"papermill":{"duration":0.041514,"end_time":"2022-04-08T02:33:15.847206","exception":false,"start_time":"2022-04-08T02:33:15.805692","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from py7zr import unpack_7zarchive\nimport shutil\n\nshutil.register_unpack_format('7zip',['.7z'],unpack_7zarchive)","metadata":{"papermill":{"duration":0.27562,"end_time":"2022-04-08T02:33:16.156701","exception":false,"start_time":"2022-04-08T02:33:15.881081","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#unpack train images to temp directory\nshutil.unpack_archive('/kaggle/input/cifar-10/train.7z','/kaggle/temp/')","metadata":{"papermill":{"duration":41.937342,"end_time":"2022-04-08T02:33:58.12812","exception":false,"start_time":"2022-04-08T02:33:16.190778","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels = pd.read_csv('/kaggle/input/cifar-10/trainLabels.csv', header= 'infer')\n\n#unique labels\nclasses = train_labels['label'].unique()\n\nprint(classes)\n\nimport os\n\nif not os.path.exists(\"/kaggle/temp/validation/\"):\n    os.mkdir(\"/kaggle/temp/validation/\")\n\nparent_path_train = \"/kaggle/temp/train/\"\nparent_path_validation = \"/kaggle/temp/validation/\"\nparent_path_test = \"/kaggle/temp/test/\"\n\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        \n    path_validation = os.path.join(parent_path_validation,class1)\n    if not os.path.exists(path_validation):\n        os.mkdir(path_validation)\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 <= 0.80:\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_validation,row[\"label\"],id)\n        os.replace(source_path,target_path)\n","metadata":{"papermill":{"duration":4.605198,"end_time":"2022-04-08T02:34:02.789544","exception":false,"start_time":"2022-04-08T02:33:58.184346","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\n\nfrom keras import Sequential\nfrom keras.layers import Dense,Conv2D,MaxPooling2D,Activation,BatchNormalization,GlobalAveragePooling2D,Flatten\nfrom keras.utils.np_utils import to_categorical\nfrom keras.callbacks import ReduceLROnPlateau\n\nfrom keras.preprocessing.image import ImageDataGenerator\n","metadata":{"papermill":{"duration":4.478441,"end_time":"2022-04-08T02:34:07.302581","exception":false,"start_time":"2022-04-08T02:34:02.82414","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def my_model():\n    model = Sequential()\n    model.add(Conv2D(filters=32,kernel_size=(3,3),strides=(1,1),padding='valid',activation=None,use_bias=False,input_shape=(32,32,3)))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    \n    model.add(Conv2D(filters=48, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    \n    model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    \n    model.add(Conv2D(filters=80, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    \n    model.add(Conv2D(filters=96, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, 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='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n\n    model.add(Flatten())\n    model.add(Dense(units=10))\n    model.add(BatchNormalization())\n    model.add(Activation('softmax'))\n    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n    return model\n","metadata":{"papermill":{"duration":0.047838,"end_time":"2022-04-08T02:34:07.385783","exception":false,"start_time":"2022-04-08T02:34:07.337945","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = my_model()","metadata":{"papermill":{"duration":2.5347,"end_time":"2022-04-08T02:34:09.954384","exception":false,"start_time":"2022-04-08T02:34:07.419684","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(featurewise_center= False,\n                                  samplewise_center= False,\n                                  featurewise_std_normalization=False,\n                                  samplewise_std_normalization=False,\n                                  zca_whitening=False,\n                                  rotation_range=10,\n                                  zoom_range=0.1,\n                                  width_shift_range=0.1,\n                                  height_shift_range=0.1,\n                                  horizontal_flip=False,\n                                  vertical_flip=False,\n                                  rescale=1./255\n                                  )\n\ntrain_gen = train_datagen.flow_from_directory(directory='/kaggle/temp/train/',target_size=(32,32),batch_size=128)\nvalidation_datagen = ImageDataGenerator(rescale=1./255)\nvalid_gen = validation_datagen.flow_from_directory(directory='/kaggle/temp/validation/',target_size=(32,32),batch_size=128)","metadata":{"papermill":{"duration":2.297649,"end_time":"2022-04-08T02:34:12.287709","exception":false,"start_time":"2022-04-08T02:34:09.99006","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(train_gen,epochs=50,validation_data=valid_gen,steps_per_epoch=train_gen.n//train_gen.batch_size,\n         validation_steps= valid_gen.n//valid_gen.batch_size,workers=8,use_multiprocessing=True)","metadata":{"papermill":{"duration":1820.874263,"end_time":"2022-04-08T03:04:33.230631","exception":false,"start_time":"2022-04-08T02:34:12.356368","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unpack_archive('/kaggle/input/cifar-10/test.7z','/kaggle/temp/test')","metadata":{"papermill":{"duration":864.338802,"end_time":"2022-04-08T03:19:01.2356","exception":false,"start_time":"2022-04-08T03:04:36.896798","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unregister_unpack_format('7zip')","metadata":{"papermill":{"duration":5.404692,"end_time":"2022-04-08T03:19:10.533226","exception":false,"start_time":"2022-04-08T03:19:05.128534","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_datagen = ImageDataGenerator(rescale=1./255)\n\ntest_gen = test_datagen.flow_from_directory(directory='/kaggle/temp/test',target_size=(32,32),batch_size=64,class_mode=None,shuffle=False)","metadata":{"papermill":{"duration":13.332158,"end_time":"2022-04-08T03:19:27.460342","exception":false,"start_time":"2022-04-08T03:19:14.128184","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\n\nos.chdir('/kaggle/temp/test/test')\nprint(os.getcwd())","metadata":{"papermill":{"duration":3.487505,"end_time":"2022-04-08T03:19:34.742365","exception":false,"start_time":"2022-04-08T03:19:31.25486","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_gen.filenames","metadata":{"papermill":{"duration":3.555154,"end_time":"2022-04-08T03:19:41.927932","exception":false,"start_time":"2022-04-08T03:19:38.372778","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions_final = model.predict(test_gen)","metadata":{"papermill":{"duration":87.215959,"end_time":"2022-04-08T03:21:12.668577","exception":false,"start_time":"2022-04-08T03:19:45.452618","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions_final[1]","metadata":{"papermill":{"duration":3.485064,"end_time":"2022-04-08T03:21:19.787481","exception":false,"start_time":"2022-04-08T03:21:16.302417","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(type(train_gen.class_indices))\nprint(train_gen.class_indices)\n\nclasses = {value:key for (key,value) in train_gen.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[np.argmax(i)]\n    ind=ind+1","metadata":{"papermill":{"duration":6.950421,"end_time":"2022-04-08T03:21:30.218877","exception":false,"start_time":"2022-04-08T03:21:23.268456","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predicted_classes[9]","metadata":{"papermill":{"duration":3.518763,"end_time":"2022-04-08T03:21:37.681468","exception":false,"start_time":"2022-04-08T03:21:34.162705","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filenames_wo_ext = []\nfor fname in test_gen.filenames:\n    filenames_wo_ext.append(int(fname.split(sep=\"/\")[-1].split(sep=\".\")[0])-1)\n\n# print(filenames_wo_ext)\n# print(len(predicted_classes))\n\npredicted_classes_final = np.empty(shape=300000,dtype=np.dtype('U20'))\n# for i in range(0,300000) :\n#     predicted_classes_final[i]= predicted_classes[i]\npredicted_classes_final[filenames_wo_ext]=predicted_classes","metadata":{"papermill":{"duration":3.740066,"end_time":"2022-04-08T03:21:45.256715","exception":false,"start_time":"2022-04-08T03:21:41.516649","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predicted_classes_final","metadata":{"papermill":{"duration":3.837596,"end_time":"2022-04-08T03:21:52.568225","exception":false,"start_time":"2022-04-08T03:21:48.730629","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/cifar-10/sampleSubmission.csv',header='infer')\nsub.info()","metadata":{"papermill":{"duration":3.574407,"end_time":"2022-04-08T03:21:59.518485","exception":false,"start_time":"2022-04-08T03:21:55.944078","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub['label'] = predicted_classes_final\nsub.to_csv('/kaggle/working/submission.csv',index=False)","metadata":{"papermill":{"duration":4.54989,"end_time":"2022-04-08T03:22:07.777283","exception":false,"start_time":"2022-04-08T03:22:03.227393","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.head(10)","metadata":{"papermill":{"duration":3.559243,"end_time":"2022-04-08T03:22:14.998607","exception":false,"start_time":"2022-04-08T03:22:11.439364","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]}]}