{"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)\nimport os\nfrom tensorflow import keras\nimport tensorflow as tf\nfrom keras import Sequential\nfrom keras.layers import Dense, Conv2D, MaxPooling2D, Activation, BatchNormalization, Flatten\nfrom keras.utils.np_utils import to_categorical\nfrom keras.preprocessing.image import ImageDataGenerator\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":5.293529,"end_time":"2022-03-22T16:47:20.692893","exception":false,"start_time":"2022-03-22T16:47:15.399364","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:00:14.029735Z","iopub.execute_input":"2022-03-28T09:00:14.030235Z","iopub.status.idle":"2022-03-28T09:00:20.078735Z","shell.execute_reply.started":"2022-03-28T09:00:14.030094Z","shell.execute_reply":"2022-03-28T09:00:20.077755Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install py7zr","metadata":{"papermill":{"duration":12.063587,"end_time":"2022-03-22T16:47:32.773555","exception":false,"start_time":"2022-03-22T16:47:20.709968","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:00:20.079837Z","iopub.execute_input":"2022-03-28T09:00:20.080140Z","iopub.status.idle":"2022-03-28T09:00:38.150955Z","shell.execute_reply.started":"2022-03-28T09:00:20.080109Z","shell.execute_reply":"2022-03-28T09:00:38.149801Z"},"trusted":true},"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":0.174623,"end_time":"2022-03-22T16:47:32.974572","exception":false,"start_time":"2022-03-22T16:47:32.799949","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:00:38.156101Z","iopub.execute_input":"2022-03-28T09:00:38.156403Z","iopub.status.idle":"2022-03-28T09:00:38.345359Z","shell.execute_reply.started":"2022-03-28T09:00:38.156364Z","shell.execute_reply":"2022-03-28T09:00:38.344380Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unpack_archive('../input/cifar-10/train.7z', '/kaggle/temp/')","metadata":{"papermill":{"duration":40.947491,"end_time":"2022-03-22T16:48:13.947518","exception":false,"start_time":"2022-03-22T16:47:33.000027","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:00:38.347853Z","iopub.execute_input":"2022-03-28T09:00:38.348177Z","iopub.status.idle":"2022-03-28T09:01:26.960358Z","shell.execute_reply.started":"2022-03-28T09:00:38.348142Z","shell.execute_reply":"2022-03-28T09:01:26.959387Z"},"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":{"papermill":{"duration":0.075423,"end_time":"2022-03-22T16:48:14.049351","exception":false,"start_time":"2022-03-22T16:48:13.973928","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:01:26.961798Z","iopub.execute_input":"2022-03-28T09:01:26.962121Z","iopub.status.idle":"2022-03-28T09:01:27.032464Z","shell.execute_reply.started":"2022-03-28T09:01:26.962080Z","shell.execute_reply":"2022-03-28T09:01:27.031439Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if 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":{"papermill":{"duration":4.408834,"end_time":"2022-03-22T16:48:18.484450","exception":false,"start_time":"2022-03-22T16:48:14.075616","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:01:27.034223Z","iopub.execute_input":"2022-03-28T09:01:27.034875Z","iopub.status.idle":"2022-03-28T09:01:32.354219Z","shell.execute_reply.started":"2022-03-28T09:01:27.034826Z","shell.execute_reply":"2022-03-28T09:01:32.353187Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls /kaggle/temp/valid\n!ls /kaggle/temp/train","metadata":{"papermill":{"duration":1.354448,"end_time":"2022-03-22T16:48:19.865324","exception":false,"start_time":"2022-03-22T16:48:18.510876","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:01:32.355342Z","iopub.execute_input":"2022-03-28T09:01:32.355599Z","iopub.status.idle":"2022-03-28T09:01:33.798709Z","shell.execute_reply.started":"2022-03-28T09:01:32.355569Z","shell.execute_reply":"2022-03-28T09:01:33.797577Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(filters=32,kernel_size=(3,3),strides=(1,1),padding='valid',activation=None,use_bias=False,input_shape=(32,32,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(filters=48, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(filters=80, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(filters=96, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(filters=128, kernel_size=(3,3), strides=(1,1), padding='valid', activation=None, use_bias=False))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Flatten())\nmodel.add(Dense(units=10))\nmodel.add(BatchNormalization())\nmodel.add(Activation('softmax'))\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n","metadata":{"papermill":{"duration":2.682358,"end_time":"2022-03-22T16:48:22.574648","exception":false,"start_time":"2022-03-22T16:48:19.892290","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:01:33.801838Z","iopub.execute_input":"2022-03-28T09:01:33.802160Z","iopub.status.idle":"2022-03-28T09:01:34.102243Z","shell.execute_reply.started":"2022-03-28T09:01:33.802119Z","shell.execute_reply":"2022-03-28T09:01:34.101433Z"},"trusted":true},"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)\nvalid_datagen = ImageDataGenerator()\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":{"papermill":{"duration":2.142424,"end_time":"2022-03-22T16:48:24.758758","exception":false,"start_time":"2022-03-22T16:48:22.616334","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:01:34.103666Z","iopub.execute_input":"2022-03-28T09:01:34.104000Z","iopub.status.idle":"2022-03-28T09:01:36.164022Z","shell.execute_reply.started":"2022-03-28T09:01:34.103922Z","shell.execute_reply":"2022-03-28T09:01:36.163122Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(train_generator,epochs=10, 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":{"papermill":{"duration":346.614694,"end_time":"2022-03-22T16:54:11.402612","exception":false,"start_time":"2022-03-22T16:48:24.787918","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-03-28T09:01:36.165467Z","iopub.execute_input":"2022-03-28T09:01:36.165966Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unpack_archive('/kaggle/input/cifar-10/test.7z','/kaggle/temp/test')","metadata":{"papermill":{"duration":840.452863,"end_time":"2022-03-22T17:08:12.742978","exception":false,"start_time":"2022-03-22T16:54:12.290115","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unregister_unpack_format('7zip')","metadata":{"papermill":{"duration":0.715726,"end_time":"2022-03-22T17:08:14.155549","exception":false,"start_time":"2022-03-22T17:08:13.439823","status":"completed"},"tags":[],"trusted":true},"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":9.806948,"end_time":"2022-03-22T17:08:24.657991","exception":false,"start_time":"2022-03-22T17:08:14.851043","status":"completed"},"tags":[],"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":{"papermill":{"duration":85.243655,"end_time":"2022-03-22T17:09:51.190863","exception":false,"start_time":"2022-03-22T17:08:25.947208","status":"completed"},"tags":[],"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\n","metadata":{"papermill":{"duration":1.223995,"end_time":"2022-03-22T17:09:53.116025","exception":false,"start_time":"2022-03-22T17:09:51.892030","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('../input/cifar-10/sampleSubmission.csv',header='infer')\nsub.info()","metadata":{"papermill":{"duration":0.847595,"end_time":"2022-03-22T17:09:54.677979","exception":false,"start_time":"2022-03-22T17:09:53.830384","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub['label'] = predicted_classes_final\nsub.to_csv('submission.csv',index=False)","metadata":{"papermill":{"duration":1.248443,"end_time":"2022-03-22T17:09:56.638946","exception":false,"start_time":"2022-03-22T17:09:55.390503","status":"completed"},"tags":[],"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.70802,"end_time":"2022-03-22T17:09:58.051414","exception":false,"start_time":"2022-03-22T17:09:57.343394","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]}]}