{"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-03-25T00:25:23.966490Z","iopub.execute_input":"2022-03-25T00:25:23.967031Z","iopub.status.idle":"2022-03-25T00:25:23.977315Z","shell.execute_reply.started":"2022-03-25T00:25:23.966992Z","shell.execute_reply":"2022-03-25T00:25:23.975119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install py7zr","metadata":{"execution":{"iopub.status.busy":"2022-03-25T00:25:23.981569Z","iopub.execute_input":"2022-03-25T00:25:23.981948Z","iopub.status.idle":"2022-03-25T00:25:35.175939Z","shell.execute_reply.started":"2022-03-25T00:25:23.981915Z","shell.execute_reply":"2022-03-25T00:25:35.175095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.layers import BatchNormalization\nfrom tensorflow.keras.regularizers import l2\nfrom tensorflow.keras.layers import Dense, Dropout, Activation,Flatten,Conv2D,MaxPooling2D\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.datasets import cifar10 \nimport warnings\nwarnings.filterwarnings('ignore')\n\ntf.__version__","metadata":{"execution":{"iopub.status.busy":"2022-03-25T00:25:35.179786Z","iopub.execute_input":"2022-03-25T00:25:35.180018Z","iopub.status.idle":"2022-03-25T00:25:40.766281Z","shell.execute_reply.started":"2022-03-25T00:25:35.179992Z","shell.execute_reply":"2022-03-25T00:25:40.765557Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from py7zr import unpack_7zarchive\nimport shutil\nshutil.register_unpack_format('7zip',['.7z'],unpack_7zarchive)","metadata":{"execution":{"iopub.status.busy":"2022-03-25T00:25:40.767700Z","iopub.execute_input":"2022-03-25T00:25:40.767954Z","iopub.status.idle":"2022-03-25T00:25:40.909618Z","shell.execute_reply.started":"2022-03-25T00:25:40.767920Z","shell.execute_reply":"2022-03-25T00:25:40.908848Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unpack_archive('../input/cifar-10/train.7z', '/kaggle/temp/')","metadata":{"execution":{"iopub.status.busy":"2022-03-25T00:25:40.911552Z","iopub.execute_input":"2022-03-25T00:25:40.911891Z","iopub.status.idle":"2022-03-25T00:26:22.790445Z","shell.execute_reply.started":"2022-03-25T00:25:40.911854Z","shell.execute_reply":"2022-03-25T00:26:22.789686Z"},"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":{"execution":{"iopub.status.busy":"2022-03-25T00:26:22.791908Z","iopub.execute_input":"2022-03-25T00:26:22.792165Z","iopub.status.idle":"2022-03-25T00:26:22.857321Z","shell.execute_reply.started":"2022-03-25T00:26:22.792131Z","shell.execute_reply":"2022-03-25T00:26:22.855468Z"},"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":{"execution":{"iopub.status.busy":"2022-03-25T00:26:22.860084Z","iopub.execute_input":"2022-03-25T00:26:22.862522Z","iopub.status.idle":"2022-03-25T00:26:28.086158Z","shell.execute_reply.started":"2022-03-25T00:26:22.862481Z","shell.execute_reply":"2022-03-25T00:26:28.084626Z"},"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'])","metadata":{"execution":{"iopub.status.busy":"2022-03-25T00:26:28.087430Z","iopub.execute_input":"2022-03-25T00:26:28.087696Z","iopub.status.idle":"2022-03-25T00:26:31.210276Z","shell.execute_reply.started":"2022-03-25T00:26:28.087661Z","shell.execute_reply":"2022-03-25T00:26:31.209242Z"},"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":{"execution":{"iopub.status.busy":"2022-03-25T00:26:31.211757Z","iopub.execute_input":"2022-03-25T00:26:31.211993Z","iopub.status.idle":"2022-03-25T00:26:33.050297Z","shell.execute_reply.started":"2022-03-25T00:26:31.211958Z","shell.execute_reply":"2022-03-25T00:26:33.049392Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(train_generator,epochs=50, 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":{"execution":{"iopub.status.busy":"2022-03-25T00:26:33.055135Z","iopub.execute_input":"2022-03-25T00:26:33.057562Z","iopub.status.idle":"2022-03-25T00:56:02.705662Z","shell.execute_reply.started":"2022-03-25T00:26:33.057521Z","shell.execute_reply":"2022-03-25T00:56:02.704658Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unpack_archive('/kaggle/input/cifar-10/test.7z','/kaggle/temp/test')\nshutil.unregister_unpack_format('7zip')","metadata":{"execution":{"iopub.status.busy":"2022-03-25T00:58:40.803858Z","iopub.execute_input":"2022-03-25T00:58:40.804134Z","iopub.status.idle":"2022-03-25T01:12:46.017670Z","shell.execute_reply.started":"2022-03-25T00:58:40.804105Z","shell.execute_reply":"2022-03-25T01:12:46.016576Z"},"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":{"execution":{"iopub.status.busy":"2022-03-25T01:12:46.019307Z","iopub.execute_input":"2022-03-25T01:12:46.019709Z","iopub.status.idle":"2022-03-25T01:12:53.548166Z","shell.execute_reply.started":"2022-03-25T01:12:46.019672Z","shell.execute_reply":"2022-03-25T01:12:53.547144Z"},"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":{"execution":{"iopub.status.busy":"2022-03-25T01:14:30.081974Z","iopub.execute_input":"2022-03-25T01:14:30.082712Z","iopub.status.idle":"2022-03-25T01:15:53.235356Z","shell.execute_reply.started":"2022-03-25T01:14:30.082669Z","shell.execute_reply":"2022-03-25T01:15:53.234555Z"},"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":{"execution":{"iopub.status.busy":"2022-03-25T01:15:53.237098Z","iopub.execute_input":"2022-03-25T01:15:53.237354Z","iopub.status.idle":"2022-03-25T01:15:53.709691Z","shell.execute_reply.started":"2022-03-25T01:15:53.237320Z","shell.execute_reply":"2022-03-25T01:15:53.708936Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('../input/cifar-10/sampleSubmission.csv',header='infer')\nsub.info()\n","metadata":{"execution":{"iopub.status.busy":"2022-03-25T01:15:53.710974Z","iopub.execute_input":"2022-03-25T01:15:53.711200Z","iopub.status.idle":"2022-03-25T01:15:53.872421Z","shell.execute_reply.started":"2022-03-25T01:15:53.711169Z","shell.execute_reply":"2022-03-25T01:15:53.871696Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub['label'] = predicted_classes_final\nsub.to_csv('submission.csv',index=False)","metadata":{"execution":{"iopub.status.busy":"2022-03-25T01:15:53.874079Z","iopub.execute_input":"2022-03-25T01:15:53.874293Z","iopub.status.idle":"2022-03-25T01:15:54.397147Z","shell.execute_reply.started":"2022-03-25T01:15:53.874251Z","shell.execute_reply":"2022-03-25T01:15:54.396446Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub","metadata":{"execution":{"iopub.status.busy":"2022-03-25T01:20:41.680682Z","iopub.execute_input":"2022-03-25T01:20:41.681361Z","iopub.status.idle":"2022-03-25T01:20:41.697116Z","shell.execute_reply.started":"2022-03-25T01:20:41.681324Z","shell.execute_reply":"2022-03-25T01:20:41.695977Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}