{"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)\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Activation, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D\nfrom tensorflow.keras.layers import BatchNormalization\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":"2022-08-31T05:59:27.271303Z","iopub.execute_input":"2022-08-31T05:59:27.271751Z","iopub.status.idle":"2022-08-31T05:59:32.609342Z","shell.execute_reply.started":"2022-08-31T05:59:27.271635Z","shell.execute_reply":"2022-08-31T05:59:32.608056Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install py7zr","metadata":{"execution":{"iopub.status.busy":"2022-08-31T05:59:43.920401Z","iopub.execute_input":"2022-08-31T05:59:43.921103Z","iopub.status.idle":"2022-08-31T05:59:58.494319Z","shell.execute_reply.started":"2022-08-31T05:59:43.921066Z","shell.execute_reply":"2022-08-31T05:59:58.493142Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from py7zr import unpack_7zarchive\nimport shutil","metadata":{"execution":{"iopub.status.busy":"2022-08-31T06:00:04.721479Z","iopub.execute_input":"2022-08-31T06:00:04.722163Z","iopub.status.idle":"2022-08-31T06:00:04.726520Z","shell.execute_reply.started":"2022-08-31T06:00:04.722126Z","shell.execute_reply":"2022-08-31T06:00:04.725548Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.register_unpack_format('7zip',['.7z'],unpack_7zarchive)\nshutil.unpack_archive('/kaggle/input/cifar-10/train.7z', '/kaggle/temp/')","metadata":{"execution":{"iopub.status.busy":"2022-08-31T06:00:08.095043Z","iopub.execute_input":"2022-08-31T06:00:08.095403Z","iopub.status.idle":"2022-08-31T06:00:53.956076Z","shell.execute_reply.started":"2022-08-31T06:00:08.095372Z","shell.execute_reply":"2022-08-31T06:00:53.954804Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels = pd.read_csv('/kaggle/input/cifar-10/trainLabels.csv',) \nclasses = train_labels['label'].unique()\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)\n","metadata":{"execution":{"iopub.status.busy":"2022-08-31T06:00:56.883869Z","iopub.execute_input":"2022-08-31T06:00:56.885972Z","iopub.status.idle":"2022-08-31T06:01:06.256527Z","shell.execute_reply.started":"2022-08-31T06:00:56.885923Z","shell.execute_reply":"2022-08-31T06:01:06.255258Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(64, kernel_size=(3, 3),activation='relu',input_shape=(32,32,3),padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64, kernel_size=(3, 3),activation='relu',padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D((2, 2),padding='same'))\n\nmodel.add(Conv2D(128, (3, 3), activation='relu',padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128, (3, 3), activation='relu',padding='same'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\n\nmodel.add(Conv2D(256, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(Conv2D(256, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(Conv2D(256, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\n\nmodel.add(Conv2D(512, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(Conv2D(512, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(Conv2D(512, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\n\nmodel.add(Conv2D(512, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(Conv2D(512, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(Conv2D(512, (3, 3), activation='relu',padding='same')) \nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\n\nmodel.add(Flatten())\nmodel.add(Dense(4096, activation='relu')) \nmodel.add(Dense(4096, activation='relu'))\nmodel.add(Dense(1000, activation='relu'))\nmodel.add(Dense(10, activation='softmax'))\n\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2022-08-31T06:01:09.349831Z","iopub.execute_input":"2022-08-31T06:01:09.352272Z","iopub.status.idle":"2022-08-31T06:01:12.679587Z","shell.execute_reply.started":"2022-08-31T06:01:09.352235Z","shell.execute_reply":"2022-08-31T06:01:12.678554Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\ntrain_datagen = ImageDataGenerator()\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":"2022-08-31T06:50:50.404718Z","iopub.execute_input":"2022-08-31T06:50:50.405422Z","iopub.status.idle":"2022-08-31T06:50:51.522431Z","shell.execute_reply.started":"2022-08-31T06:50:50.405385Z","shell.execute_reply":"2022-08-31T06:50:51.521307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(train_generator,epochs=30, 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":"2022-08-31T06:50:59.062219Z","iopub.execute_input":"2022-08-31T06:50:59.063099Z","iopub.status.idle":"2022-08-31T07:01:04.786844Z","shell.execute_reply.started":"2022-08-31T06:50:59.063056Z","shell.execute_reply":"2022-08-31T07:01:04.781758Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.models import load_model\nmodel.save('/kaggle/working/vgg16_model4_noaug_30epoch.h5')\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2022-08-31T07:01:15.410286Z","iopub.execute_input":"2022-08-31T07:01:15.410713Z","iopub.status.idle":"2022-08-31T07:01:16.524004Z","shell.execute_reply.started":"2022-08-31T07:01:15.410652Z","shell.execute_reply":"2022-08-31T07:01:16.522917Z"},"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":"2022-08-31T06:08:20.756999Z","iopub.execute_input":"2022-08-31T06:08:20.757379Z","iopub.status.idle":"2022-08-31T06:23:06.686069Z","shell.execute_reply.started":"2022-08-31T06:08:20.757345Z","shell.execute_reply":"2022-08-31T06:23:06.684791Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_datagen = ImageDataGenerator()\n\ntest_gen = test_datagen.flow_from_directory(directory='/kaggle/temp/test',target_size=(32,32),batch_size=64,class_mode=None,shuffle=False)\n\ntest_gen.reset()\nmy_model = load_model('/kaggle/working/vgg16_model4_noaug_30epoch.h5')\npredictions_vecs = my_model.predict(test_gen)\npredictions_final = np.argmax(predictions_vecs, axis=1)\n\nclasses = {value:key for (key,value) in train_generator.class_indices.items()}\nprint(classes)\npredicted_classes=np.empty(shape=300000,dtype=np.dtype('U20'))\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\n\nsub = pd.read_csv('../input/cifar-10/sampleSubmission.csv',header='infer')\nsub['label'] = predicted_classes_final\nsub.to_csv('submission.csv',index=False)\n\nsubmission = pd.read_csv('submission.csv')\nprint(submission)","metadata":{"execution":{"iopub.status.busy":"2022-08-31T07:01:26.205825Z","iopub.execute_input":"2022-08-31T07:01:26.206182Z","iopub.status.idle":"2022-08-31T07:02:45.650325Z","shell.execute_reply.started":"2022-08-31T07:01:26.206153Z","shell.execute_reply":"2022-08-31T07:02:45.649319Z"},"trusted":true},"execution_count":null,"outputs":[]}]}