{"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":"import 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 , Model\nfrom keras.layers import Dense, Conv2D, MaxPooling2D, Activation, BatchNormalization, Flatten, Dropout\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))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-08-26T21:04:47.323558Z","iopub.execute_input":"2022-08-26T21:04:47.323935Z","iopub.status.idle":"2022-08-26T21:04:52.512865Z","shell.execute_reply.started":"2022-08-26T21:04:47.323904Z","shell.execute_reply":"2022-08-26T21:04:52.511186Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install py7zr","metadata":{"execution":{"iopub.status.busy":"2022-08-26T21:11:51.636433Z","iopub.execute_input":"2022-08-26T21:11:51.637416Z","iopub.status.idle":"2022-08-26T21:12:05.933089Z","shell.execute_reply.started":"2022-08-26T21:11:51.637379Z","shell.execute_reply":"2022-08-26T21:12:05.931858Z"},"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":{"execution":{"iopub.status.busy":"2022-08-26T21:12:15.981247Z","iopub.execute_input":"2022-08-26T21:12:15.981990Z","iopub.status.idle":"2022-08-26T21:12:16.333404Z","shell.execute_reply.started":"2022-08-26T21:12:15.981951Z","shell.execute_reply":"2022-08-26T21:12:16.332466Z"},"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":"2022-08-26T21:12:19.849872Z","iopub.execute_input":"2022-08-26T21:12:19.850241Z","iopub.status.idle":"2022-08-26T21:13:09.607455Z","shell.execute_reply.started":"2022-08-26T21:12:19.850196Z","shell.execute_reply":"2022-08-26T21:13:09.606207Z"},"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":"2022-08-26T21:15:47.702126Z","iopub.execute_input":"2022-08-26T21:15:47.702926Z","iopub.status.idle":"2022-08-26T21:15:47.745685Z","shell.execute_reply.started":"2022-08-26T21:15:47.702887Z","shell.execute_reply":"2022-08-26T21:15:47.744645Z"},"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":"2022-08-26T21:15:53.619278Z","iopub.execute_input":"2022-08-26T21:15:53.620202Z","iopub.status.idle":"2022-08-26T21:15:58.303358Z","shell.execute_reply.started":"2022-08-26T21:15:53.620167Z","shell.execute_reply":"2022-08-26T21:15:58.302259Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls /kaggle/temp/valid\n!ls /kaggle/temp/train","metadata":{"execution":{"iopub.status.busy":"2022-08-26T21:16:06.043127Z","iopub.execute_input":"2022-08-26T21:16:06.043720Z","iopub.status.idle":"2022-08-26T21:16:08.017836Z","shell.execute_reply.started":"2022-08-26T21:16:06.043673Z","shell.execute_reply":"2022-08-26T21:16:08.016643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, (3,3), padding='same', input_shape=(32,32,3)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32, (3,3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.2))\n\nmodel.add(Conv2D(2*32, (3,3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(2*32, (3,3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.3))\n\nmodel.add(Conv2D(4*32, (3,3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(4*32, (3,3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.4))\n\nmodel.add(Conv2D(6*32, (3,3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(6*32, (3,3), padding='same'))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.4))\n\nmodel.add(Flatten())\nmodel.add(Dense(10, activation='softmax'))\n\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2022-08-26T21:17:54.136642Z","iopub.execute_input":"2022-08-26T21:17:54.137025Z","iopub.status.idle":"2022-08-26T21:17:54.340656Z","shell.execute_reply.started":"2022-08-26T21:17:54.136993Z","shell.execute_reply":"2022-08-26T21:17:54.339616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.optimizers import Adam\nopt = Adam(learning_rate=1.0e-4)","metadata":{"execution":{"iopub.status.busy":"2022-08-26T21:21:08.534928Z","iopub.execute_input":"2022-08-26T21:21:08.535347Z","iopub.status.idle":"2022-08-26T21:21:08.541940Z","shell.execute_reply.started":"2022-08-26T21:21:08.535316Z","shell.execute_reply":"2022-08-26T21:21:08.540802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer= opt , metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2022-08-26T21:21:13.780334Z","iopub.execute_input":"2022-08-26T21:21:13.781062Z","iopub.status.idle":"2022-08-26T21:21:13.797178Z","shell.execute_reply.started":"2022-08-26T21:21:13.781025Z","shell.execute_reply":"2022-08-26T21:21:13.796176Z"},"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":"2022-08-26T21:21:22.826595Z","iopub.execute_input":"2022-08-26T21:21:22.827335Z","iopub.status.idle":"2022-08-26T21:21:23.850041Z","shell.execute_reply.started":"2022-08-26T21:21:22.827298Z","shell.execute_reply":"2022-08-26T21:21:23.848928Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2022-08-27T00:22:27.495186Z","iopub.execute_input":"2022-08-27T00:22:27.496141Z","iopub.status.idle":"2022-08-27T01:22:41.613582Z","shell.execute_reply.started":"2022-08-27T00:22:27.496102Z","shell.execute_reply":"2022-08-27T01:22:41.612398Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unpack_archive('/kaggle/input/cifar-10/test.7z','/kaggle/temp/test')","metadata":{"execution":{"iopub.status.busy":"2022-08-27T01:26:08.000373Z","iopub.execute_input":"2022-08-27T01:26:08.001046Z","iopub.status.idle":"2022-08-27T01:40:48.638266Z","shell.execute_reply.started":"2022-08-27T01:26:08.001008Z","shell.execute_reply":"2022-08-27T01:40:48.637279Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.unregister_unpack_format('7zip')","metadata":{"execution":{"iopub.status.busy":"2022-08-27T01:41:09.541537Z","iopub.execute_input":"2022-08-27T01:41:09.541886Z","iopub.status.idle":"2022-08-27T01:41:09.546736Z","shell.execute_reply.started":"2022-08-27T01:41:09.541856Z","shell.execute_reply":"2022-08-27T01:41:09.545700Z"},"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":"2022-08-27T01:41:13.304512Z","iopub.execute_input":"2022-08-27T01:41:13.304864Z","iopub.status.idle":"2022-08-27T01:41:19.848996Z","shell.execute_reply.started":"2022-08-27T01:41:13.304837Z","shell.execute_reply":"2022-08-27T01:41:19.848049Z"},"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":"2022-08-27T01:41:23.745904Z","iopub.execute_input":"2022-08-27T01:41:23.746292Z","iopub.status.idle":"2022-08-27T01:42:48.605658Z","shell.execute_reply.started":"2022-08-27T01:41:23.746258Z","shell.execute_reply":"2022-08-27T01:42:48.604650Z"},"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":"2022-08-27T01:42:53.017904Z","iopub.execute_input":"2022-08-27T01:42:53.018431Z","iopub.status.idle":"2022-08-27T01:42:53.385862Z","shell.execute_reply.started":"2022-08-27T01:42:53.018395Z","shell.execute_reply":"2022-08-27T01:42:53.384883Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('../input/cifar-10/sampleSubmission.csv',header='infer')\nsub.info()","metadata":{"execution":{"iopub.status.busy":"2022-08-27T01:43:00.395786Z","iopub.execute_input":"2022-08-27T01:43:00.396275Z","iopub.status.idle":"2022-08-27T01:43:00.566509Z","shell.execute_reply.started":"2022-08-27T01:43:00.396197Z","shell.execute_reply":"2022-08-27T01:43:00.565533Z"},"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":"2022-08-27T01:43:05.433601Z","iopub.execute_input":"2022-08-27T01:43:05.434180Z","iopub.status.idle":"2022-08-27T01:43:05.755132Z","shell.execute_reply.started":"2022-08-27T01:43:05.434137Z","shell.execute_reply":"2022-08-27T01:43:05.754169Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.save('model.h5')","metadata":{"execution":{"iopub.status.busy":"2022-08-27T01:43:10.101019Z","iopub.execute_input":"2022-08-27T01:43:10.101405Z","iopub.status.idle":"2022-08-27T01:43:10.209911Z","shell.execute_reply.started":"2022-08-27T01:43:10.101373Z","shell.execute_reply":"2022-08-27T01:43:10.208913Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}