Merge branch 'code' of http://khuhub.khu.ac.kr/2020-1-capstone-design2/2014103189 into report

+.vscode/
+__pycache__/
+trained/
+src/

+from keras.models import Model
+
+from keras.layers import Input, Reshape
+from keras.layers.core import Dense, Lambda, Activation
+from keras.layers.convolutional import Conv2D
+from keras.layers.pooling import GlobalAveragePooling2D, MaxPooling2D
+from keras.layers.merge import concatenate, add, multiply
+from keras.layers.normalization import BatchNormalization
+
+from keras.regularizers import l2
+from keras.utils.data_utils import get_file
+from keras_applications.imagenet_utils import _obtain_input_shape
+
+import keras.backend as K
+
+import os
+
+
+class SEResNeXt(Model):
+    def __init__(self, weight, input_shape=None):
+        '''
+            ResNext Model
+
+            ## Args
+            + weight: 
+            + input_shape: optional shape tuple
+        '''
+
+        if weights not in {'cifar10', 'imagenet'}:
+            raise ValueError
+
+        self.__weight = weight
+
+        if weight == 'cifar10':
+            self.__depth = 29
+            self.__cardinality = 8
+            self.__width = 64
+            self.__classes = 10
+        else:
+            self.__depth = [3, 8, 36, 3]
+            self.__cardinality = 32
+            self.__width = 4
+            self.__classes = 1000
+
+        self.__reduction_ratio = 4
+        self.__weight_decay = 5e-4
+        self.__channel_axis = 1 if K.image_data_format() == "channels_first" else -1
+
+        if weight == 'cifar10':
+            self.__input_shape = _obtain_input_shape(input_shape, default_size=32, min_size=8, data_format=K.image_data_format(), require_flatten=True)
+        else:
+            self.__input_shape = _obtain_input_shape(input_shape, default_size=224, min_size=112, data_format=K.image_data_format(), require_flatten=True)
+        self.__img_input = Input(shape=self.__input_shape)
+
+        # Create model.
+        super(SEResNeXt, self).__init__(self.__img_input, self.__create_res_next(), name='seresnext')
+
+    def __initial_conv_block(self):
+        '''
+            Adds an initial conv block, with batch norm and relu for the inception resnext
+        '''
+        if weight == 'cifar10':
+            x = Conv2D(64, (3, 3), padding='same', use_bias=False, kernel_initializer='he_normal', kernel_regularizer=l2(self.__weight_decay))(self.__img_input)
+            x = BatchNormalization(axis=self.__channel_axis)(x)
+            x = Activation('relu')(x)
+            return x
+        else:
+            x = Conv2D(64, (7, 7), padding='same', use_bias=False, kernel_initializer='he_normal', kernel_regularizer=l2(self.__weight_decay), strides=(2, 2))(self.__img_input)
+            x = BatchNormalization(axis=self.__channel_axis)(x)
+            x = Activation('relu')(x)
+            x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
+            return x
+
+    def __grouped_convolution_block(self, input, grouped_channels, strides):
+        ''' 
+            Adds a grouped convolution block. It is an equivalent block from the paper
+
+            ## Args
+            + input: input tensor
+            + grouped_channels: grouped number of filters
+            + strides: performs strided convolution for downscaling if > 1
+
+            ## Returns
+            a keras tensor
+        '''
+        init = input
+
+        group_list = []
+        for c in range(self.__cardinality):
+            x = Lambda(lambda z: z[:, :, :, c * grouped_channels:(c + 1) * grouped_channels])(input)
+            x = Conv2D(grouped_channels, (3, 3), padding='same', use_bias=False, strides=(strides, strides), kernel_initializer='he_normal', kernel_regularizer=l2(self.__weight_decay))(x)
+            group_list.append(x)
+
+        group_merge = concatenate(group_list, axis=self.__channel_axis)
+        x = BatchNormalization(axis=self.__channel_axis)(group_merge)
+        x = Activation('relu')(x)
+
+        return x
+
+    def __bottleneck_block(self, input, filters=64, strides=1):
+        '''
+            Adds a bottleneck block
+            
+            ## Args
+            + input: input tensor
+            + filters: number of output filters
+            + strides: performs strided convolution for downsampling if > 1
+
+            ## Returns
+            a keras tensor
+        '''
+        init = input
+
+        grouped_channels = int(filters / self.__cardinality)
+
+        # Check if input number of filters is same as 16 * k, else create convolution2d for this input
+        if init._keras_shape[-1] != 2 * filters:
+            init = Conv2D(filters * 2, (1, 1), padding='same', strides=(strides, strides), use_bias=False, kernel_initializer='he_normal', kernel_regularizer=l2(self.__weight_decay))(init)
+            init = BatchNormalization(axis=self.__channel_axis)(init)
+
+        x = Conv2D(filters, (1, 1), padding='same', use_bias=False, kernel_initializer='he_normal', kernel_regularizer=l2(self.__weight_decay))(input)
+        x = BatchNormalization(axis=self.__channel_axis)(x)
+        x = Activation('relu')(x)
+        x = self.__squeeze_excitation_layer(x, x[0].get_shape()[self.__channel_axis])
+
+        x = self.__grouped_convolution_block(x, grouped_channels, strides)
+
+        x = Conv2D(filters * 2, (1, 1), padding='same', use_bias=False, kernel_initializer='he_normal', kernel_regularizer=l2(self.__weight_decay))(x)
+        x = BatchNormalization(axis=self.__channel_axis)(x)
+
+        x = add([init, x])
+        x = Activation('relu')(x)
+
+        return x
+
+    def __create_res_next(self):
+        ''' 
+            Creates a ResNeXt model with specified parameters
+        '''
+        if type(self.__depth) is list or type(self.__depth) is tuple:
+            N = list(self.__depth)
+        else:
+            N = [(self.__depth - 2) // 9 for _ in range(3)]
+        print(N)
+        
+        filters = self.__cardinality * self.__width
+        filters_list = []
+        for i in range(len(N)):
+            filters_list.append(filters)
+            filters *= 2  # double the size of the filters
+
+        x = self.__initial_conv_block()
+
+        # block 1 (no pooling)
+        for i in range(N[0]):
+            x = self.__bottleneck_block(x, filters_list[0], strides=1)
+
+        N = N[1:]  # remove the first block from block definition list
+        filters_list = filters_list[1:]  # remove the first filter from the filter list
+
+        # block 2 to N
+        for block_idx, n_i in enumerate(N):
+            for i in range(n_i):
+                if i == 0:
+                    x = self.__bottleneck_block(x, filters_list[block_idx], strides=2)
+                else:
+                    x = self.__bottleneck_block(x, filters_list[block_idx], strides=1)
+
+        
+        x = GlobalAveragePooling2D()(x)
+        x = Dense(self.__classes, use_bias=False, kernel_regularizer=l2(self.__weight_decay), kernel_initializer='he_normal', activation='softmax')(x)
+        
+        return x
+
+    def __squeeze_excitation_layer(self, x, out_dim):
+        '''
+            SE Block Function
+
+            ## Args
+            + x : input feature map
+            + out_dim : dimention of output channel
+        '''
+        squeeze = GlobalAveragePooling2D()(x)
+        
+        excitation = Dense(units=out_dim // self.__reduction_ratio)(squeeze)
+        excitation = Activation('relu')(excitation)
+        excitation = Dense(units=out_dim)(excitation)
+        excitation = Activation('sigmoid')(excitation)
+        excitation = Reshape((1,1,out_dim))(excitation)
+        
+        scale = multiply([x,excitation])
+        
+        return scale
+
+
+if __name__ == '__main__':
+    model = SEResNeXt((112, 112, 3))
+    model.summary()

+alabaster==0.7.12
+anaconda-client==1.7.2
+anaconda-navigator==1.9.12
+anaconda-project==0.8.3
+argh==0.26.2
+asn1crypto==1.3.0
+astroid==2.3.3
+astropy==4.0
+atomicwrites==1.3.0
+attrs==19.3.0
+autopep8==1.4.4
+Babel==2.8.0
+backcall==0.1.0
+backports.functools-lru-cache==1.6.1
+backports.shutil-get-terminal-size==1.0.0
+backports.tempfile==1.0
+backports.weakref==1.0.post1
+beautifulsoup4==4.8.2
+bitarray==1.2.1
+bkcharts==0.2
+bleach==3.1.0
+bokeh==1.4.0
+boto==2.49.0
+Bottleneck==1.3.2
+certifi==2019.11.28
+cffi==1.14.0
+chardet==3.0.4
+Click==7.0
+cloudpickle==1.3.0
+clyent==1.2.2
+colorama==0.4.3
+conda==4.8.3
+conda-build==3.18.11
+conda-package-handling==1.7.0
+conda-verify==3.4.2
+contextlib2==0.6.0.post1
+cryptography==2.8
+cycler==0.10.0
+Cython==0.29.15
+cytoolz==0.10.1
+dask==2.11.0
+decorator==4.4.1
+defusedxml==0.6.0
+diff-match-patch==20181111
+distributed==2.11.0
+docutils==0.16
+entrypoints==0.3
+et-xmlfile==1.0.1
+fastcache==1.1.0
+filelock==3.0.12
+flake8==3.7.9
+Flask==1.1.1
+fsspec==0.6.2
+future==0.18.2
+gevent==1.4.0
+glob2==0.7
+gmpy2==2.0.8
+greenlet==0.4.15
+h5py==2.10.0
+HeapDict==1.0.1
+html5lib==1.0.1
+hypothesis==5.5.4
+idna==2.8
+imageio==2.6.1
+imagesize==1.2.0
+importlib-metadata==1.5.0
+intervaltree==3.0.2
+ipykernel==5.1.4
+ipython==7.12.0
+ipython-genutils==0.2.0
+ipywidgets==7.5.1
+isort==4.3.21
+itsdangerous==1.1.0
+jdcal==1.4.1
+jedi==0.14.1
+jeepney==0.4.2
+Jinja2==2.11.1
+joblib==0.14.1
+json5==0.9.1
+jsonschema==3.2.0
+jupyter==1.0.0
+jupyter-client==5.3.4
+jupyter-console==6.1.0
+jupyter-core==4.6.1
+jupyterlab==1.2.6
+jupyterlab-server==1.0.6
+keyring==21.1.0
+kiwisolver==1.1.0
+lazy-object-proxy==1.4.3
+libarchive-c==2.8
+lief==0.9.0
+llvmlite==0.31.0
+locket==0.2.0
+lxml==4.5.0
+MarkupSafe==1.1.1
+matplotlib==3.1.3
+mccabe==0.6.1
+mistune==0.8.4
+mkl-fft==1.0.15
+mkl-random==1.1.0
+mkl-service==2.3.0
+mock==4.0.1
+more-itertools==8.2.0
+mpmath==1.1.0
+msgpack==0.6.1
+multipledispatch==0.6.0
+navigator-updater==0.2.1
+nbconvert==5.6.1
+nbformat==5.0.4
+networkx==2.4
+nltk==3.4.5
+nose==1.3.7
+notebook==6.0.3
+numba==0.48.0
+numexpr==2.7.1
+numpy==1.18.1
+numpydoc==0.9.2
+olefile==0.46
+openpyxl==3.0.3
+packaging==20.1
+pandas==1.0.1
+pandocfilters==1.4.2
+parso==0.5.2
+partd==1.1.0
+path==13.1.0
+pathlib2==2.3.5
+pathtools==0.1.2
+patsy==0.5.1
+pep8==1.7.1
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==7.0.0
+pkginfo==1.5.0.1
+pluggy==0.13.1
+ply==3.11
+prometheus-client==0.7.1
+prompt-toolkit==3.0.3
+psutil==5.6.7
+ptyprocess==0.6.0
+py==1.8.1
+pycodestyle==2.5.0
+pycosat==0.6.3
+pycparser==2.19
+pycrypto==2.6.1
+pycurl==7.43.0.5
+pydocstyle==4.0.1
+pyflakes==2.1.1
+Pygments==2.5.2
+pylint==2.4.4
+pyodbc===4.0.0-unsupported
+pyOpenSSL==19.1.0
+pyparsing==2.4.6
+pyrsistent==0.15.7
+PySocks==1.7.1
+pytest==5.3.5
+pytest-arraydiff==0.3
+pytest-astropy==0.8.0
+pytest-astropy-header==0.1.2
+pytest-doctestplus==0.5.0
+pytest-openfiles==0.4.0
+pytest-remotedata==0.3.2
+python-dateutil==2.8.1
+python-jsonrpc-server==0.3.4
+python-language-server==0.31.7
+pytz==2019.3
+PyWavelets==1.1.1
+pyxdg==0.26
+PyYAML==5.3
+pyzmq==18.1.1
+QDarkStyle==2.8
+QtAwesome==0.6.1
+qtconsole==4.6.0
+QtPy==1.9.0
+requests==2.22.0
+rope==0.16.0
+Rtree==0.9.3
+ruamel-yaml==0.15.87
+scikit-image==0.16.2
+scikit-learn==0.22.1
+scipy==1.4.1
+seaborn==0.10.0
+SecretStorage==3.1.2
+Send2Trash==1.5.0
+simplegeneric==0.8.1
+singledispatch==3.4.0.3
+six==1.14.0
+snowballstemmer==2.0.0
+sortedcollections==1.1.2
+sortedcontainers==2.1.0
+soupsieve==1.9.5
+Sphinx==2.4.0
+sphinxcontrib-applehelp==1.0.1
+sphinxcontrib-devhelp==1.0.1
+sphinxcontrib-htmlhelp==1.0.2
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==1.0.2
+sphinxcontrib-serializinghtml==1.1.3
+sphinxcontrib-websupport==1.2.0
+spyder==4.0.1
+spyder-kernels==1.8.1
+SQLAlchemy==1.3.13
+statsmodels==0.11.0
+sympy==1.5.1
+tables==3.6.1
+tblib==1.6.0
+terminado==0.8.3
+testpath==0.4.4
+toolz==0.10.0
+tornado==6.0.3
+tqdm==4.42.1
+traitlets==4.3.3
+ujson==1.35
+unicodecsv==0.14.1
+urllib3==1.25.8
+watchdog==0.10.2
+wcwidth==0.1.8
+webencodings==0.5.1
+Werkzeug==1.0.0
+widgetsnbextension==3.5.1
+wrapt==1.11.2
+wurlitzer==2.0.0
+xlrd==1.2.0
+XlsxWriter==1.2.7
+xlwt==1.3.0
+xmltodict==0.12.0
+yapf==0.28.0
+zict==1.0.0
+zipp==2.2.0

+from keras.models import load_model
+from keras.datasets import fashion_mnist
+import matplotlib.pyplot as plt
+import os
+
+MODEL_SAVE_FOLDER_PATH = os.path.join(os.getcwd(), 'trained')
+MODEL_SAVE_PATH = MODEL_SAVE_FOLDER_PATH + '/seresnext_cifar10.h5'
+TEST_IMAGE_FOLDER_PATH = os.path.join(os.getcwd(), 'test')
+TEST_IMAGE_PATH = TEST_IMAGE_FOLDER_PATH + '/test01.png'
+
+model = load_model('MODEL_SAVE_PATH')
+(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
+model.predict(test_images[:1, :])
+model.predict_classes(test_images[:1, :], verbose=0)
+
+plt.imshow(test_images[0])

+from model import SEResNeXt
+
+from keras.datasets import fashion_mnist
+from keras import optimizers
+
+import os
+import sys
+
+import tensorflow_datasets as tfds
+
+import os
+
+MODEL_SAVE_FOLDER_PATH = os.path.join(os.getcwd(), 'trained')
+if not os.path.exists(MODEL_SAVE_FOLDER_PATH):
+  os.mkdir(MODEL_SAVE_FOLDER_PATH)
+MODEL_SAVE_PATH = MODEL_SAVE_FOLDER_PATH + '/seresnext_cifar.h5'
+
+model = SEResNeXt('cifar-10', (32, 32, 3))
+
+model.compile(optimizer=optimizers.Adam(0.001), loss='categorical_crossentropy', metrics=['accuracy'])
+
+# ds_train = tfds.load('imagenet2012_corrupted', split='train', shuffle_files=True)
+ds_train = tfds.load('cifar-10', split='train', shuffle_files=True)
+ds_train = ds_train.shuffle(1000).batch(128).prefetch(10)
+
+model.fit(ds_train['image'], ds_train['label'], epochs=10, steps_per_epoch=30)
+
+model.save(MODEL_SAVE_PATH)