def _make_layer(block,
num_filters,
blocklayers,
strides=1,
dilate=False,
use_bias=use_bias,
layer_name=''):
conv_shortcut = False
if strides != 1 or block is bottleneck:
conv_shortcut = True
layers = []
layers.append(
block(num_filters=num_filters,
strides=strides,
expansion=4,
conv_shortcut=conv_shortcut,
use_bias=use_bias,
name=layer_name + '_0'))
for k in range(1, blocklayers):
layers.append(
block(num_filters=num_filters,
strides=1,
expansion=4,
conv_shortcut=False,
use_bias=use_bias,
name=layer_name + '_{0}'.format(k)))
laters_block = Sequential(*layers)
laters_block.name = layer_name
return laters_block
def DenseNet(blocks,
growth_rate=32,
initial_filters=64,
include_top=True,
pretrained=True,
input_shape=(3,224,224),
num_classes=1000,
name='',
**kwargs):
"""'
Instantiates the DenseNet architecture.
Optionally loads weights pre-trained on ImageNet.
Args
blocks (tuple/ list of int ): numbers of building blocks for the dense layers.
growth_rate (int):The growth rate regulates how much new information each layer contributes to the global state
initial_filters (int): the channel of the first convolution layer
pretrained (bool): If True, returns a model pre-trained on ImageNet.
input_shape (tuple or list): the default input image size in CHW order (C, H, W)
num_classes (int): number of classes
name (string): anme of the model
Returns
A trident image classification model instance.
"""
densenet=Sequential()
densenet.add_module('conv1/conv',Conv2d_Block((7,7),initial_filters,strides=2,use_bias=False,auto_pad=True,padding_mode='zero',activation='relu',normalization='batch', name='conv1/conv'))
densenet.add_module('maxpool', (MaxPool2d((3, 3), strides=2, auto_pad=True, padding_mode='zero')))
densenet.add_module('denseblock1', DenseBlock(blocks[0],growth_rate=growth_rate))
densenet.add_module('transitiondown1', Transition(0.5))
densenet.add_module('denseblock2', DenseBlock(blocks[1], growth_rate=growth_rate))
densenet.add_module('transitiondown2', Transition(0.5))
densenet.add_module('denseblock3', DenseBlock(blocks[2], growth_rate=growth_rate))
densenet.add_module('transitiondown3', Transition(0.5))
densenet.add_module('denseblock4', DenseBlock(blocks[3], growth_rate=growth_rate))
densenet.add_module('classifier_norm',BatchNorm2d(name='classifier_norm'))
densenet.add_module('classifier_relu', Relu(name='classifier_relu'))
if include_top:
densenet.add_module('avg_pool', GlobalAvgPool2d(name='avg_pool'))
densenet.add_module('classifier', Dense(num_classes, activation=None, name='classifier'))
densenet.add_module('softmax', SoftMax( name='softmax'))
densenet.name = name
model=ImageClassificationModel(input_shape=input_shape,output=densenet)
#model.model.to(_device)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'imagenet_labels1.txt'), 'r',encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names = labels
model.preprocess_flow = [resize((input_shape[2], input_shape[1]), keep_aspect=True), normalize(0, 255), normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]
# model.summary()
return model
def resnet(block, layers, input_shape=(3, 224, 224), num_classes=1000, use_bias=False, include_top=True, model_name='',
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Args
block: a function that returns output tensor for the stacked residual blocks.
layers: list of integer, the number of repeat units in each blocks.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be`(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
num_classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
include_top: whether to include the fully-connected layer at the top of the network.
model_name: string, model name.
Returns
A Keras model instance.
Raises
ValueError: in case of invalid argument for `weights`, or invalid input shape.
"""
def _make_layer(block, num_filters, blocklayers, strides=1, dilate=False,use_bias=use_bias,layer_name=''):
conv_shortcut=False
if strides!=1 or block is bottleneck:
conv_shortcut=True
layers = []
layers.append(block(num_filters=num_filters, strides=strides, expansion = 4, conv_shortcut=conv_shortcut,use_bias=use_bias, name=layer_name+'_0'))
for k in range(1, blocklayers):
layers.append(block(num_filters=num_filters, strides=1, expansion = 4, conv_shortcut=False, use_bias=use_bias,name=layer_name+'_{0}'.format(k)))
laters_block=Sequential(*layers)
laters_block.name=layer_name
return laters_block
flow_list=[]
resnet = Sequential()
resnet.add_module('first_block',Conv2d_Block((7,7),64,strides=2,use_bias=use_bias,auto_pad=True,padding_mode='zero',normalization='batch',activation='relu',name='first_block'))
resnet.add_module('maxpool',(MaxPool2d((3,3),strides=2,auto_pad=True,padding_mode='zero')))
resnet.add_module('layer1',(_make_layer(block, 64, layers[0],strides=1, dilate=None,use_bias=use_bias,layer_name='layer1' )))
resnet.add_module('layer2',(_make_layer(block, 128, layers[1], strides=2, dilate=None,use_bias=use_bias,layer_name='layer2' )))
resnet.add_module('layer3',(_make_layer(block, 256, layers[2], strides=2, dilate=None,use_bias=use_bias,layer_name='layer3' )))
resnet.add_module('layer4' ,(_make_layer(block, 512, layers[3], strides=2, dilate=None,use_bias=use_bias,layer_name='layer4' )))
if include_top:
resnet.add_module('avg_pool', GlobalAvgPool2d(name='avg_pool'))
resnet.add_module('fc',Dense(num_classes,activation=None,name='fc'))
resnet.add_module('softmax', SoftMax(name='softmax'))
resnet.name=model_name
return resnet
def SEResNet_IR(include_top=True,num_layers=50,Bottleneck=BottleNeck_IR_SE,drop_ratio=0.4,feature_dim=128,input_shape=(3,112,112)):
blocks=OrderedDict()
blocks['input_layer']=Conv2d_Block((3,3),64,strides=1,auto_pad=True,use_bias=False,activation=PRelu(64),normalization='batch',name='input_layer')
blocks['body']=Sequential(
get_block(Bottleneck, out_channel=64, num_units=3,keep_filter=True)+
get_block(Bottleneck, out_channel=128, num_units=4,keep_filter=False)+
get_block(Bottleneck, out_channel=256, num_units=14,keep_filter=False)+
get_block(Bottleneck, out_channel=512, num_units=3,keep_filter=False)
)
blocks['output_layer']=Sequential(
BatchNorm2d(),
Dropout(drop_ratio),
Flatten(),
Dense(feature_dim),
BatchNorm(),
name='output_layer'
)
facenet=Sequential(blocks).to(_device)
facenet.name=camel2snake('SEResNet_IR')
model=FaceRecognitionModel(input_shape=input_shape,output=facenet)
model.preprocess_flow=[Resize((input_shape[1],input_shape[2]),keep_aspect=True),Normalize(0,255),Normalize([0.485, 0.456, 0.406],[0.229, 0.224, 0.225])]
#model.summary()
return model
def SE_ResNet(block,
layers,
input_shape=(3, 224, 224),
num_classes=1000,
use_bias=False,
include_top=True,
model_name='',
**kwargs):
"""Instantiates the ResNet, ResNetV2, and ResNeXt architecture.
Args
block: a function that returns output tensor for the stacked residual blocks.
layers: list of integer, the number of repeat units in each blocks.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be`(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
num_classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
use_bias: whether to use biases for convolutional layers or not
(True for ResNet and ResNetV2, False for ResNeXt).
include_top: whether to include the fully-connected layer at the top of the network.
model_name: string, model name.
Returns
A Keras model instance.
Raises
ValueError: in case of invalid argument for `weights`, or invalid input shape.
"""
def _make_layer(block,
num_filters,
blocklayers,
strides=1,
dilate=False,
use_bias=use_bias,
layer_name=''):
conv_shortcut = False
if strides != 1 or block is bottleneck or num_filters != 128:
conv_shortcut = True
layers = []
layers.append(
block(num_filters=num_filters,
strides=strides,
expansion=4,
conv_shortcut=conv_shortcut,
use_bias=use_bias,
name=layer_name + '.0'))
for k in range(1, blocklayers):
layers.append(
block(num_filters=num_filters,
strides=1,
expansion=4,
conv_shortcut=False,
use_bias=use_bias,
name=layer_name + '.{0}'.format(k)))
layers_block = Sequential(*layers)
layers_block.name = layer_name
return layers_block
flow_list = []
resnet = Sequential()
layer0 = Sequential(name='layer0')
layer0.add_module(
'first_block',
Conv2d_Block((7, 7),
64,
strides=2,
use_bias=use_bias,
auto_pad=True,
padding_mode='zero',
normalization='batch',
activation='relu',
name='first_block'))
layer0.add_module('maxpool', (MaxPool2d(
(3, 3), strides=2, auto_pad=True, padding_mode='zero')))
resnet.add_module('layer0', layer0)
resnet.add_module('layer1', (_make_layer(block,
64,
layers[0],
strides=1,
dilate=None,
use_bias=use_bias,
layer_name='layer1')))
resnet.add_module('layer2', (_make_layer(block,
128,
layers[1],
strides=2,
dilate=None,
use_bias=use_bias,
layer_name='layer2')))
resnet.add_module('layer3', (_make_layer(block,
256,
layers[2],
strides=2,
dilate=None,
use_bias=use_bias,
layer_name='layer3')))
resnet.add_module('layer4', (_make_layer(block,
512,
layers[3],
strides=2,
dilate=None,
use_bias=use_bias,
layer_name='layer4')))
resnet.add_module('avg_pool', GlobalAvgPool2d(name='avg_pool'))
if include_top:
resnet.add_module('fc', Dense(num_classes, activation=None, name='fc'))
resnet.add_module('softmax', SoftMax(name='softmax'))
resnet.name = model_name
model = ImageClassificationModel(input_shape=input_shape, output=resnet)
with open(os.path.join(os.path.dirname(os.path.abspath(__file__)),
'imagenet_labels1.txt'),
'r',
encoding='utf-8-sig') as f:
labels = [l.rstrip() for l in f]
model.class_names = labels
model.preprocess_flow = [
resize((input_shape[1], input_shape[2]), keep_aspect=True),
normalize(0, 255),
normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]
#model.summary()
return model