Resnet-Tensorflow 在Mask-Rcnn 中的结构
阅读Mask-Rcnn代码时，观察resnet结构。
其中重要的有identity_block和conv_block。
Identity Block:
1*1，3*3，1*1的三层stride=(1,1)卷积，最后直接输出x+input作为输出。
def identity_block(input_tensor, kernel_size, filters, stage, block,
use_bias=True):
"""The identity_block is the block that has no conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
"""
nb_filter1, nb_filter2, nb_filter3 = filters
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = KL.Conv2D(nb_filter1, (1, 1), name=conv_name_base + '2a',
use_bias=use_bias)(input_tensor)
x = BatchNorm(axis=3, name=bn_name_base + '2a')(x)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter2, (kernel_size, kernel_size), padding='same',
name=conv_name_base + '2b', use_bias=use_bias)(x)
x = BatchNorm(axis=3, name=bn_name_base + '2b')(x)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base + '2c',
use_bias=use_bias)(x)
x = BatchNorm(axis=3, name=bn_name_base + '2c')(x)
x = KL.Add()([x, input_tensor])
x = KL.Activation('relu', name='res' + str(stage) + block + '_out')(x)
return x
Conv Block
1*1 3*3 1*1 的三层卷积模块,stride=(2*2)，与identity block不同的是，conv block创建了shortcut = bn(conv(input) )+ 输出x，作为输出。而indentity block直接加上input，没有再次conv和bn的过程。
def conv_block(input_tensor, kernel_size, filters, stage, block,
strides=(2, 2), use_bias=True):
"""conv_block is the block that has a conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
And the shortcut should have subsample=(2,2) as well
"""
nb_filter1, nb_filter2, nb_filter3 = filters
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = KL.Conv2D(nb_filter1, (1, 1), strides=strides,
name=conv_name_base + '2a', use_bias=use_bias)(input_tensor)
x = BatchNorm(axis=3, name=bn_name_base + '2a')(x)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter2, (kernel_size, kernel_size), padding='same',
name=conv_name_base + '2b', use_bias=use_bias)(x)
x = BatchNorm(axis=3, name=bn_name_base + '2b')(x)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base +
'2c', use_bias=use_bias)(x)
x = BatchNorm(axis=3, name=bn_name_base + '2c')(x)
shortcut = KL.Conv2D(nb_filter3, (1, 1), strides=strides,
name=conv_name_base + '1', use_bias=use_bias)(input_tensor)
shortcut = BatchNorm(axis=3, name=bn_name_base + '1')(shortcut)
x = KL.Add()([x, shortcut])
x = KL.Activation('relu', name='res' + str(stage) + block + '_out')(x)
return xidentityblock = 3层
convblock = 3层
stage1 :padding(3,3) + conv(7,7) + bn + relu + pool
stage2 : convblock + identityblock * 2
stage3 : convblock + identityblock * 3
stage4 : convblock + identity_block * 5 or 22 (resnet50 or resnet 101)
stage5 : if ture: convblock + identityblock * 2
if stage5, padding+conv + convblock * 4 + identityblock * 12=resnet 50
def resnet_graph(input_image, architecture, stage5=False):
assert architecture in ["resnet50", "resnet101"]
# Stage 1
x = KL.ZeroPadding2D((3, 3))(input_image)
x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
x = BatchNorm(axis=3, name='bn_conv1')(x)
x = KL.Activation('relu')(x)
C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
# Stage 2
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
# Stage 3
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
# Stage 4
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
block_count = {"resnet50": 5, "resnet101": 22}[architecture]
for i in range(block_count):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i))
C4 = x
# Stage 5
if stage5:
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
else:
C5 = None
return [C1, C2, C3, C4, C5]