ResNet 网络学习

个人笔记 感谢指正

Import

参考来源 ：刘博

from __future__ import print_function
import numpy as np
import warnings
from keras.layers import Input
from keras import layers
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Flatten
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import GlobalMaxPooling2D
from keras.layers import ZeroPadding2D
from keras.layers import AveragePooling2D
from keras.layers import GlobalAveragePooling2D
from keras.layers import BatchNormalization
from keras.models import Model
from keras.preprocessing import image
import keras.backend as K
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import preprocess_input
from keras_applications.imagenet_utils import _obtain_input_shape
from keras.engine.topology import get_source_inputs

恒等模块(Identity_block 函数)

def identity_block(input_tensor, kernel_size, filters, stage, block):
    """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 filterss 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

    # Returns
        Output tensor for the block.
    """
    filters1, filters2, filters3 = filters
    if K.image_data_format() == 'channels_last':   
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters2, kernel_size,
               padding='same', name=conv_name_base + '2b')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = layers.add([x, input_tensor])    #residual
    x = Activation('relu')(x)
    return x

参数：
input_tensor : 输入给该模块的tensor
kernel_size : 默认值是3，主路中间卷积层卷积核的大小，其实就是卷积核的元组
filters : 以实数为元素的列表，主路3个卷积核的数目
stage : 当前阶段的标签，是实数，用于生成层的名称
block : 与satge配合，用于生成层的名称，例如：‘a’, ‘b’

函数作用概述：一个恒等结构块由三个卷积层和一个恒等快捷通道组成，恒等快捷通道不需要任何参数！我们需要指定的参数是卷积核大小、三个过滤器以及每一层的名称。

K.image_data_format() 函数：Returns the default image data format convention (‘channels_first’ or ‘channels_last’)，函数后面的括号一定不能漏掉

BatchNormalization()函数：Normalize the activations of the previous layer at each batch, i.e. applies a transformation that maintains the mean activation close to 0 and the activation standard deviation close to 1