Keras框架：resent50代码实现

Residual net概念

概念：

Residual net(残差网络)：将靠前若干层的某一层数据输出直接跳过多层引入到后面数据层的输入 部分。
残差神经单元：假定某段神经网络的输入是x，期望输出是H(x)，如果我们直接将输入x传到输出作 为初始结果，那么我们需要学习的目标就是F(x) = H(x) - x，这就是一个残差神经单元，相当于将 学习目标改变了，不再是学习一个完整的输出H(x)，只是输出和输入的差别 H(x) - x ，即残差。

细节：

• 普通的直连的卷积神经网络和ResNet的最大区别在 于，ResNet有很多旁路的支线将输入直接连到后面 的层，使得后面的层可以直接学习残差，这种结构也 被称为shortcut或skip connections。
• 传统的卷积层或全连接层在信息传递时，或多或少会 存在信息丢失、损耗等问题。ResNet在某种程度上 解决了这个问题，通过直接将输入信息绕道传到输出， 保护信息的完整性，整个网络只需要学习输入、输出 差别的那一部分，简化了学习目标和难度。

思路：

ResNet50有两个基本的块，分别名为Conv Block和Identity Block，其中Conv Block输入和输出的维度 是不一样的，所以不能连续串联，它的作用是改变网络的维度；Identity Block输入维度和输出维度相 同，可以串联，用于加深网络的。

resent50代码实现：

网络主体部分：

#-------------------------------------------------------------#
#   ResNet50的网络部分
#-------------------------------------------------------------#
from __future__ import print_function


import numpy as np
from keras import layers

from keras.layers import Input
from keras.layers import Dense,Conv2D,MaxPooling2D,ZeroPadding2D,AveragePooling2D
from keras.layers import Activation,BatchNormalization,Flatten
from keras.models import Model

from keras.preprocessing import image
import keras.backend as K
from keras.utils.data_utils import get_file
from keras_applications.imagenet_utils import decode_predictions
from keras_applications.imagenet_utils import preprocess_input


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

    filters1, filters2, filters3 = filters

    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(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(name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

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

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


def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):

    filters1, filters2, filters3 = filters

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

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

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

    shortcut = Conv2D(filters3, (1, 1), strides=strides,
                      name=conv_name_base + '1')(input_tensor)
    shortcut = BatchNormalization(name=bn_name_base + '1')(shortcut)

    x = layers.add([x, shortcut])
    x = Activation('relu')(x)
    return x


def ResNet50(input_shape=[224,224,3],classes=1000):

    img_input = Input(shape=input_shape)
    x = ZeroPadding2D((3, 3))(img_input)

    x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
    x = BatchNormalization(name='bn_conv1')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((3, 3), strides=(2, 2))(x)

    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')
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')

    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')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')

    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')

    x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')

    x = AveragePooling2D((7, 7), name='avg_pool')(x)

    x = Flatten()(x)
    x = Dense(classes, activation='softmax', name='fc1000')(x)

    model = Model(img_input, x, name='resnet50')

    model.load_weights("resnet50_weights_tf_dim_ordering_tf_kernels.h5")

    return model

if __name__ == '__main__':
    model = ResNet50()
    model.summary()
    img_path = 'elephant.jpg'
    # img_path = 'bike.jpg'
    img = image.load_img(img_path, target_size=(224, 224))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    x = preprocess_input(x)

    print('Input image shape:', x.shape)
    preds = model.predict(x)
    print('Predicted:', decode_predictions(preds))