卷积神经网络＜二＞keras实现多分支输入VGG

VGG的模型图

VGG使用Keras实现

这里的代码借鉴了VGG实现Keras，但是这段代码不支持多通道，并且vgg函数的扩展性不好。下面修改一下，方便进行多分支图片输入的建立，以及更见方便的调参。

# from keras.models import
from keras.layers import *
from keras.models import Input, load_model, Sequential
from keras import Model
from keras.datasets import mnist
from keras.utils import to_categorical
from keras.losses import categorical_crossentropy
import keras.optimizers
import numpy as np
 
 
def vgg(input_shape, num_cls, filters_num, conv_nums):
    # print(input_shape)
    inputs = Input(shape=input_shape)
    x = inputs
    for i in range(len(conv_nums)):
        for j in range(conv_nums[i]):
            x = Conv2D(filters=filters_num[i], kernel_size=3, padding='same',
                       name='stage{0}_conv{1}'.format(i+1, j+1))(x)
        x = MaxPool2D((2, 2), strides=2, name='maxpool_'+str(i+1))(x)
        x = ZeroPadding2D((1, 1))(x)
    x = Flatten(name='flatten')(x)
    x = Dense(units=4096, name='dense4096_1')(x)
    x = Dense(units=4096, name='dense4096_2')(x)
    x = Dense(units=num_cls, name='dense1000', activation='softmax')(x)
    model = Model(inputs=inputs, outputs=x, name='vgg')
    model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['acc'])
    return model
 
 
def train(net_name):
    path = r'C:\Users\.keras\datasets\mnist.npz'
    with np.load(path, allow_pickle=True) as f:
        x_train, y_train = f['x_train'], f['y_train']
        x_test, y_test = f['x_test'], f['y_test']
 
    x_train = x_train.reshape(x_train.shape[0], 28, 28, 1).astype('float32')
    x_test = x_test.reshape(x_test.shape[0], 28, 28, 1).astype('float32')
    num_classes = 10
    x_train = x_train / 255.
    x_test = x_test / 255.
    y_train = to_categorical(y_train, num_classes)
    y_test = to_categorical(y_test, num_classes)
 
    batch_size = 16
    epochs = 1
 
    if net_name == 'vgg-19':
        filters_num = [64, 128, 256, 512, 512]
        conv_nums = [2, 2, 4, 4, 4]
    else:
        filters_num = [32, 64, 128, 256, 512]
        conv_nums = [2, 2, 3, 3, 3]
    vgg_model = vgg(input_shape=(28, 28, 1), num_cls=num_classes, filters_num=filters_num,
                    conv_nums=conv_nums)
    vgg_model.summary()
    vgg_model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1)
    vgg_model.save('{0}-mnist.h5'.format(net_name))
    eval_res = vgg_model.evaluate(x_test, y_test)
    print(eval_res)
 
 
if __name__ == '__main__':
    train('vgg-16')

方便调参版本

1. 把optimizer和input等重要参数进行了封装，方便调参和调用。
2. 建立了多分支输入函数build_multy_vgg()，方便调用。

"""
@author:fuzekun
@file:VGG_Model.py
@time:2022/11/22
@description: 定义VGG的模型进行图片的训练，首先只使用rri进行训练
"""

# from keras.models import
from keras.layers import *
from keras.models import Input, load_model, Sequential
from keras import Model
from keras.datasets import mnist
from keras.utils.all_utils import to_categorical
from keras.losses import categorical_crossentropy
import keras.optimizers
import numpy as np
import tensorflow as tf
"""
这里建立模型的时候，压缩到最后就没有了，个人以为是图片太小导致的，所以240的时候可以去掉zero那一层
"""

def vgg(input_shape, num_cls, filters_num, conv_nums, multy):
    # print(input_shape)
    inputs = Input(shape=input_shape)
    x = inputs
    for i in range(len(conv_nums)):
        for j in range(conv_nums[i]):
            x = Conv2D(filters=filters_num[i], kernel_size=3, padding='same')(x)
        x = MaxPool2D((2, 2), strides=2)(x)
        if input_shape[0] < 224:
            x = ZeroPadding2D((1, 1))(x)
    x = Flatten()(x)
    x = Dense(units=4096)(x)
    x = Dense(units=4096)(x)
    if not multy:      # 单模型直接输出到类别
        x = Dense(units=num_cls, activation='softmax')(x)
    model = Model(inputs=inputs, outputs=x, name='vgg')
    return model


def build_vgg(net_name, input_shape, num_classes, optimizer, filter_num=[], conv_nums=[], multy = False):

    if net_name == 'vgg-19':
        filters_num = [64, 128, 256, 512, 512]
        conv_nums = [2, 2, 4, 4, 4]
    else:
        filters_num = [32, 64, 128, 256, 512]
        conv_nums = [2, 2, 3, 3, 3]

    vgg_model = vgg(input_shape=input_shape, num_cls=num_classes, filters_num=filters_num,
                    conv_nums=conv_nums, multy=multy)
    if not multy:   # 多输入的不进行编译
        vgg_model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['acc'])
    # vgg_model.summary()
    return vgg_model

# 创建多输入的VGG模型
def build_multy_VGG(net_name, input_shape, num_classes, optimizer, n_hiddens,
                    filter_num=[], conv_nums=[]):
    out_rri = build_vgg(net_name, input_shape, num_classes, optimizer, filter_num, conv_nums, True)
    out_edr = build_vgg(net_name, input_shape, num_classes, optimizer, filter_num, conv_nums, True)
    out_amp = build_vgg(net_name, input_shape, num_classes, optimizer, filter_num, conv_nums, True)
    # 2. 进行模型融合
    # print(out_rri.output)
    combined = concatenate([out_rri.output, out_edr.output])  # (None, 7, 7, 768)
    # print(combined)
    # 2.1融合输入
    x = Dense(n_hiddens, activation='relu')(combined)
    x = Flatten()(x)
    # 2.2最后输出
    x = Dense(num_classes, activation='softmax')(x)
    # 2.3模型定义完成
    model = Model(inputs=[out_rri.input, out_edr.input], outputs=x)
    model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['acc'])
    return model

def train(net_name):
    path = r'C:\Users\.keras\datasets\mnist.npz'
    with np.load(path, allow_pickle=True) as f:
        x_train, y_train = f['x_train'], f['y_train']
        x_test, y_test = f['x_test'], f['y_test']

    x_train = x_train.reshape(x_train.shape[0], 28, 28, 1).astype('float32')
    x_test = x_test.reshape(x_test.shape[0], 28, 28, 1).astype('float32')
    num_classes = 10
    x_train = x_train / 255.
    x_test = x_test / 255.
    y_train = to_categorical(y_train, num_classes)
    y_test = to_categorical(y_test, num_classes)

    batch_size = 16
    epochs = 1

    lr = 0.001
    opt = tf.keras.optimizers.Adam(learning_rate=lr)
    model = build_vgg("vgg-16", input_shape=(28,28,1), num_classes=2, optimizer=opt)
    model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1)
    model.save('{0}-mnist.h5'.format(net_name))
    eval_res = model.evaluate(x_test, y_test)
    print(eval_res)


if __name__ == '__main__':
    train('vgg-16')