一、 VGG16简介

VGG16网络是通过卷积和全连接的方式提取图片特征，进行识别一种网络结构。曾在某年取得分类第二，定位任务第一的佳绩。
其结构包含： 13个卷积层 + 3个全连接层，所以被称为VGG16,如下图绿色的部分即是网络的结构组成：
卷积配置说明：
- input(224224RGB image) ：输入图片大小为：224224,通道数为：3
- conv3_XXX ：卷积核为3（以下都是卷积核都是3，后面省略），卷积层的通道数为：XXX
VGG16特点（这里是借鉴[韩鼎の个人网站]：
- 卷积核全部使用3*3的卷积核，且所有卷积核： strides=[1,1,1,1] ,padding=“SAME”。
- 池化层全部使用： max的池化方式，2*2的池化核，通过全0填充，步长为2，strides=[1,2,2,1] ，padding=“SAME”。

二、代码实现

import h5py
import json
import tensorflow as tf
import cv2
import numpy as np
import matplotlib.pyplot as plt# 该文件包括最后三层的全连接层
# 这里的h5文件和下面的json文件下载来自于kaggle：链接为：https://www.kaggle.com/keras/vgg16
model_path = './kreas_vgg16_model_para/vgg16_weights_tf_dim_ordering_tf_kernels.h5'
# 该文件不包含最后三层的全连接层
# model_path = './kreas_vgg16_model_para/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5'# 1.通过h5py读取model的各层参数，笨办法就主要笨在这个地方，但是很好理解。
with h5py.File(model_path,'r') as f:# # 得到h5文件的第一层目录名字# layer1 = [ i for i in f]# print(layer1)# # 得到h5文件的第二层目录名字# layer2 = {'layer2_'+str(i):[j for j in f[layer1[i]]] for i in range(len(layer1))}# print(layer2)# 13层convolution 5个block  卷积核kernel为3*3*3# block1block1_conv1_W_1 = f['/block1_conv1/block1_conv1_W_1:0'][:]# print(block1_conv1_W_1.shape)block1_conv2_W_1 = f['/block1_conv2/block1_conv2_W_1:0'][:]# print(block1_conv2_W_1.shape)block1_conv1_b_1 = f['/block1_conv1/block1_conv1_b_1:0'][:]block1_conv2_b_1 = f['/block1_conv2/block1_conv2_b_1:0'][:]# block2block2_conv1_W_1 = f['/block2_conv1/block2_conv1_W_1:0'][:]# print(block2_conv1_W_1.shape)block2_conv2_W_1 = f['/block2_conv2/block2_conv2_W_1:0'][:]# print(block2_conv2_W_1.shape)block2_conv1_b_1 = f['/block2_conv1/block2_conv1_b_1:0'][:]block2_conv2_b_1 = f['/block2_conv2/block2_conv2_b_1:0'][:]# block3block3_conv1_W_1 = f['/block3_conv1/block3_conv1_W_1:0'][:]# print(block3_conv1_W_1.shape)block3_conv2_W_1 = f['/block3_conv2/block3_conv2_W_1:0'][:]# print(block3_conv2_W_1.shape)block3_conv3_W_1 = f['/block3_conv3/block3_conv3_W_1:0'][:]# print(block3_conv3_W_1.shape)block3_conv1_b_1 = f['/block3_conv1/block3_conv1_b_1:0'][:]block3_conv2_b_1 = f['/block3_conv2/block3_conv2_b_1:0'][:]block3_conv3_b_1 = f['/block3_conv3/block3_conv3_b_1:0'][:]# block4block4_conv1_W_1 = f['/block4_conv1/block4_conv1_W_1:0'][:]block4_conv2_W_1 = f['/block4_conv2/block4_conv2_W_1:0'][:]block4_conv3_W_1 = f['/block4_conv3/block4_conv3_W_1:0'][:]block4_conv1_b_1 = f['/block4_conv1/block4_conv1_b_1:0'][:]block4_conv2_b_1 = f['/block4_conv2/block4_conv2_b_1:0'][:]block4_conv3_b_1 = f['/block4_conv3/block4_conv3_b_1:0'][:]# block5block5_conv1_W_1 = f['/block5_conv1/block5_conv1_W_1:0'][:]block5_conv2_W_1 = f['/block5_conv2/block5_conv2_W_1:0'][:]block5_conv3_W_1 = f['/block5_conv3/block5_conv3_W_1:0'][:]block5_conv1_b_1 = f['/block5_conv1/block5_conv1_b_1:0'][:]block5_conv2_b_1 = f['/block5_conv2/block5_conv2_b_1:0'][:]block5_conv3_b_1 = f['/block5_conv3/block5_conv3_b_1:0'][:]# 三个全连接层fc1_W_1 = f['/fc1/fc1_W_1:0'][:]fc1_b_1 = f['/fc1/fc1_b_1:0'][:]# print(fc1_W_1.shape)fc2_W_1 = f['/fc2/fc2_W_1:0'][:]fc2_b_1 = f['/fc2/fc2_b_1:0'][:]# print(fc2_W_1.shape)predictions_W_1 = f['/predictions/predictions_W_1:0'][:]predictions_b_1 = f['/predictions/predictions_b_1:0'][:]# print(predictions_W_1.shape)# 2.把拿到的参数交给网络结构，就可以做预测了，得到softmax后的千分类。
def prediction(image):# 13个卷积层# block 1conv1 = conv2d(image,block1_conv1_W_1)relu1 = tf.nn.relu(tf.nn.bias_add(conv1,block1_conv1_b_1))conv2 = conv2d(relu1,block1_conv2_W_1)relu2 = tf.nn.relu(tf.nn.bias_add(conv2,block1_conv2_b_1))pool1 = max_pool_2x2(relu2)# block 2conv3 = conv2d(pool1,block2_conv1_W_1)relu3 = tf.nn.relu(tf.nn.bias_add(conv3,block2_conv1_b_1))conv4 = conv2d(relu3,block2_conv2_W_1)relu4 = tf.nn.relu(tf.nn.bias_add(conv4,block2_conv2_b_1))pool2 = max_pool_2x2(relu4)# block 3conv5 = conv2d(pool2,block3_conv1_W_1)relu5 = tf.nn.relu(tf.nn.bias_add(conv5,block3_conv1_b_1))conv6 = conv2d(relu5,block3_conv2_W_1)relu6 = tf.nn.relu(tf.nn.bias_add(conv6,block3_conv2_b_1))conv7 = conv2d(relu6,block3_conv3_W_1)relu7 = tf.nn.relu(tf.nn.bias_add(conv7,block3_conv3_b_1))pool3 = max_pool_2x2(relu7)# block 4conv8 = conv2d(pool3,block4_conv1_W_1)relu8 = tf.nn.relu(tf.nn.bias_add(conv8,block4_conv1_b_1))conv9 = conv2d(relu8,block4_conv2_W_1)relu9 = tf.nn.relu(tf.nn.bias_add(conv9,block4_conv2_b_1))conv10 = conv2d(relu9,block4_conv3_W_1)relu10 = tf.nn.relu(tf.nn.bias_add(conv10,block4_conv3_b_1))pool4 = max_pool_2x2(relu10)# block 5conv11 = conv2d(pool4,block5_conv1_W_1)relu11 = tf.nn.relu(tf.nn.bias_add(conv11,block5_conv1_b_1))conv12 = conv2d(relu11,block5_conv2_W_1)relu12 = tf.nn.relu(tf.nn.bias_add(conv12,block5_conv2_b_1))conv13 = conv2d(relu12,block5_conv3_W_1)relu13 = tf.nn.relu(tf.nn.bias_add(conv13,block5_conv3_b_1))pool5 = max_pool_2x2(relu13)# print(pool5.shape)  # (1, 7, 7, 512)pool_shape = pool5.get_shape().as_list()nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]reshaped = tf.reshape(pool5,[pool_shape[0],nodes])# print(reshaped.shape)  # (1, 25088)# 3个全连接层fc1 = tf.nn.relu(tf.nn.bias_add(tf.matmul(reshaped,fc1_W_1),fc1_b_1))fc2 =tf.nn.relu(tf.nn.bias_add(tf.matmul(fc1,fc2_W_1),fc2_b_1))y = tf.nn.softmax(tf.nn.bias_add(tf.matmul(fc2,predictions_W_1),predictions_b_1))# print(y.shape)  # (1, 1000)y = tf.squeeze(y)index = tf.argmax(y,0)labels_data = reafLabels()with tf.Session() as sess:sess.run(tf.global_variables_initializer())y_value = sess.run(y)# 将拿到的前五种可能，通过matplotlib可视化出来getTop5(y_value)return None# 2.1 TOP5可视化
def getTop5(y_value):# 传入的参数y_value只是softmax后得到的ndarray# ndarray的内容是：各个...（有点难表述）# 举例：y_value = [0.02,0.01,0.4....]表示识别的该物品在index=0上的可能性是0.02，在index=1上的可能性是0.01，在index=2上的可能性是0.4...# 拿到可能性最大的前五个索引index，后面通过索引拿到可能的valuetop5_index = np.argsort(-y_value)[:5]# 读取下载好的json文件，json文件内容：包含索引和对应的value，打开一看便知labels_data = reafLabels()# top5 各自的可能性top5_accuracy = [(y_value[i]) for index in top5_index for i in range(len(y_value)) if index==i]# top5 各自的valuetop5_prediction = [value[1] for index in top5_index for key,value in labels_data.items()  if key==str(index)]# 画图plt.figure(figsize=(8,8),dpi=80)x_ticks = range(len(top5_prediction))# 柱状图plt.bar(x_ticks,top5_accuracy,width=0.3,color=["purple","orange","y","g","c"])# 标记数字for x, y in zip(x_ticks, top5_accuracy):plt.text(x , y + 0.005, '%s' % percent(y), ha='center', va='bottom')# 添加刻度上的值plt.xticks(x_ticks,top5_prediction)# 标题plt.title("PREDICTIONS TOP5")plt.show()return Nonedef reafLabels():with open('./kreas_vgg16_model_para/imagenet_class_index.json', 'r', encoding='utf8')as fp:labels_data = json.load(fp)return labels_datadef dealImage(image_path="./image/frog.jpg"):image = cv2.imread(image_path)resized_image = cv2.resize(image,(224,224))# astype不改变numpy原数组，dtype容易出错retyped_image = resized_image.astype(np.float32)final_image = np.reshape(retyped_image,[1,224,224,3])# cv2.imshow('IMAGE',image)# cv2.waitKey(0)return final_imagedef conv2d(x,w):return tf.nn.conv2d(x,w,[1,1,1,1],padding="SAME")def max_pool_2x2(x):return tf.nn.max_pool(x,[1,2,2,1],[1,2,2,1],padding="SAME")def percent(value):return "%.2f%%"%(value*100)if __name__ == '__main__':image = dealImage()prediction(image)