vgg16动物识别

1、概述

        VGG是5个group的卷积、2层全连接层用于提取图像特征、1层全连接层用于分类特征。根据前5个卷积层组每个组中的不同配置，卷积层数从8到16递增，网络结构如下图所示。

 2、实验部分

        采用预加载模式，利用训练好的模型参数进行加载。

        权重集：vgg16_weights.npz

        2.1 模块加载

import numpy as np
import tensorflow.compat.v1 as tf
import matlab
import cv2
#from imagenet_classes import class_names

        2.2 vgg16网络结构

tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, name=None)
第一个参数input：指需要做卷积的输入图像，它要求是一个Tensor，具有[batch, in_height, in_width, in_channels]这样的shape，具体含义是[训练时一个batch的图片数量, 图片高度, 图片宽度, 图像通道数]，注意这是一个4维的Tensor，要求类型为float32和float64其中之一
第二个参数filter：相当于CNN中的卷积核，它要求是一个Tensor，具有[filter_height, filter_width, in_channels, out_channels]这样的shape，具体含义是[卷积核的高度，卷积核的宽度，图像通道数，卷积核个数]，要求类型与参数input相同，有一个地方需要注意，第三维in_channels，就是参数input的第四维
第三个参数strides：卷积时在图像每一维的步长，这是一个一维的向量，长度4
第四个参数padding：string类型的量，只能是"SAME","VALID"其中之一，这个值决定了不同的卷积方式
第五个参数：use_cudnn_on_gpu:bool类型，是否使用cudnn加速，默认为true
结果返回一个Tensor，这个输出，就是我们常说的feature map，shape仍然是[batch, height, width, channels]这种形式。

class vgg16:
    def __init__(self,imgs,weights=None,sess=None):
        self.imgs = imgs;
        self.convlayers();
        self.fc_layers();
        self.probs = tf.nn.softmax(self.fc3l)
        if weights is not None and sess is not None:
            self.load_weights(weights,sess)
    #vgg16网络层
    def convlayers(self):
        self.parameters=[]
        #输入
        with tf.name_scope('preprocess') as scope:
            mean = tf.constant([123.68,116.79,103.939],dtype=tf.float32,shape=[1,1,1,3],name='img_mean')
            images = self.imgs;
        #conv1_1
        with tf.name_scope('conv1_1') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,3,64],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(images,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[64],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv1_1 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv1_2
        with tf.name_scope('conv1_2') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,64,64],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv1_1,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[64],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv1_2 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]   
        #pool
        self.pool1 = tf.nn.max_pool(self.conv1_2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME',name='pool1')
        
        #conv2_1
        with tf.name_scope('conv2_1') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,64,128],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.pool1,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[128],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv2_1 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv2_2
        with tf.name_scope('conv2_2') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,128,128],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv2_1,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[128],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv2_2 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]    
        #poo2
        self.pool2 = tf.nn.max_pool(self.conv2_2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME',name='pool2')
        
        #conv3_1
        with tf.name_scope('conv3_1') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,128,256],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.pool2,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[256],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv3_1 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv3_2
        with tf.name_scope('conv3_2') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,256,256],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv3_1,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[256],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv3_2 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv3_3
        with tf.name_scope('conv3_3') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,256,256],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv3_2,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[256],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv3_3 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]    
        #pool3
        self.pool3 = tf.nn.max_pool(self.conv3_3,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME',name='pool3')
        
        #conv4_1
        with tf.name_scope('conv4_1') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,256,512],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.pool3,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[512],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv4_1 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv4_2
        with tf.name_scope('conv4_2') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,512,512],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv4_1,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[512],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv4_2 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv4_3
        with tf.name_scope('conv4_3') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,512,512],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv4_2,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[512],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv4_3 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]    
        #pool4
        self.pool4 = tf.nn.max_pool(self.conv4_3,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME',name='pool4')
        
        #conv5_1
        with tf.name_scope('conv5_1') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,512,512],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.pool4,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[512],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv5_1 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv5_2
        with tf.name_scope('conv5_2') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,512,512],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv5_1,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[512],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv5_2 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]
        #conv5_3
        with tf.name_scope('conv4_3') as scope:
            kernel = tf.Variable(tf.truncated_normal([3,3,512,512],dtype=tf.float32,stddev=1e-1),name='weights')
            conv = tf.nn.conv2d(self.conv5_2,kernel,[1,1,1,1],padding='SAME')
            biases = tf.Variable(tf.constant(0.0,shape=[512],dtype=tf.float32),trainable=True,name='biases')
            out = tf.nn.bias_add(conv,biases)
            self.conv5_3 = tf.nn.relu(out,name=scope)
            self.parameters+=[kernel,biases]    
        #pool5
        self.pool5 = tf.nn.max_pool(self.conv5_3,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME',name='pool5')
    def fc_layers(self):
        #fc1
        with tf.name_scope('fc1') as scope:
            shape = int(np.prod(self.pool5.get_shape()[1:]))
            fc1w = tf.Variable(tf.truncated_normal([shape,4096],dtype=tf.float32,stddev=1e-1),name='weights')
            fc1b = tf.Variable(tf.constant(1.0,shape=[4096],dtype=tf.float32),trainable=True,name='bias')
            pool5_flat = tf.reshape(self.pool5,[-1,shape])
            fc1l = tf.nn.bias_add(tf.matmul(pool5_flat,fc1w),fc1b)
            self.fc1 = tf.nn.relu(fc1l)
            self.parameters +=[fc1w,fc1b]
        #fc2
        with tf.name_scope('fc2') as scope:
            fc2w = tf.Variable(tf.truncated_normal([4096,4096],dtype=tf.float32,stddev=1e-1),name='weights')
            fc2b = tf.Variable(tf.constant(1.0,shape=[4096],dtype=tf.float32),trainable=True,name='bias')
            fc2l = tf.nn.bias_add(tf.matmul(self.fc1,fc2w),fc2b)
            self.fc2 = tf.nn.relu(fc2l)
            self.parameters +=[fc2w,fc2b]
        #fc3
        with tf.name_scope('fc3') as scope:
            fc3w = tf.Variable(tf.truncated_normal([4096,1000],dtype=tf.float32,stddev=1e-1),name='weights')
            fc3b = tf.Variable(tf.constant(1.0,shape=[1000],dtype=tf.float32),trainable=True,name='bias')
            self.fc3l = tf.nn.bias_add(tf.matmul(self.fc2,fc3w),fc3b)
            self.parameters +=[fc3w,fc3b]
    def load_weights(self,weight_file,sess):
        weights = np.load(weight_file)
        print(weights)
        keys = sorted(weights.keys())
        for i,k in enumerate(keys):
            print(i,k,np.shape(weights[k]))
            sess.run(self.parameters[i].assign(weights[k]))

        2.3  运行模型

tf.disable_eager_execution()
sess = tf.Session()
imgs = tf.placeholder(tf.float32,[None,224,224,3])
vgg = vgg16(imgs,'./vgg16_weights.npz',sess)
img1 = cv2.imread('./laska.jpg')
#img1 = imresize(img1,(224,224))
prob = sess.run(vgg.probs,feed_dict={vgg.imgs:[img1]})[0]
preds = (np.argsort(prob)[::-1])[0:5]
for p in preds:
    #print(class_names[p],prob[p])
    print(p,prob[p])

         notebook代码下载地址：

                animal_recognition.ipynb