python神经网络VGG16模型复现及其如何预测详解

#-------------------------------------------------------------#
#   vgg16的网络部分
#-------------------------------------------------------------#
import tensorflow as tf
# 创建slim对象
slim = tf.contrib.slim
def vgg_16(inputs,
           num_classes=1000,
           is_training=True,
           dropout_keep_prob=0.5,
           spatial_squeeze=True,
           scope='vgg_16'):
    with tf.variable_scope(scope, 'vgg_16', [inputs]):
        # 建立vgg_16的网络
        # conv1两次[3,3]卷积网络，输出的特征层为64，输出为(224,224,64)
        net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
        # 2X2最大池化，输出net为(112,112,64)
        net = slim.max_pool2d(net, [2, 2], scope='pool1')
        # conv2两次[3,3]卷积网络，输出的特征层为128，输出net为(112,112,128)
        net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
        # 2X2最大池化，输出net为(56,56,128)
        net = slim.max_pool2d(net, [2, 2], scope='pool2')
        # conv3三次[3,3]卷积网络，输出的特征层为256，输出net为(56,56,256)
        net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
        # 2X2最大池化，输出net为(28,28,256)
        net = slim.max_pool2d(net, [2, 2], scope='pool3')
        # conv3三次[3,3]卷积网络，输出的特征层为256，输出net为(28,28,512)
        net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
        # 2X2最大池化，输出net为(14,14,512)
        net = slim.max_pool2d(net, [2, 2], scope='pool4')
        # conv3三次[3,3]卷积网络，输出的特征层为256，输出net为(14,14,512)
        net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
        # 2X2最大池化，输出net为(7,7,512)
        net = slim.max_pool2d(net, [2, 2], scope='pool5')
        # 利用卷积的方式模拟全连接层，效果等同，输出net为(1,1,4096)
        net = slim.conv2d(net, 4096, [7, 7], padding='VALID', scope='fc6')
        net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                            scope='dropout6')
        # 利用卷积的方式模拟全连接层，效果等同，输出net为(1,1,4096)
        net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
        net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
                            scope='dropout7')
        # 利用卷积的方式模拟全连接层，效果等同，输出net为(1,1,1000)
        net = slim.conv2d(net, num_classes, [1, 1],
                        activation_fn=None,
                        normalizer_fn=None,
                        scope='fc8')
        # 由于用卷积的方式模拟全连接层，所以输出需要平铺
        if spatial_squeeze:
            net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
        return net

from nets import vgg16
import tensorflow as tf
import numpy as np
import utils
# 读取图片
img1 = utils.load_image("./test_data/dog.jpg")
# 对输入的图片进行resize，使其shape满足(-1,224,224,3)
inputs = tf.placeholder(tf.float32,[None,None,3])
resized_img = utils.resize_image(inputs, (224, 224))
# 建立网络结构
prediction = vgg16.vgg_16(resized_img)
# 载入模型
sess = tf.Session()
ckpt_filename = './model/vgg_16.ckpt'
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess, ckpt_filename)
# 最后结果进行softmax预测
pro = tf.nn.softmax(prediction)
pre = sess.run(pro,feed_dict={inputs:img1})
# 打印预测结果
utils.print_prob(pre[0], './synset.txt')

import matplotlib.image as mpimg
import numpy as np
import tensorflow as tf
from tensorflow.python.ops import array_ops
def load_image(path):
    # 读取图片，rgb
    img = mpimg.imread(path)
    # 将图片修剪成中心的正方形
    short_edge = min(img.shape[:2])
    yy = int((img.shape[0] - short_edge) / 2)
    xx = int((img.shape[1] - short_edge) / 2)
    crop_img = img[yy: yy + short_edge, xx: xx + short_edge]
    return crop_img
def resize_image(image, size,
                 method=tf.image.ResizeMethod.BILINEAR,
                 align_corners=False):
    with tf.name_scope('resize_image'):
        image = tf.expand_dims(image, 0)
        image = tf.image.resize_images(image, size,
                                       method, align_corners)
        image = tf.reshape(image, tf.stack([-1,size[0], size[1], 3]))
        return image
def print_prob(prob, file_path):
    synset = [l.strip() for l in open(file_path).readlines()]
    # 将概率从大到小排列的结果的序号存入pred
    pred = np.argsort(prob)[::-1]
    # 取最大的1个、5个。
    top1 = synset[pred[0]]
    print(("Top1: ", top1, prob[pred[0]]))
    top5 = [(synset[pred[i]], prob[pred[i]]) for i in range(5)]
    print(("Top5: ", top5))
    return top1

('Top1: ', 'n02099601 golden retriever', 0.98766345)
('Top5: ', [('n02099601 golden retriever', 0.98766345), ('n02099712 Labrador retriever', 0.0108569125), ('n02101556 clumber, clumber spaniel', 0.00039345716), ('n02102480 Sussex spaniel', 0.0002893341), ('n02102318 cocker spaniel, English cocker spaniel, cocker', 0.00018955152)])