TensorFlow中的VGG16 介绍以及 代码

VGG是由牛津大学的K. Simonyan和A. Zisserman在“用于大规模图像识别的超深度卷积网络”一文中提出的卷积神经网络模型。  。该模型在ImageNet中实现了92.7%的前5个测试精度  ,这是属于1000个类的超过1400万张图像的数据集。

 

VGG16 之前一直没找到代码,今天找到了。

关于原理,之前看过,这里就不写了。一以后有hi时间再写。

这段代码是测试代码,人家已经把模型训练好了。我们直接下载它的模型用就可以了。

关于训练,以及换数据集,我明天再试试。

我是在这里找到的。https://www.cs.toronto.edu/~frossard/post/vgg16/

代码:

import tensorflow as tf
import numpy as np
from scipy.misc import imread, imresize
from imagenet_classes import class_names


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)


    def convlayers(self):
        self.parameters = []

        # zero-mean input
        with tf.name_scope('preprocess') as scope:
            mean = tf.constant([123.68, 116.779, 103.939], dtype=tf.float32, shape=[1, 1, 1, 3], name='img_mean')
            images = self.imgs-mean

        # 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]

        # pool1
        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]

        # pool2
        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('conv5_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='pool4')

    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='biases')
            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='biases')
            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='biases')
            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)
        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]))

if __name__ == '__main__':
    sess = tf.Session()
    imgs = tf.placeholder(tf.float32, [None, 224, 224, 3])
    vgg = vgg16(imgs, 'vgg16_weights.npz', sess)

    img1 = imread('gou.jpg', mode='RGB')
    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])

以上代码在在VGG16.py文件中。这段代码还不够,需要两个文件 文件地址在上面写着。

imagenet_classes.py     https://www.cs.toronto.edu/~frossard/vgg16/imagenet_classes.py

vgg16_weights.npz        https://www.cs.toronto.edu/~frossard/vgg16/vgg16_weights.npz

把这两个和上面的代码放在一个文件中。

再找一个图片引入测试就可以看识别的情况了。

我的运行结果

个人感觉识别率不高。不过识别的范围还是挺广的。 

希望后期能够改进(改进是不可能的,这辈子都不可能)

 

  • 4
    点赞
  • 20
    收藏
    觉得还不错? 一键收藏
  • 3
    评论
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值