vgg19_net网络参数的下载与迁移

1.下载数据

下载地址：http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat

from urllib import request
        #回调函数，当连接上服务器、以及相应的数据块传输完毕的时候会触发该回调。我们可以利用这个回调函数来显示当前的下载进度。
        def _progress(count, block_size, total_size):
            #sys.stdout.write等价于print
            sys.stdout.write(
                '\r>> Downloading %s %.1f%%' % (filename, float(count * block_size) / float(total_size) * 100.0))
            sys.stdout.flush()
        #下载指定url中的文件
        filepath, _ = urllib.request.urlretrieve(url_name, filepath, reporthook=_progress)

2.解压压缩包

2.1.解压zip文件

import zipfile
#压缩包解压
 with zipfile.ZipFile(filepath) as zf:
     zip_dir = zf.namelist()[0]
     zf.extractall(dir_path)

2. 2.解压tar文件

import tarfile
tarfile.open(filepath, 'r:gz').extractall(dir_path)

 3.加载mat格式文件

import scipy.io  #必须导入scipy.io，不能仅仅导入scipy
data = scipy.io.loadmat(filepath)

4.生成vgg19模型

def vgg_net(weights, image):
    layers = (
        'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1',

        'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',

        'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3',
        'relu3_3', 'conv3_4', 'relu3_4', 'pool3',

        'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3',
        'relu4_3', 'conv4_4', 'relu4_4', 'pool4',

        'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3',
        'relu5_3', 'conv5_4', 'relu5_4'
    )

    net = {}
    current = image
    for i, name in enumerate(layers):
        kind = name[:4]
        if kind == 'conv':
            kernels, bias = weights[i][0][0][0][0]
            # matconvnet: weights are [width, height, in_channels, out_channels]
            # tensorflow: weights are [height, width, in_channels, out_channels]
            kernels = utils.get_variable(np.transpose(kernels, (1, 0, 2, 3)), name=name + "_w")
            bias = utils.get_variable(bias.reshape(-1), name=name + "_b")
            current = utils.conv2d_basic(current, kernels, bias)
        elif kind == 'relu':
            current = tf.nn.relu(current, name=name)
            if FLAGS.debug:
                utils.add_activation_summary(current)
        elif kind == 'pool':
            current = utils.avg_pool_2x2(current)
        net[name] = current

    return net

mean = model_data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
weights = np.squeeze(model_data['layers'])

processed_image = utils.process_image(image, mean_pixel)

image_net = vgg_net(weights, processed_image)