深度学习之加载VGG19模型获取特征图

1、加载VGG19获取图片特征图

# coding = utf-8
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import os
import scipy.io
import scipy.misc

def _conv_layer(input,weights,bias):
    conv = tf.nn.conv2d(input,tf.constant(weights),strides=(1,1,1,1),padding="SAME")
    return tf.nn.bias_add(conv,bias)
def _pool_layer(input):
    return tf.nn.max_pool(input,ksize=(1,2,2,1),strides=(1,2,2,1),padding="SAME")
def preprocess(image,mean_pixel):
    '''简单预处理,全部图片减去平均值'''
    return image - mean_pixel
def unprocess(img,mean_pixel):
    return img + mean_pixel
def imread(path):
    return scipy.misc.imread(path).astype(np.float)
def imsave(path,img):
    img = np.clip(img,0,255).astype(np.uint8)
    scipy.misc.imsave(path,img)
def net(data_path,input_image):
    """
    读取VGG模型参数,搭建VGG网络
    :param data_path: VGG模型文件位置
    :param input_image: 输入测试图像
    :return:
    """
    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'
    )
    data = scipy.io.loadmat(data_path)
    mean = data['normalization'][0][0][0]
    mean_pixel = np.mean(mean,axis=(0,1))
    weights = data['layers'][0]
    net = {}
    current = input_image
    for i, name in enumerate(layers):
        kind =name[:4]
        if kind == 'conv':
            kernels,bias = weights[i][0][0][0][0]
            kernels = np.transpose(kernels,(1,0,2,3))
            bias = bias.reshape(-1)
            current = _conv_layer(current,kernels,bias)
        elif kind == 'relu':
            current = tf.nn.relu(current)
        elif kind == 'pool':
            current = _pool_layer(current)
        net[name] = current
    assert len(net) == len(layers)
    return net,mean_pixel,layers

if __name__ == '__main__':
    VGG_PATH = "./one/imagenet-vgg-verydeep-19.mat"
    IMG_PATH = './one/3.jpg'
    input_image =imread(IMG_PATH)
    shape = (1, input_image.shape[0], input_image.shape[1], input_image.shape[2])
    with tf.Session() as sess:
        image = tf.placeholder('float', shape=shape)
        nets, mean_pixel, all_layers= net(VGG_PATH, image)
        input_image_pre=np.array([preprocess(input_image,mean_pixel)])
        layers = all_layers

        for i , layer in enumerate(layers):
            print("[%d/%d] %s" % (i+1,len(layers),layers))
            features = nets[layer].eval(feed_dict={image:input_image_pre})
            print("Type of 'feature' is ",type(features))
            print("Shape of 'features' is  %s" % (features.shape,))
            if 1:
                plt.figure(i+1,figsize=(10,5))
                plt.matshow(features[0,:,:,0],cmap=plt.cm.gray,fignum=i+1)
                plt.title(""+layer)
                plt.colorbar()
                plt.show()