加载已经训练好的VGG模型,并使用该模型进行测试
常用模型下载地址:http://www.vlfeat.org/matconvnet/models/
import scipy.io
import numpy as np
import os
import scipy.misc
import matplotlib.pyplot as plt
import tensorflow as tf
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):
return image - mean_pixel
def unprocess(image, mean_pixel):
return image + mean_pixel
def imread(path):
# scipy.misc.imread()函数可以将读取图片,返回的是一个numpy数组
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)
print ("Functions for VGG ready")
def net(data_path, input_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'
)
# 加载VGG模型
# print(data.keys())
# dict_keys(['__header__', '__version__', '__globals__', 'layers', 'classes', 'normalization'])
# 其中'classes'是imageNet中的1000个类的对应标识和描述
# 'layers'内部是42个元素,每个元素又是1*2的结构,分别是w权值和b权值
# 'normalize',输入图像的标准化参数
data = scipy.io.loadmat(data_path)
mean = data['normalization'][0][0][0]
mean_pixel = np.mean(mean, axis=(0, 1))
# 求得每个通道上的均值
weights = data['layers'][0]
net = {}
current = input_image
for i, name in enumerate(layers):
kind = name[:4]
if kind == 'conv':
# mat文件中并没有给定参数存放的格式,所以权重和偏置都需要我们去试
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]
# 把mat格式的weights转变为tensorflow格式的
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 断言:后面的表达式必须为真,否则会报错
assert len(net) == len(layers)
return net, mean_pixel, layers
print ("Network for VGG ready")
cwd = os.getcwd()
VGG_PATH = cwd + "/data/imagenet-vgg-verydeep-19.mat"
IMG_PATH = cwd + "/data/cat.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:
# 注意三维图像在定义占位符的形式
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 all layers
# layers = ('relu2_1', 'relu3_1', 'relu4_1')
for i, layer in enumerate(layers):
print ("[%d/%d] %s" % (i+1, len(layers), layer))
features = nets[layer].eval(feed_dict={image: input_image_pre})
print (" Type of 'features' is ", type(features))
print (" Shape of 'features' is %s" % (features.shape,))
# Plot response
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()