我们使用的VGG模型是别人已经训练好的一个19层的参数所做的一个模型
第一步：定义卷积分部操作函数
mport scipy.io import numpy as np import os import scipy.misc import matplotlib.pyplot as plt import tensorflow as tf # 进行卷积操作 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) # 进行池化操作 def _pool_layer(input): return tf.nn.max_pool(input, ksize=(1, 2, 2, 1), strides=(1, 2, 2, 1), padding='SAME') # 进行去均值的操作 def preprocess(image, mean_pixel): return image - mean_pixel def unprocess(image, mean_pixel): return image + 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)
第二步：定义卷积操作函数
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' ) # 载入数据 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)) # 重构reshape 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) # 用来存放对应的处理结果 net[name] = current assert len(net) == len(layers) return net, mean_pixel, layers
第三步： 构造文件路径
# 返回当前的路径 cwd = os.getcwd() # 别人已经训练好的模型 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])
第四步：训练模型，输出特征图像
with tf.Session as sess: image = tf.placeholder('float', shape=shape) #训练模型 nets, mean_pixel, all_layers = net(VGG_PATH, image) # 去除均值 input_image_pre = np.array([preprocess(input_image, mean_pixel)]) layers = all_layers for i, layer in enumerate(layers): # 输出模型的单个特征 features = nets[layer].eval(feed_dict={image:input_image}) print(" Type of 'features' is ", type(features)) print(" Shape of 'features' is %s" % (features.shape,)) # 画卷积特征图 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()