金融软件网站建设公司排名,郴州市住房和城乡建设厅网站,网站后期的维护和更新,美食网页模板免费下载2023.8.19
深度学习的卷积对于初学者是非常抽象#xff0c;当时在入门学习的时候直接劝退一大班人#xff0c;还好我坚持了下来。可视化时用到的图片#xff08;我们学校的一角#xff01;#xff01;#xff01;#xff09;以下展示了一个卷积和一次Relu的变化 作者使…2023.8.19
深度学习的卷积对于初学者是非常抽象当时在入门学习的时候直接劝退一大班人还好我坚持了下来。可视化时用到的图片我们学校的一角以下展示了一个卷积和一次Relu的变化 作者使用的GPU是RTX 3050ti 在这张图像上已经出现了Cuda out of memory了。防止其他 图片出现类似情况附上这张cat.jpg可以完成实验 代码是Copy大神的用tensorflow1写的使用tensoflow2的伙伴们记得添上 import tensorflow.compat.v1 as tf Code:
# coding: utf-8# # 使用预训练的VGG网络# In[1]:import scipy.io
import numpy as np
import os
import scipy.misc
import matplotlib.pyplot as plt
import tensorflow as tf
import imageioimport tensorflow.compat.v1 as tf# get_ipython().magic(umatplotlib inline)
print(所有包载入完毕)# In[2]:# 下载预先训练好的vgg-19模型为Matlab的.mat格式之后会用scipy读取
# (注意此版本模型与此处http://www.vlfeat.org/matconvnet/pretrained/最新版本不同)
import os.pathif not os.path.isfile(./data/imagenet-vgg-verydeep-19.mat):os.system(uwget -O data/imagenet-vgg-verydeep-19.mat http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat)# get_ipython().system(uwget -O data/imagenet-vgg-verydeep-19.mat http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat)# # 定义网络# In[3]: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)data scipy.io.loadmat(data_path)mean_pixel [103.939, 116.779, 123.68]weights data[layers][0]net {}current input_imagefor 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 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] currentassert len(net) len(layers)return net, mean_pixel, layersprint(Network for VGG ready)# # 定义模型# In[4]:def _conv_layer(input, weights, bias):conv tf.nn.conv2d(input, tf.constant(weights), strides(1, 1, 1, 1),paddingSAME)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),paddingSAME)def preprocess(image, mean_pixel):return image - mean_pixeldef unprocess(image, mean_pixel):return image mean_pixeldef imread(path):# return scipy.misc.imread(path).astype(np.float)return imageio.imread(path)def imsave(path, img):img np.clip(img, 0, 255).astype(np.uint8)scipy.misc.imsave(path, img)print(Functions for VGG ready)# # 运行# In[5]:cwd os.getcwd()
VGG_PATH cwd /data/imagenet-vgg-verydeep-19.mat
IMG_PATH cwd /images/cat.jpg
input_image imread(IMG_PATH)
shape (1,) input_image.shape # (h, w, nch) (1, h, w, nch)
with tf.Graph().as_default(), tf.Session() as sess:image tf.placeholder(float, shapeshape)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], cmapplt.cm.gray, fignumi 1)plt.title( layer)plt.colorbar()plt.show()
