pytorch 对特征进行mean_PyTorch 提取神经网络中间层特征进行可视化
实现步骤：处理单张图片作为网络输入
根据给定的layer层，获取该层的输出结果 features
考虑到 feature 的形状为 (batch_size, filter_number, H, W), 提取其中的第一个过滤器得到的结果
以一张图片作为输入的情况下，我们得到的feature即为(H, W)大小的tensor
将tensor 转为numpy, 然后归一化到 [0, 1], 最后乘255，使得范围为[0, 255]
代码说明：使用了在ImageNet预先训练好的VGG16作为示例
打印模型结构可以看到每一层对应的ID编号是什么
通常选择conv后面的特征进行可视化
整个的实现放在类 FeatureVisualization中实现
对于归一化[0, 1]的方法，使用了sigmoid方法
数字5意思是，选择ID编号为5的层。myClass=FeatureVisualization('./input_images/home.jpg',5)
代码如下：
import cv2
import numpy as np
import torch
from torch.autograd import Variable
from torchvision import models
def preprocess_image(cv2im, resize_im=True):
"""
Processes image for CNNs
Args:
PIL_img (PIL_img): Image to process
resize_im (bool): Resize to 224 or not
returns:
im_as_var (Pytorch variable): Variable that contains processed float tensor
"""
# mean and std list for channels (Imagenet)
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
# Resize image
if resize_im:
cv2im = cv2.resize(cv2im, (224, 224))
im_as_arr = np.float32(cv2im)
im_as_arr = np.ascontiguousarray(im_as_arr[..., ::-1])
im_as_arr = im_as_arr.transpose(2, 0, 1) # Convert array to D,W,H
# Normalize the channels
for channel, _ in enumerate(im_as_arr):
im_as_arr[channel] /= 255
im_as_arr[channel] -= mean[channel]
im_as_arr[channel] /= std[channel]
# Convert to float tensor
im_as_ten = torch.from_numpy(im_as_arr).float()
# Add one more channel to the beginning. Tensor shape = 1,3,224,224
im_as_ten.unsqueeze_(0)
# Convert to Pytorch variable
im_as_var = Variable(im_as_ten, requires_grad=True)
return im_as_var
class FeatureVisualization():
def __init__(self,img_path,selected_layer):
self.img_path=img_path
self.selected_layer=selected_layer
self.pretrained_model = models.vgg16(pretrained=True).features
def process_image(self):
img=cv2.imread(self.img_path)
img=preprocess_image(img)
return img
def get_feature(self):
# input = Variable(torch.randn(1, 3, 224, 224))
input=self.process_image()
print(input.shape)
x=input
for index,layer in enumerate(self.pretrained_model):
x=layer(x)
if (index == self.selected_layer):
return x
def get_single_feature(self):
features=self.get_feature()
print(features.shape)
feature=features[:,0,:,:]
print(feature.shape)
feature=feature.view(feature.shape[1],feature.shape[2])
print(feature.shape)
return feature
def save_feature_to_img(self):
#to numpy
feature=self.get_single_feature()
feature=feature.data.numpy()
#use sigmod to [0,1]
feature= 1.0/(1+np.exp(-1*feature))
# to [0,255]
feature=np.round(feature*255)
print(feature[0])
cv2.imwrite('./img.jpg',feature)
if __name__=='__main__':
# get class
myClass=FeatureVisualization('./input_images/home.jpg',5)
print (myClass.pretrained_model)
myClass.save_feature_to_img()
结果如下：
输入图片：
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) 的结果：
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))的结果