pytorch可视化 resnet50特征图

参考：https://blog.csdn.net/u012435142/article/details/84711978

Python可视化resnet50所有层特征图
使用pytorch中预训练模型,在网络inference的过程中显示特征图的每个通道.
文章目录
代码
input image [1,3,224,224]
conv1 [1,64,112,112]
bn1_relu [1,64,112,112]
maxpool [1,64,56,56]
layer1 [1,256,56,56]
layer2 [1,512,28,28]
layer3 [1,1024,14,14]
layer4 [1,2048,7,7]
avgpool [1,2048]
fc [1,1000]
代码
import cv2
import time
import os
import matplotlib.pyplot as plt
import torch
from torch import nn
import torchvision.models as models
import torchvision.transforms as transforms
import numpy as np

savepath='vis_resnet50/features_elephant'
if not os.path.exists(savepath):
    os.mkdir(savepath)


def draw_features(width,height,x,savename):
    tic=time.time()
    fig = plt.figure(figsize=(16, 16))
    fig.subplots_adjust(left=0.05, right=0.95, bottom=0.05, top=0.95, wspace