Pytorch自带Resnet50特征图heat map热力图可视化

最新推荐文章于 2024-08-30 08:59:25 发布

IT-Sunshine

最新推荐文章于 2024-08-30 08:59:25 发布

阅读量3.4k

点赞数 1

本文链接：https://blog.csdn.net/weixin_39338645/article/details/102916492

版权

本文展示了使用PyTorch实现Resnet50模型对输入图像进行处理，通过热力图可视化特征图的过程。代码运行结果显示了经过各个层后的特征信息，包括卷积、批量归一化、池化等，最终得出前五大预测类别及其得分。

摘要由CSDN通过智能技术生成

代码如下：

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 = r'features_whitegirl'
savepath =r"D:/hexiaojuan/coding/lianxi/hatmap_RGB"
#savepath='D:\hexiaojuan\coding\Unsupervised-Person-Re-identification-Clustering-and-Fine-tuning-master\dataset\DukeMTMC-reID\DukeMTMC-reID\bounding_box_test\0030_c1_f0056923'
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=0.05, hspace=0.05)
    for i in range(width * height):
        plt.subplot(height, width, i + 1)
        plt.axis('off')
        img = x[0, i, :, :]
        pmin = np.min(img)
        pmax = np.max(img)
        img = ((img - pmin) / (pmax - pmin + 0.000001)) * 255  # float在[0，1]之间，转换成0-255
        img = img.astype(np.uint8)  # 转成unit8
        img = cv2.applyColorMap(img, cv2.COLORMAP_JET)  # 生成heat map
        img = img[:, :, ::-1]  # 注意cv2（BGR）和matplotlib(RGB)通道是相反的
        plt.imshow(img)
        print("{}/{}".format(i, width * height))
    fig.savefig(savename, dpi=100)
    fig.clf()
    plt.close