显示feature的heatmap热力图

最新推荐文章于 2025-06-01 22:37:20 发布

兜里没钱但是有纸

最新推荐文章于 2025-06-01 22:37:20 发布

阅读量1.5k

点赞数

文章标签：图像处理

本文链接：https://blog.youkuaiyun.com/zhang911007xing/article/details/113184037

版权

显示feature的heatmap

import cv2
import numpy as np
import scipy.misc

# feature：numpy array; 从网络的forward过程当中保存下来的feature map
# row_image：numpy array; 3*224*224
# output_jpg_name: eg. "out.jpg"

def show_heatmap(feature,output_jpg_name,row_image):
    data = feature
    heatmap = data.sum(0)/data.shape[0]
    heatmap = np.maximum(heatmap, 0)
    heatmap /= np.max(heatmap)
    heatmap = 1.0 - heatmap # 也可以不写，就是蓝色红色互换的作用
    heatmap = cv2.resize(heatmap, (224,224)) # (224,224)指的是图像的size，需要resize到原图大小
    heatmap = np.uint8(255 * heatmap)
    heatmap = cv2.applyColorMap(heatmap, cv2.COLORMAP_JET)
    row = row_image
    row = row.transpose(1,2,0)
    superimposed_img = heatmap*1.0 + row*0.5 # 1.0 和 0.5代表heatmap和row image的强度占比，可调整
    scipy.misc.imsave(output_jpg_name,superimposed_img)