赞
踩
在pycharm终端中输入 pip install grad-cam
pytorch-grad-cam
这个库可以用来干啥?这个库提供了多种类激活映射方法,具体如下:
方法 | 干啥的 |
GradCAM | Weight the 2D activations by the average gradient 通过平均梯度对2D激活进行加权 |
GradCAM++ | Like GradCAM but uses second order gradients 与GradCAM类似,但使用二阶梯度 |
XGradCAM | Like GradCAM but scale the gradients by the normalized activations 类似于GradCAM,但通过归一化激活来缩放梯度 |
AblationCAM | Zero out activations and measure how the output drops (this repository includes a fast batched implementation) 清除激活并测量输出如何下降(此存储库包含快速批处理实现) |
ScoreCAM | Perbutate the image by the scaled activations and measure how the output drops 通过缩放的激活来修改图像并测量输出是如何下降的 |
EigenCAM | Takes the first principle component of the 2D Activations (no class discrimination, but seems to give great results) 采取的二维激活的第一个主要组成部分(没有阶级歧视,但似乎给伟大的结果) |
EigenGradCAM | Like EigenCAM but with class discrimination: First principle component of Activations*Grad. Looks like GradCAM, but cleaner 如EigenCAM但是带有阶级歧视:激活*Grad的第一个主要组成部分。看起来像GradCAM但是更干净 |
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。