论文

论文名称： Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks

数据集： 无

pytorch项目地址： grad-cam

最新进展

⭐ 支持的8个method为：gradcam、scorecam、gradcam++、ablationcam、xgradcam、eigencam、eigengradcam、layercam。

Method	What it does
GradCAM	Weight the 2D activations by the average gradient
GradCAM++	Like GradCAM but uses second order gradients
XGradCAM	Like GradCAM but scale the gradients by the normalized activations
AblationCAM	Zero out activations and measure how the output drops (this repository includes a fast batched implementation)
ScoreCAM	Perbutate the image by the scaled activations and measure how the output drops
EigenCAM	Takes the first principle component of the 2D Activations (no class discrimination, but seems to give great results)
EigenGradCAM	Like EigenCAM but with class discrimination: First principle component of Activations*Grad. Looks like GradCAM, but cleaner
LayerCAM	Spatially weight the activations by positive gradients. Works better especially in lower layers

⭐ 支持的smoothing模式为aug_smooth和eigen_smooth。

To reduce noise in the CAMs, and make it fit better on the objects, two smoothing methods are supported:

aug_smooth=True

Test time augmentation: increases the run time by x6.

Applies a combination of horizontal flips, and mutiplying the image by [1.0, 1.1, 0.9].

This has the effect of better centering the CAM around the objects.
eigen_smooth=True

First principle component of activations*weights

This has the effect of removing a lot of noise.

⭐ 使用的模型为resnet50。

./models/torch2paddle.py脚本：用于保存torchvision.models.resnet50的预训练模型到本地；

将resnet50 torch的预训练模型resnet50.pth转换为resnet50 paddle的预训练模型resnet50.pdparams。

⭐ 默认加载的图片input_img为./examples/both.png。