Generate a test image that corresponds to that part of the code.

[1691077362]

Hi,
Thanks for sharing the code!!!
Why did I test with MSMT17 and only get map data, but not the generated images.
Generate a test image that corresponds to that part of the code.

[1691077362]

你好，
感谢分享代码！！！
为什么我用msmt17进行测试最后只得到了map数据，而没有得到生成的图片。
还有就是生成测试后的图片，对应着那部分的代码。 @ @CHENGY12

[CHENGY12]

Thanks for your interest in our paper.
APNet is a discriminative model for the person ReID task. Given a benchmark (including MSMT), APNet extracts the features of both query and gallery images and matches them for evaluation. This evaluation process is not related to image generation. The details can be found in the paper. Hope you find it helpful.

[1691077362]

不好意思我可能能没表达清楚，我想要的是数据可视化的代码。

[1691077362]

@CHENGY12 Can you share the code for your visualization part? I really won't, thanks

[Gutianpei]

@CHENGY12 Can you share the code for your visualization part? I really won't, thanks

Hello,

As mentioned in our paper, we used Grad-CAM to visualize the attention map. Please consider using the open-source implementation of Grad-CAM such as https://github.com/jacobgil/pytorch-grad-cam.

[1691077362]

@Gutianpei thank you