LoraLinH / Boosting-Crowd-Counting-via-Multifaceted-Attention

Official Implement of CVPR 2022 paper 'Boosting Crowd Counting via Multifaceted Attention'
MIT License
106 stars 20 forks source link

关于可视化代码的问题 #14

Open Sunshine-L59 opened 1 year ago

Sunshine-L59 commented 1 year ago

作者您好,我在运行可视化代码save_attention.py时,遇到了以下问题:

RuntimeError: requested resize to 19x16 (304 elements in total), but the given tensor has a size of 512 (512 elements). autograd's resize can only change the shape of a given tensor, while preserving the number of elements.

请问这个问题应该怎样解决呢?我应该如何可视化才能分别输出论文中图4所示的每个特征点所关注的区域?

shaun881017 commented 1 year ago

请问这问题解决了吗? 如果解决了能提供解决方法吗?