CCN icon indicating copy to clipboard operation
CCN copied to clipboard

Connective Cognition Network for Directional Visual Commonsense Reasoning

Results 3 CCN issues
Sort by recently updated
recently updated
newest added

Bumps [flask-cors](https://github.com/corydolphin/flask-cors) from 3.0.7 to 3.0.9. Release notes Sourced from flask-cors's releases. Release 3.0.9 Security Escape path before evaluating resource rules (thanks @​praetorian-colby-morgan). Prior to this, flask-cors incorrectly evaluated CORS...

dependencies

前辈你好,我是研一的学生,研究方向为visual storytelling, 我目前在重写《No Metrics Are Perfect:Adversarial Reward Learning for Visual Storytelling》,遇到了很多问题。 我看见您在原作者的GitHub下面留言了,如果可以的话,我们可以给个联系方式(邮箱也可以),我想您请教几个问题吗? 因为我们实验室没人研究这个,我属于摸着石头过河,希望前辈给个机会,谢谢您。 我的邮箱是[email protected] 我的vx是13093193765 我的QQ是841222073 万分感谢,谢谢您,祝您生活愉快!!!!!!!!!!

https://github.com/AmingWu/CCN/blob/2254049e5b090952406f14fbf4a63b4e30e99a17/train/train.py#L242 你好,按照论文里写的这里softmax是对每一行进行操作,obj_graph的维度是三维的,我的理解应该是对最后一维进行softmax,dim的设置应该是2或者-1吧?