abcdvzz

Training process.

2

Could you please tell me how to train the models from scratch? I'm new in Pytorch and I cannot find the training script. Thank you.

How to select the best model?

1

Hi there, thank you for your wonderful work. I have a naive question. There are 154 models in the process_text2video model zoo. How can we select the most suitable pre-trained...

可否增加subject内容以及删选

1

比如某篇论文的 Subjects: Image and Video Processing (eess.IV); Machine Learning (cs.LG); Applied Physics (physics.app-ph); Instrumentation and Detectors (physics.ins-det) 首先可以考虑显示 subjects 内容，这样方便筛选，比如这一个可能和物理相关，就直接略过了； 第二是不是可以增加这样一个功能，比如某篇论文CV 和 ML 都有，这时候选择ML和CV两项，ML为第一项，CV第二项，先看ML，再看CV的时候，自动把ML的paper去掉，因为已经看过了。

error occurs when set gradient_checking = True during stage 2

2

File "./Moore-AnimateAnyone/src/models/mutual_self_attention.py", line 154, in d.unsqueeze(1).repeat(1, video_length, 1, 1), TypeError: repeat(): argument 'repeats' must be tuple of ints, but found element of type NoneType at pos 2d.unsqueeze(1).repeat(1, video_length, 1, 1),...

Can anyone tell me how to visualize the cross attention and self attention maps in fig. 3?

插件右键跳转可以恢复成本页面打开么

3

最新更新后，我发现右键跳转成了新页面打开，可以恢复成原页面打开么，或者变成可设置的选项，谢谢。