HI, authors,
Great work! My question about the implementation is as follows:
During training, I found that you randomly set 20% of CLIP's input as zeros tensors,
however, during testing, you concatenate the output of clip embedding with zero tensors, like this:
As far as I am concerned, to align the training and testing, should we randomly set 20% of the output of CLIP as zero tensors rather than the input of CLIP model?
HI, authors, Great work! My question about the implementation is as follows:
During training, I found that you randomly set 20% of CLIP's input as zeros tensors,![image](https://github.com/MooreThreads/Moore-AnimateAnyone/assets/37365950/8510efbd-1647-4441-8b30-0a6d1450617d)
however, during testing, you concatenate the output of clip embedding with zero tensors, like this:![image](https://github.com/MooreThreads/Moore-AnimateAnyone/assets/37365950/2b6cf6b2-9495-4c80-8a0c-82bc59735b75)
As far as I am concerned, to align the training and testing, should we randomly set 20% of the output of CLIP as zero tensors rather than the input of CLIP model?