胡钧耀

icon indicating a website link junyaohu.github.io icon indicating an email [email protected]

icon company Nankai University icon location Jinnan District, Tianjin Provience icon location PhD @ Nankai University, researching on action recognition, image sentiment analysis, and vision generative AI.

Results 4 issues of 胡钧耀

what the function of self.compute_latent_shifts ?

2 comment

In ddpm https://github.com/CompVis/latent-diffusion/blob/2b46bcb98c8e8fdb250cb8ff2e20874f3ccdd768/ldm/models/diffusion/ddpm.py#L686-L689

Update train.py

solve problem when training. ``` Traceback (most recent call last): File ".../slamp/train.py", line 139, in main(opt) File ".../slamp/train.py", line 68, in main v.train() AttributeError: 'Namespace' object has no attribute 'train'...

why did not add conditional frames into videos for FVD metric

https://github.com/google-research/fitvid/blob/31461d22184248970292c0ebf807725fef7f97f7/train.py#L60-L65 Hello, I see other paper like [MCVD](https://github.com/voletiv/mcvd-pytorch/issues/19), [SRVP](https://github.com/edouardelasalles/srvp/blob/3e90a748db04d182290132163fea5b0410ea2452/test.py#L292-L302) and [SLAMP](https://github.com/kaanakan/slamp/blob/4f5fc0707a4843d34dd1cb98f4939f1357e05183/calculate_fvd.py#L25-L31) are all add conditional frames into videos for FVD calculation.

C2二维码用户自定义颜色

希望能像A模板的二维码一样能设置信息点颜色，目前我是通过PS后期进行颜色的修改的，希望能进行改进，谢谢开发者！