duanyiqun / duanyiqun/DiffusionDepth
A question about the pred noise.
Open
- Dominant language
- Python
- Stars
- 341
- Forks
- 23
- PR merge metrics
- No merged PRs in 30d
Description
Thanks for ur excellent work!
I have a question about ddim loss which is computed with noise and pred noise.
The pred noise, which is the output of ScheduledCNNRefine Model is >0, because the last activation function is RELU.
However, shouldn't the randn noise contains both >0 parts and <0 parts?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.