ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
How to obtain consistent input and output resolutions?
Open
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
For example, if my input RGB image has a resolution of 640x640x3, but the output depth image (the inference parameter 'process_res' is set to 640) becomes 644x644 in resolution, how can I ensure that the output resolution matches the input resolution? Alternatively, how can I remove the extra 4 pixels in both the horizontal and vertical directions from the output?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.