facebookresearch / facebookresearch/segment-anything
How to train SAM in batches?
Open
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
I have more than one target objects to segment in the image. Is it possible to feed batches into the model? It is possible to feed the batches into an image encoder. What about a prompt encoder? As I understand, the shape of the prompt batch should be BxNx4 for bounding boxes, where B is the batch size, N is the number of bounding boxes in image. I have checked the source code and prompt encoder expects a shape of Bx4. Am I missing something?
Contributor guide
Assessment
This issue has not been assessed yet.