Inquiry about memory usage compare to maskrcnn_benchmark repository.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
I cross checked that FasterRCNN in torchvision and in https://github.com/facebookresearch/maskrcnn-benchmark/ are almost identical.
I tried both repository and compared memory usage. What I found is that maskrcnn_benchmark repository use less GPU. I am using Titan xp pascal 1 GPU, and I could run it with 5 batch images for maskrcnn repo, but for torchvision, 3 batch was maximum.
Can I know why?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by comparing the FasterRCNN implementations in torchvision and the referenced maskrcnn-benchmark repository under the stated Titan XP, one-GPU setup. Establish a reproducible memory comparison across the reported batch sizes; done would be an evidence-based explanation of the difference or a confirmed, actionable memory bug.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100