pytorch / pytorch/vision

Inquiry about memory usage compare to maskrcnn_benchmark repository.

Open
#1,150 7 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

awaiting response module: ops
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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.