pytorch / pytorch/vision

process.wait(0) when traing faster_rcnn

Open
#1,643 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

awaiting response help wanted module: reference scripts needs discussion needs reproduction topic: object detection
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

662FE0EB-CD0B-4FED-B036-CB5964218D31

I use the provided code to train my data using faster_rcnn on 2 GPUs. The program always stops at epoch 27(just stop, no more output), and when I use ctrl+c to interrupt the program, the content is as shown in the pic.

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 with references/detection/train.py, which the report uses to train faster_rcnn on 2 GPUs. Reproduce the stop at epoch 27 and inspect the interrupt output shown in the attached image. Done means identifying the cause of the process.wait(0) stop and confirming the training run can proceed.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.