onnx / onnx/models

Script to convert Mask R-CNN model to ONNX

Open
#421 4 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

Hi all,
I am able to load and use your ONNX Mask R-CNN model following your very detailed instructions, which is great.

Given that, I was wondering if you could provide more details around the script you used to convert the original trained model to ONNX.
I come from a PyTorch background and I am having hard times to get the official torchvision model exported correctly to ONNX, so I hoped you guys could share the code you used to do that (even if you didn't train the model in PyTorch in the first place).
It would be super helpful!

Thanks a lot

Contributor guide

No contributing guide indexed for this repository

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 the linked Mask R-CNN model instructions and the official torchvision export path mentioned in the issue. Determine which conversion script or procedure produced the linked ONNX model, then document it and verify that the documented process can reproduce a usable ONNX Mask R-CNN model.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
documentation, machine-learning
Issue type
Documentation
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.