Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Inference with onnx (Image matting) #65

Merged
merged 3 commits into from
Feb 19, 2021
Merged

Conversation

manthan2305
Copy link

  1. Added a modified version of the modnet.py file without pred_semantic and pred_details as both returns None when inference=True, which will make it easy to convert onnx model.

  2. export_modnet.py will take checkpoint file as an input and generate onnx model with dynamic input and output shape.

  3. Inference code is also provided for image matting.

  4. Try this colab demo

  5. Download modnet.onnx

manthandrive01 added 3 commits February 11, 2021 23:52
@ZHKKKe ZHKKKe merged commit 39298cb into ZHKKKe:master Feb 19, 2021
@ZHKKKe
Copy link
Owner

ZHKKKe commented Feb 19, 2021

@manthan3C273
I have processed this pull request.
The code has been reorganized under the folder onnx.
Big thanks.

@manthan2305
Copy link
Author

Thank you, @ZHKKKe
Your changes made it easy to access. And I would love to contribute more.!

@ZHKKKe
Copy link
Owner

ZHKKKe commented Feb 20, 2021

@manthan3C273 We are open for any other contributions!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants