I hope you can provide 3D align-pooling layer directly. Pray.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
I see that 2D align-pooling has been implemented, but there is no 3D one. I do target detection of 3D voxels. The input data format is (batch, channel, depth, height, w). I customized a 3D align-pooling Op. However, there is a big problem in the deployment. The custom OP needs to be registered in the torchscript. In this way, the model can be exported normally, and finally the model can be loaded on the C + + side.I tried for months, but it didn't work. I hope you can provide 3D align-pooling layer directly. Pray.
This is the function:
torchvision.ops.roi_align(input, boxes, output_size, spatial_scale=1.0, sampling_ratio=-1)
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 from the existing 2D torchvision.ops.roi_align implementation and the reported input shape (batch, channel, depth, height, width). Determine the requirements for a 3D align-pooling layer, including TorchScript registration, model export, and loading on the C++ side; done means the requested operation is available without the reported custom-operator deployment problem.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100