Philip Lassen
Philip Lassen
> I saw upsample beams deprecated. Can we use onnx.resize to express onnx.upsample? This is already done in decompose. The reason I added a shape inference implementation is that in...
@chentong319 thanks for the review, I've updated the PR to address the comments. Please let me know if you would like any further changes
I can likely add support for the ingestion of opset 17 by the end of next week
Yes next week would work well too
We are making really good progress on this Only two PRs remaining: - #1771 - #1776
Actually there are two more after those - #1779 - #1780 But that is it!
Yes, it's been available since opset 18. If you want it working with `torch_scatter`, you can look at this [file](https://github.com/philass/onnx-experiments/blob/master/export-custom.py) for inspiration
@gramalingam, @liqunfu Thanks for the clarification guys! Much appreciated.