Closed shinh closed 5 years ago
| | ONNX-Chainer | Chainer-compiler | F.huber_loss | (1) | (3) | F.normalize | PR, merged | Need chainerx op | F.roi_pooling_2d | PR | Need chainerx op | F.unpooling_2d | No ONNX Op | Need chainerx op | F.upsampling_2d | MaxUnpool (*2) | Need chainerx op | L.DilatedConvolution2D | OK | Need chainerx op
(1) Sub, Abs, Where, Mul(Pow) ? onnxruntime lacks Where (2) onnxruntime master only. PR is ready. (3) same as (1). chainerx op is easier
comments from tanaka-san
Memo: chainercv/examples/fpn/demo.py needs Unpooling2D
and ROIAverageAlign2D
F.unpooling_2d
looks similar to Upsample, but as per tanaka-san, it cannot fully represent chainer's semantics for ksize=3
or outsize!=None
Most of them are handled.
100% coverage for https://github.com/chainer/chainercv/tree/master/chainercv/links/model could be a great goal for both elichika and compiler+runtime.
Looking at the result of the above command, the following ops look important.
Some of the above have standard ONNX ops. It would be also great if we add support of them in ONNX-chainer.