You are viewing a plain text version of this content. The canonical link for it is here.

Posted to discuss-archive@tvm.apache.org by Jorge via Apache TVM Discuss <no...@discuss.tvm.ai> on 2021/08/17 20:01:18 UTC

[Apache TVM Discuss] [Questions] [PyTorch] dyn.strided_slice loses shape information


Hi,

I think that I am having a similar behavior when trying to compile [YOLOX-ONNX](https://github.com/Megvii-BaseDetection/YOLOX/tree/main/demo/ONNXRuntime) models in TVM. 

```
%40 = dyn.strided_slice(%0, %8, %9, meta[relay.Constant][7] /* ty=Tensor[(4), int64] */, 
begin=None, end=None, strides=None, axes=None) /* ty=Tensor[(?, ?, ?, ?), float32] */;
```

Can you support YOLOX?

Thanks!





---
[Visit Topic](https://discuss.tvm.apache.org/t/pytorch-dyn-strided-slice-loses-shape-information/10655/7) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/fc6008c76f92dc826d88746eb3e06da7ad39d01067aafc99293172017a358e78).