Henry Tao

Great op! Thanks @pokidyshev

@gorisanson Thanks for replying. But I found that when the game begin (by inviting people to my room), it goes pretty smooth on both sides, even though I'm at the...

This look like a bug in the complex op type inference.

@alealv does the `torch.jit.trace` works for your model? That is what we recommend in generally, instead of using `torch.jit.script`.

This issue should be fixed in the `8.0b2` release. Please give it a try.

@ayes-vjanssen thanks for using coremltools. This is a good question, in fact, coremltools doesn't support `inputs` when then source model is `milinternal`, I believe this will be a useful feature...

@ayes-vjanssen You are correct, right now the `ImageType` input can only be supported through pytorch / TF conversion

@vyshemirsky Coreml conversion will have a parity of your original LSTM model. i.e., if your original model is 1 input and 1 output, so do the converter coreml model. I...

@gsigms Thanks for filing this issue. However, I strongly won't recommend using the int32 input data type, since the most of the coreml op only accept float inputs. Please change...