James Kelly comments

Results 7 comments of


                                            James Kelly

Add EfficientNet-lite Models?

@galaktyk This is awesome and has saved me a lot of time. Do you have the code you used to create these h5 files? It would be amazing if you...

Add torch ops for d2go models

>Has this PR been included? i.e. is it possible to convert d2go models to coreml? +1 would love to know the status on this PR, adding these ops would be...

Conversion of ONNX End-to-End

No problem, I'll take a look at the new implementation. Thank you for sharing this excellent work.

Error Converting Minimal DETR Implementation - I think it originates from torch.nn.Transformer()

Thanks @TobyRoseman this solved the issue for the model I posted above. I have two models that gave me the same problem so I posted the simplest code to reproduce...

Error Converting Minimal DETR Implementation - I think it originates from torch.nn.Transformer()

If I roll back to version 6.3.0 I get the error message: `RuntimeError: PyTorch convert function for op 'unflatten' not implemented.` I don't see any calls to `unflatten` in the...

Error Converting Minimal DETR Implementation - I think it originates from torch.nn.Transformer()

@TobyRoseman Thanks, changing `shape=(1,ct.RangeDim(1, 512))` -> `shape=(1, 512)` works. Interestingly I have to add `compute_precision=ct.precision.FLOAT32` to the conversion call in order to get the same results with CoreML that I...

Error Converting Minimal DETR Implementation - I think it originates from torch.nn.Transformer()

The values aren't too far out, but just enough to make the predictions unreliable. I found that setting the precision to `FLOAT32` and then running this code: ``` import coremltools.optimize.coreml...