Toby Roseman
Toby Roseman
```python ----> 1 import transforms as T ModuleNotFoundError: No module named 'transforms' ``` Where is this package coming from? I'm certainly familiar with the `transformers` package but not the `transforms`...
I have the `transformers` package installed. Your code is importing `transforms` not `transformers`. There is no `PILToTensor` or `ConvertImageDtype` under the `transformers` package. `transforms` looks like a pretty obscure (i.e....
I've never heard of something like this before. How fast was your model loading with coremltools 5.2? How long is it loading with 6.2? Are these numbers consistent?
We probably need a more general solution of #1917.
@mlaves - to request changes to the Core ML Framework, please use [the Feedback Assistant](https://developer.apple.com/bug-reporting/).
There is not way to add this preprocessing. I recommend you add this functionality to your PyTorch model prior to conversion. As you already mention, adding this functionality directly to...
@anuar12 - I am not able to reproduce this problem. I need to know how `torch_model` is created.
This is indeed a bug. Looking at `model.get_spec()`, the return values are coming from an identity layer. This is also an issue for `convert_to="mlprogram"`.
We have only "experimental" support for untraced PyTorch models. Can you give us a minimal example to reproduce this issue?
This GitHub repository is for the coremltools Python package. This isn't really the right forum to ask about `kCVPixelFormatType` or `CVPixelBuffer`. For questions like that, I recommend asking in [the...