Toby Roseman comments

Results 543 comments of


                                            Toby Roseman

Adding enumerated sizes works for single input model but not multiple inputs models.

Using coremltools 6.0, both `predict` class now run without error.

compiler error: Espresso exception: "Invalid blob shape": Cannot broadcast blobs

ONNX support has been removed in [coremltools 6.0](https://github.com/apple/coremltools/releases/tag/6.0).

return NaN values when passing through specific convolution layer

Multi-backend Keras support has been removed in [coremltools 6.0](https://github.com/apple/coremltools/releases/tag/6.0).

Error converting sklearn linear regression model

We now support the latest version of Scikit-Learn (`1.1.2`). So I believe this is fixed. Can anyone confirm this is fixed? Or give us step to reproduce the issue, if...

Converting Hugging Face model to CoreML: Torch var attention_mask.1 not found in context

Since we have not heard back here, I'm going to close this issue.

Keras layer '<class 'keras.layers.normalization_v2.BatchNormalization'>' not supported.

Multi-backend Keras support has been removed in [coremltools 6.0](https://github.com/apple/coremltools/releases/tag/6.0).

NotImplementedError: Conversion for TF op 'MLCMatMul' not implemented.

Seems like this issue has been fixed. Since we have not heard back, I'm going to close this issue.

RuntimeError: PyTorch convert function for op 'pixel_unshuffle' not implemented.

[We now support torch's `pixel_unshuffle`](https://github.com/apple/coremltools/blob/da9b8ca98e5a758290f6a5703a995b56c22288c6/coremltools/converters/mil/frontend/torch/ops.py#L678-L683).

Conversion error for a model with the `transpose` operation

Fixed by #1563.

How to pass multiple inputs contain integer in pytorch.jit.trace and coreml convert?

Since we have not heard back here, I'm going to close the issue.