onnx-coreml icon indicating copy to clipboard operation
onnx-coreml copied to clipboard

ONNX to Core ML Converter

Results 55 onnx-coreml issues
Sort by recently updated
recently updated
newest added

Command CoreMLModelCompile failed with a nonzero exit code i have successfully converted the onnx model (originally in pytorch) using the following: `mlmodel = convert('NetModel.onnx', target_ios='13', custom_conversion_functions={'Upsample': _convert_upsample})` and when i...

question

## 🐞Describe the bug I have tried the virtual environment and in my main environment. "`from onnx-coreml import convert`" causes the problem ## Trace If applicable, please paste the error...

bug

hi, all, has anyone succeed to convert mobilenetv3 onnx to coreml yet? I found it will get `Error while converting op of type: Conv. Error message: provided number axes -1...

bug

Was there a version update? (i don't think so but i feel i'm going crazy) A week ago i was able to convert the `Softmax` layer: ``` softmax = nn.Softmax(dim=1)...

question

## ❓Help Hi ONNX partner, We have released TestPyPI packages of ONNX 1.9.0: [onnx ](https://test.pypi.org/project/onnx/ )(onnx 1.8.204 is the latest version number for testing now). Please verify it and let...

question

I've been having trouble converting the Huggingface PyTorch DistilBert to CoreML. Initially the model converted but produced incorrect results when measured against PyTorch. Attempting to verify the ONNX model using...

question

## 🐞Describe the bug The readme file says that examples have been moved to coreml repo, but the link results in 404.

bug

## ❓Question Is it possible to convert a pytorch model withtout classification layer into mlmodel? I don't know how to do it because in the example, I am asked to...

bug

## 🐞Bug Description Hi using opset_version=11, I'm trying to convert Architecture with Upscaling Layers and ReflectionPad2d from Pytorch to CoreML ## Trace 1/214: Converting Node Type Sub 2/214: Converting Node...

bug

I'm trying to convert a `Pipeline` which uses categorical conversion with `pd.get_dummies`, and for some reason I'm getting an error when trying to convert the fitted Pipeline (although the fitting...