onnx-coreml
onnx-coreml copied to clipboard
ONNX to Core ML Converter
I'm trying to convert the ClusterGAN and the conversion fails in two places. The first error is a Slice in the encoder that fails in the `forward()` function: ``` def...
Re-applying fix that was approved in PR: https://github.com/onnx/onnx-coreml/pull/524 I also experienced the issue that this patch resolves, and am re-opening since I have signed the CLA.
## 🐞Describe the bug onnx to CoreML, but onnx's upsample BILINEAR cannot find the corresponding op in CoreML; CoreML : message UpsampleLayerParams { /** * Scaling Factor. * Must be...
When i installed from source using install-develop.sh, i got this error below. It reads version from onnx_coreml.__init__ and it also imports convert that needs coremltools. So, it occurs error no...
## 🐞Describe the bug A clear and brief description of what the bug is. I converted to CoreML and then got the wrong prediction. ## Trace If applicable, please paste...
Hello, I don't know if you need such feature, but since it can be a useful change I share it with you. The only options of `convert-onnx-to-coreml` is the output...
## ❓Question in `_make_coreml_output_features` in `converter.py` you don't allow shape of 2 (B, C), why is it? this is quite common in classification networks (such as mobileNet).
## 🐞Describe the bug When converting a model that has a Slice op immediately after an Expand op, it crashes. ## Trace ``` Requirement already satisfied: onnx==1.6.0 in /usr/local/lib/python3.6/dist-packages (1.6.0)...
## 🌱 Describe your Feature Request Support Path (from pathlib) as type of argument `model` https://github.com/onnx/onnx-coreml/blob/7a630c113b27c8cc1a83412ce1dbfda77f9f8422/onnx_coreml/converter.py#L447 `convert` doesn't support Path as type of argument `model ` but `onnx.load` supports Path...