onnxmltools
onnxmltools copied to clipboard
Unsupported shape calculation for operator visionFeaturePrint - Converting CoreML to ONNX
Seems to be unsupported
Traceback (most recent call last):
File "convert.py", line 9, in <module>
onnx_model = onnxmltools.convert_coreml(coreml_model, 'Example Model')
File "/Library/Python/3.7/site-packages/onnxmltools/convert/main.py", line 18, in convert_coreml
custom_conversion_functions, custom_shape_calculators)
File "/Library/Python/3.7/site-packages/onnxmltools/convert/coreml/convert.py", line 60, in convert
topology = parse_coreml(spec, initial_types, target_opset, custom_conversion_functions, custom_shape_calculators)
File "/Library/Python/3.7/site-packages/onnxmltools/convert/coreml/_parse.py", line 467, in parse_coreml
topology.compile()
File "/Library/Python/3.7/site-packages/onnxconverter_common/topology.py", line 632, in compile
self._infer_all_types()
File "/Library/Python/3.7/site-packages/onnxconverter_common/topology.py", line 508, in _infer_all_types
operator.infer_types()
File "/Library/Python/3.7/site-packages/onnxconverter_common/topology.py", line 110, in infer_types
registration.get_shape_calculator(self.type)(self)
File "/Library/Python/3.7/site-packages/onnxconverter_common/registration.py", line 68, in get_shape_calculator
raise ValueError('Unsupported shape calculation for operator %s' % operator_name)
ValueError: Unsupported shape calculation for operator visionFeaturePrint
Ran into the same issue, just trying to convert a very simple image classification model. Is this not yet supported in general for CoreML to ONNX?
Im running into this issue still also.
I too, am running into this issue.
Just ran into this issue today as well.
same. Anyone found the fix?
Hi guys, any update on this? Are these models not suported? If so, how can you export coreml to another format?
Same here, just got the same error converting a basic image classification into ONNX, using onnxmltools.
I have been having this issue for over a year now lol. I am looking for a clean way to convert a coreml model to a pytorch
On Wed, Dec 22, 2021 at 1:42 AM Santosh @.***> wrote:
Same here, just got the same error converting a basic image classification into ONNX, using onnxmltools.
— Reply to this email directly, view it on GitHub https://github.com/onnx/onnxmltools/issues/354#issuecomment-999325935, or unsubscribe https://github.com/notifications/unsubscribe-auth/ASY4UEDHNUAQ5BOJD3AK7HLUSFXMLANCNFSM4JQ6FVUQ . You are receiving this because you commented.Message ID: @.***>
Still not working in 6.0 :(
Did this receive any fix on the current version ?
To my understanding it will never be fixed. I think Apple intentionally stopped supporting their model to be converted. But it has supported the other direction, converting from other libraries to coreML.
On Fri, Jan 13, 2023 at 12:46 AM abhishekwynum @.***> wrote:
Did this receive any fix on the current version ?
— Reply to this email directly, view it on GitHub https://github.com/onnx/onnxmltools/issues/354#issuecomment-1381343576, or unsubscribe https://github.com/notifications/unsubscribe-auth/ASY4UEE4AVHCXCS4VI5KEL3WSDT3RANCNFSM4JQ6FVUQ . You are receiving this because you commented.Message ID: @.***>