onnx autocast raise error with dynamic input shape

[lzcchl]

I think this is no good, because now a lot of model is dynamic input shape, I think it shoulds be a warning rather than a error. (ValueError: Input shape from 'images' does not match provided input shape: [0, 3, 0, 0] vs [1, 3, 480, 640]. Please make sure that your calibration data matches the ONNX input shapes.)

https://github.com/NVIDIA/Model-Optimizer/blob/main/modelopt/onnx/autocast/referencerunner.py#L93
raise ValueError ==>logger.warning

will it changed future release?

[jricker2]

I ran into the same issue, it was fixed in this commit 24e3587

Hopefully this will make it into 0.42, would be very useful as it is currently preventing me from upgrading from 0.39