[v1.x] ONNX: fix error handling when op is not registered #20261
Conversation
|
Hey @Zha0q1 , Thanks for submitting the PR
CI supported jobs: [miscellaneous, clang, edge, unix-cpu, sanity, unix-gpu, website, centos-gpu, centos-cpu, windows-gpu, windows-cpu] Note: |
mseth10
added
the
pr-awaiting-testing
| @@ -91,15 +91,22 @@ def convert_layer(node, **kwargs): | |||
|
|
|||
| op = str(node["op"]) | |||
| opset_version = kwargs.get("opset_version", onnx_opset_version()) | |||
| if opset_version < 12: | |||
| logging.warning('Your ONNX op set version is %s, ' % str(opset_version) + | |||
| 'which is lower than then lowest tested op set (12), please consider ' | |||
There was a problem hiding this comment.
is there some variable we can use to print the op set version instead of hard coding "12" in this message? its likely we may forget to update it later...
There was a problem hiding this comment.
I think unlike cuda where we keep a supported window, the minimum supported version for onnx is fixed at 12 (latest is 14). When new opeset is released we can add support for it without removing the previous opset support
| continue | ||
| convert_func = MXNetGraph.registry_[op_version][op] | ||
| break | ||
|
|
||
| if convert_func is None: | ||
| raise AttributeError("No conversion function registered for op type %s yet." % op) |
There was a problem hiding this comment.
can you add a comment here to explain why this would happen? (ie. is it because the op is not supported or because the installed version of onnx is too old?)
mseth10
added
pr-work-in-progress
mseth10
added
pr-awaiting-testing
mseth10
added
pr-work-in-progress
fixes #20260