Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ONNX frontend bug with MissingOperator #136

Closed
victorromeo opened this issue Nov 30, 2020 · 1 comment
Closed

ONNX frontend bug with MissingOperator #136

victorromeo opened this issue Nov 30, 2020 · 1 comment

Comments

@victorromeo
Copy link

In #133 Missing Operator was found to be incorrectly using dict key, due to missing Namespace term.
utensor_cgen/backend/utensor/code_generator/rearch/_operators/_impls.py

class _MissingOperator(_Operator):
  op_type = "_MissingOperator"

  def get_declare_snippet(self, op_var_name, with_const_params=True):
    return None

  def get_eval_snippet(self, op_var_name, op_info, tensor_var_map):
    return MissingOpEvalSnippet(op_info, op_var_name, tensor_var_map)

  def get_construct_snippet(self, op_var_name):
    return None


OperatorFactory._operators[_MissingOperator.op_type] = _MissingOperator # <== key should be a 2 term tensor, (namespace, op_type)
@dboyliao
Copy link
Member

dboyliao commented Dec 1, 2020

That was on purpose, since _MissinOperator is a special operator which is used for printing out information only.
Anyway, it's fixed on develop.
Closing issue.

@dboyliao dboyliao closed this as completed Dec 1, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants