Skip to content
This repository was archived by the owner on Apr 8, 2025. It is now read-only.

Bump pytorch to 1.7#660

Closed
tholor wants to merge 1 commit intorefactor_processor_qafrom
torch_1.7
Closed

Bump pytorch to 1.7#660
tholor wants to merge 1 commit intorefactor_processor_qafrom
torch_1.7

Conversation

@tholor
Copy link
Copy Markdown
Member

@tholor tholor commented Dec 21, 2020

Let's update pytorch...

@tholor
Copy link
Copy Markdown
Member Author

tholor commented Dec 21, 2020

Test for onnx conversion currently fails with

    def run(self, output_names, input_feed, run_options=None):
        """
        Compute the predictions.
    
        :param output_names: name of the outputs
        :param input_feed: dictionary ``{ input_name: input_value }``
        :param run_options: See :class:`onnxruntime.RunOptions`.
    
        ::
    
            sess.run([output_name], {input_name: x})
        """
        num_required_inputs = len(self._inputs_meta)
        num_inputs = len(input_feed)
        # the graph may have optional inputs used to override initializers. allow for that.
        if num_inputs < num_required_inputs:
            raise ValueError("Model requires {} inputs. Input Feed contains {}".format(num_required_inputs, num_inputs))
        if not output_names:
            output_names = [output.name for output in self._outputs_meta]
        try:
>           return self._sess.run(output_names, input_feed, run_options)
E           onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running If node. Name:'If_1173' Status Message: Subgraph must have the shape set for all outputs but 1673 did not.

@Timoeller
Copy link
Copy Markdown
Contributor

Sure, lets do that.

Do you think you can fix the failing test quickly or do you need help?

@Timoeller
Copy link
Copy Markdown
Contributor

About to cleanup the git history by removing large files.

Closing this PR since it will mess up the history.

@Timoeller Timoeller closed this Dec 23, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants