polygraphy: Misc fixes for pytorch runner #2906
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Fixes: ``` Fix [W] pytorch-runner-N0-04/26/23-22:50:28 | `inference_time` was not set. Inference time will be incorrect! To correctly compare runtimes, please set the `inference_time` attribute in `infer_impl()` ``` Also fixes `RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.`
| @@ -68,8 +68,9 @@ def infer_impl(self, feed_dict): | |||
|
|
|||
| out_dict = OrderedDict() | |||
| for name, output in zip(self.output_names, outputs): | |||
| out_dict[name] = output.cpu().numpy() | |||
| return out_dict, end - start | |||
| out_dict[name] = output.detach().cpu().numpy() | |||
There was a problem hiding this comment.
could also probably be just output.numpy(force = True)
There was a problem hiding this comment.
Actually we could just return PyTorch tensors now, i.e.
Suggested change
| out_dict[name] = output.detach().cpu().numpy() | |
| out_dict[name] = output |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes:
Also fixes
RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.