Skip to content

Fixes problem with torchscript when models are generated from onnx #513

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.

Sign up for GitHub

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

Draft
interesaaat wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Fixes problem with torchscript when models are generated from onnx #513

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bd03e64
play with *
interesaaat May 5, 2021
cf7c525
remove unecesary code
interesaaat May 5, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion hummingbird/ml/containers/_sklearn_api_containers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ def _run(self, function, *inputs):
splits = [inputs[input_names[idx]] for idx in range(len(input_names))]
inputs = [df.to_numpy().reshape(-1, 1) for df in splits]

return function(*inputs)
return function(inputs)


class SklearnContainerTransformer(SklearnContainer):
Expand Down
4 changes: 1 addition & 3 deletions hummingbird/ml/containers/sklearn/pytorch_containers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,8 +186,6 @@ def _predict(self, *inputs):
return output
else:
return output.ravel()
elif self._is_anomaly_detection:
return self.model.forward(*inputs)[0].cpu().numpy().ravel()
else:
return self.model.forward(*inputs)[0].cpu().numpy().ravel()

Expand Down Expand Up @@ -282,7 +280,7 @@ class TorchScriptSklearnContainerClassification(PyTorchSklearnContainerClassific
def predict(self, *inputs):
device = get_device(self.model)
f = super(TorchScriptSklearnContainerClassification, self)._predict
f_wrapped = lambda x: _torchscript_wrapper(device, f, x, extra_config=self._extra_config) # noqa: E731
f_wrapped = lambda x: _torchscript_wrapper(device, f, *x, extra_config=self._extra_config) # noqa: E731

return self._run(f_wrapped, *inputs)

Expand Down