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.

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

Optimize for inference when using call api #162

Merged
merged 2 commits into from
Feb 19, 2024
Merged

Optimize for inference when using call api #162

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cec94b1
Optimize for inference when using call api
joeyballentine Feb 19, 2024
19bfe69
We only need the decorator
joeyballentine Feb 19, 2024
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
6 changes: 5 additions & 1 deletion src/spandrel/__helpers/model_descriptor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -446,6 +446,7 @@ def __init__(
def purpose(self) -> Literal["SR", "FaceSR", "Restoration"]:
return self._purpose

@torch.inference_mode()
def __call__(self, image: Tensor) -> Tensor:
"""
Takes a single image tensor as input and returns a single image tensor as output.
Expand All @@ -466,11 +467,14 @@ def __call__(self, image: Tensor) -> Tensor:
# satisfy size requirements
did_pad, image = pad_tensor(image, self.size_requirements)

# Optimize for inference
self.model.eval()

# call model
output = self._call_fn(self.model, image)
assert isinstance(
output, Tensor
), f"Expected {type(self.model).__name__} model to returns a tensor, but got {type(output)}"
), f"Expected {type(self.model).__name__} model to return a tensor, but got {type(output)}"

# guarantee range
output = output.clamp_(0, 1)
Expand Down
Loading