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

Enable ONNX --half FP16 inference #6268

Merged
merged 2 commits into from
Jan 11, 2022
Merged

Enable ONNX --half FP16 inference #6268

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
d8dabea
Enable ONNX ``--half` FP16 inference
glenn-jocher Jan 11, 2022
03e5beb
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jan 11, 2022
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 detect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s)
imgsz = check_img_size(imgsz, s=stride) # check image size

# Half
half &= (pt or jit or engine) and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
half &= (pt or jit or onnx or engine) and device.type != 'cpu' # FP16 supported on limited backends with CUDA
if pt or jit:
model.model.half() if half else model.model.float()

Expand Down
2 changes: 1 addition & 1 deletion tutorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1099,4 +1099,4 @@
"outputs": []
}
]
}
}
4 changes: 2 additions & 2 deletions val.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,9 +137,9 @@ def run(data,

# Load model
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
stride, pt, jit, onnx, engine = model.stride, model.pt, model.jit, model.onnx, model.engine
imgsz = check_img_size(imgsz, s=stride) # check image size
half &= (pt or jit or engine) and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
half &= (pt or jit or onnx or engine) and device.type != 'cpu' # FP16 supported on limited backends with CUDA
if pt or jit:
model.model.half() if half else model.model.float()
elif engine:
Expand Down