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

Jump to bottom

DetectMultiBackend() default stride=32 #7342

Merged
merged 10 commits into from
Apr 9, 2022
Merged

DetectMultiBackend() default stride=32 #7342

Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
1407bc3
set common default stride as 32
rglkt Apr 8, 2022
0b5f249
restore default stride, and set it on argument optional
rglkt Apr 8, 2022
811fabd
fix wrong use of opt
rglkt Apr 8, 2022
c56957f
fix missing parameter of stride
rglkt Apr 8, 2022
99a6473
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Apr 8, 2022
af0e366
fix format of parameters
rglkt Apr 8, 2022
0bb0985
Merge branch 'master' of github.com:rglkt/yolov5
rglkt Apr 8, 2022
7d50c7b
Update val.py
glenn-jocher Apr 9, 2022
66a7c04
Merge branch 'master' into master
glenn-jocher Apr 9, 2022
5bc7188
Update common.py
glenn-jocher Apr 9, 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 models/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -296,7 +296,7 @@ def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False,
super().__init__()
w = str(weights[0] if isinstance(weights, list) else weights)
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = self.model_type(w) # get backend
stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
stride, names = 32, [f'class{i}' for i in range(1000)] # assign defaults
Copy link
Contributor

@zhiqwang zhiqwang Apr 8, 2022 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Seems the P6 series need stride 64, so it would be better to set this parameter optional here.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sorry, i can't realize the meaning of P6, do you mean as follow? i think the data configuration is used to config something about dataset, it's not suitable to set stride on it?
image

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sorry，i know， set it on cmd argument， i try it

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P6 is yolov5n6, yolov5s6, yolov5m6 and yolov5l6, introduced from tag 5.0.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks！and i have added argument --stride

w = attempt_download(w) # download if not local
fp16 &= (pt or jit or onnx or engine) and device.type != 'cpu' # FP16
if data: # data.yaml path (optional)
Expand Down