-
Notifications
You must be signed in to change notification settings - Fork 14
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
5 changed files
with
21 additions
and
1 deletion.
There are no files selected for viewing
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1,21 @@ | ||
# YOLOv5_with_BiFPN | ||
# YOLOv5_with_BiFPN | ||
|
||
YOLOv5 implementation is completely from the original repository (https://github.com/ultralytics/yolov5). | ||
This repo is mainly for replacing PANet with BiFPN in YOLOv5, which you can check in models/yolov5x.yaml. I didn't use the exact same BiFPN in the paper, while I try to be consistent with yolov5, so still three scale predictions. | ||
|
||
# Training | ||
|
||
python train.py --img 640 --batch 8 --epochs 200 --data CUB.yaml --weights '' --cfg yolov5x.yaml | ||
|
||
I didn't use pre-trained weights since the architecture changes a bit. And as for the performance, I will check more dataset and update it. | ||
|
||
|
||
# Reference | ||
|
||
https://github.com/ultralytics/yolov5 | ||
|
||
https://github.com/zylo117/Yet-Another-EfficientDet-Pytorch/tree/15403b5371a64defb2a7c74e162c6e880a7f462c | ||
|
||
Mingxing Tan, Ruoming Pang, and Quoc V Le. EfficientDet: Scalable and efficient object detection. In Proceedings | ||
of the IEEE Conference on Computer Vision and Pattern | ||
Recognition (CVPR), 2020. |
Binary file not shown.
Binary file not shown.
Binary file not shown.