View Code? Open in Web Editor
NEW
This project forked from megvii-basedetection /yolox
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
License: Apache License 2.0
Python 90.45%
C++ 9.43%
Shell 0.12%
yolox's People
Watchers
yolox's Issues
๐ Feature
TTA including multi-scales, reflection, and so on
Motivation & Examples
See the example of TTA for YOLOv5 at here
๐ Feature
I'd like to use some alternatives to Non-Maximum Suppression (NMS) below:
soft-NMS
Non-Maximum Weighted (NMW)
Weighted Boxes Fusion (WBF)
Motivation & Examples
NMS is one of the most conventional techniques to eliminate redundant bounding boxes
But some techniques show better results than NMS:
soft-NMS
Non-Maximum Weighted (NMW)
Weighted Boxes Fusion (WBF)
Soft-NMS surpasses NMS on PASCAL VOC 2007 and MS-COCO for R-FCN and Faster-RCNN
๐ Feature
I'd like to try vertical flip for data augmentation
Motivation & Examples
I've seen many works don't borrow vertical flip for data augmentation
Then, is it inappropriate to apply vertical flip to data augmentation in object detection?
It depends on type of domains or datasets
I benefited from it when I studied object detection in x-ray images