Skip to content

Latest commit

 

History

History
29 lines (25 loc) · 938 Bytes

README.md

File metadata and controls

29 lines (25 loc) · 938 Bytes

YOLO_v3

YOLO_v3 implemented with tensorflow

  • Group Normalization
  • Focal loss
  • Soft-NMS(no useful)
  • data augmentation
  • multi-scale training
  • Single-Shot Object Detection with Enriched Semantics
  • SNIPER

mAP on VOC2007

mAP

Reference:

paper:
YOLOv3: An Incremental Improvement
Foca Loss for Dense Object Detection
Group Normalization
Single-Shot Object Detection with Enriched Semantics
SNIPER: Efficient Multi-Scale Training

mAP calculate: mean Average Precision

Requirements

. Tensorflow
. Opencv
. Python
. Numpy