基于ShuffleNetv2-YOLOv3模型的静态手势实时识别方法
|
|
辛文斌,郝惠敏,卜明龙,兰媛,黄家海,熊晓燕
|
Static gesture real-time recognition method based on ShuffleNetv2-YOLOv3 model
|
|
Wen-bin XIN,Hui-min HAO,Ming-long BU,Yuan LAN,Jia-hai HUANG,Xiao-yan XIONG
|
|
| 表 1 ShuffleNetv2的网络结构 |
| Tab.1 Network structure of ShuffleNetv2 |
|
| 层级 | Os | Ks | S | R | Oc | | 0.5× | 1.0× | 1.5× | 2.0× | | Image | 416×416 | — | — | — | 3 | 3 | 3 | 3 | Conv1
MaxPool | 208×208
104×104 | 3×3
3×3 | 2
2 | 1
1 | 24
24 | 24
24 | 24
24 | 24
24 | Stage2
Stage2 | 52×52
52×52 | —
— | 2
1 | 1
3 | 48
48 | 116
116 | 176
176 | 244
244 | Stage3
Stage3 | 26×26
26×26 | —
— | 2
1 | 1
7 | 96
96 | 232
232 | 352
352 | 488
488 | Stage4
Stage4 | 13×13
13×13 | —
— | 2
1 | 1
3 | 192
192 | 464
464 | 704
704 | 976
976 | | Conv5 | 13×13 | 1×1 | 1 | 1 | 1024 | 1024 | 1024 | 2048 | | GlobalPool | 1×1 | 13×13 | — | — | — | — | — | — | | FC | — | — | — | — | 1000 | 1000 | 1000 | 1000 |
|
|
|