| Inference Score |
945 |
945 |
100.0% |
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Classification (F32)
|
500
|
500
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Classification (F16)
|
564
|
564
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Classification (I8)
|
770
|
770
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Segmentation (F32)
|
853
|
853
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Segmentation (F16)
|
839
|
839
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Segmentation (I8)
|
806
|
806
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Pose Estimation (F32)
|
1163
|
1163
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Pose Estimation (F16)
|
1126
|
1126
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Pose Estimation (I8)
|
4534
|
4534
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Object Detection (F32)
|
537
|
537
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Object Detection (F16)
|
488
|
488
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Object Detection (I8)
|
710
|
710
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Face Detection (F32)
|
983
|
983
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Face Detection (F16)
|
1228
|
1228
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Face Detection (I8)
|
1506
|
1506
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Depth Estimation (F32)
|
1085
|
1085
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Depth Estimation (F16)
|
1013
|
1013
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Depth Estimation (I8)
|
1630
|
1630
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Style Transfer (F32)
|
1816
|
1816
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Style Transfer (F16)
|
1872
|
1872
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Style Transfer (I8)
|
3896
|
3896
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Super-Resolution (F32)
|
659
|
659
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Super-Resolution (F16)
|
605
|
605
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Super-Resolution (I8)
|
1024
|
1024
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Text Classification (F32)
|
560
|
560
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Text Classification (F16)
|
609
|
609
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Text Classification (I8)
|
521
|
521
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Machine Translation (F32)
|
1027
|
1027
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Machine Translation (F16)
|
1072
|
1072
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Machine Translation (I8)
|
391
|
391
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
