| Inference Score |
1041 |
1041 |
100.0% |
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Classification (F32)
|
668
|
668
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Classification (F16)
|
690
|
690
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Classification (I8)
|
650
|
650
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Segmentation (F32)
|
861
|
861
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Segmentation (F16)
|
1476
|
1476
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Segmentation (I8)
|
1239
|
1239
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Pose Estimation (F32)
|
996
|
996
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Pose Estimation (F16)
|
2092
|
2092
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Pose Estimation (I8)
|
2076
|
2076
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Object Detection (F32)
|
243
|
243
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Object Detection (F16)
|
395
|
395
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Object Detection (I8)
|
269
|
269
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Face Detection (F32)
|
2410
|
2410
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Face Detection (F16)
|
3148
|
3148
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Face Detection (I8)
|
2774
|
2774
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Depth Estimation (F32)
|
1630
|
1630
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Depth Estimation (F16)
|
3112
|
3112
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Depth Estimation (I8)
|
3194
|
3194
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Style Transfer (F32)
|
5584
|
5584
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Style Transfer (F16)
|
9028
|
9028
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Style Transfer (I8)
|
8947
|
8947
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Super-Resolution (F32)
|
435
|
435
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Super-Resolution (F16)
|
999
|
999
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Image Super-Resolution (I8)
|
960
|
960
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Text Classification (F32)
|
276
|
276
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Text Classification (F16)
|
196
|
196
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Text Classification (I8)
|
321
|
321
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Machine Translation (F32)
|
370
|
370
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Machine Translation (F16)
|
370
|
370
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
|
Machine Translation (I8)
|
424
|
424
|
100.0%
|
|
vivo V2329A
|
|
|
vivo V2329A
|
|
