Inference Score |
614 |
614 |
100.0% |
vivo V2324A
|
|
vivo V2324A
|
|
Image Classification (F32)
|
346
|
346
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Classification (F16)
|
445
|
445
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Classification (I8)
|
419
|
419
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Segmentation (F32)
|
777
|
777
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Segmentation (F16)
|
788
|
788
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Segmentation (I8)
|
782
|
782
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Pose Estimation (F32)
|
385
|
385
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Pose Estimation (F16)
|
569
|
569
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Pose Estimation (I8)
|
567
|
567
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Object Detection (F32)
|
317
|
317
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Object Detection (F16)
|
439
|
439
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Object Detection (I8)
|
415
|
415
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Face Detection (F32)
|
1579
|
1579
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Face Detection (F16)
|
1589
|
1589
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Face Detection (I8)
|
1489
|
1489
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Depth Estimation (F32)
|
802
|
802
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Depth Estimation (F16)
|
970
|
970
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Depth Estimation (I8)
|
969
|
969
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Style Transfer (F32)
|
2178
|
2178
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Style Transfer (F16)
|
2743
|
2743
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Style Transfer (I8)
|
2733
|
2733
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Super-Resolution (F32)
|
457
|
457
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Super-Resolution (F16)
|
559
|
559
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Image Super-Resolution (I8)
|
552
|
552
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Text Classification (F32)
|
165
|
165
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Text Classification (F16)
|
164
|
164
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Text Classification (I8)
|
322
|
322
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Machine Translation (F32)
|
292
|
292
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Machine Translation (F16)
|
297
|
297
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|
Machine Translation (I8)
|
420
|
420
|
100.0%
|
vivo V2324A
|
|
vivo V2324A
|
|