| Inference Score |
3287 |
3287 |
100.0% |
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Classification (F32)
|
1005
|
1005
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Classification (F16)
|
4267
|
4267
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Classification (I8)
|
8264
|
8264
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Segmentation (F32)
|
645
|
645
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Segmentation (F16)
|
4009
|
4009
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Segmentation (I8)
|
1778
|
1778
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Pose Estimation (F32)
|
8380
|
8380
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Pose Estimation (F16)
|
17790
|
17790
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Pose Estimation (I8)
|
68726
|
68726
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Object Detection (F32)
|
670
|
670
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Object Detection (F16)
|
2859
|
2859
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Object Detection (I8)
|
3231
|
3231
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Face Detection (F32)
|
3407
|
3407
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Face Detection (F16)
|
11627
|
11627
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Face Detection (I8)
|
11275
|
11275
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Depth Estimation (F32)
|
924
|
924
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Depth Estimation (F16)
|
14583
|
14583
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Depth Estimation (I8)
|
26495
|
26495
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Style Transfer (F32)
|
2520
|
2520
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Style Transfer (F16)
|
2387
|
2387
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Style Transfer (I8)
|
4665
|
4665
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Super-Resolution (F32)
|
2183
|
2183
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Super-Resolution (F16)
|
10587
|
10587
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Image Super-Resolution (I8)
|
29634
|
29634
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Text Classification (F32)
|
105
|
105
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Text Classification (F16)
|
1710
|
1710
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Text Classification (I8)
|
1339
|
1339
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Machine Translation (F32)
|
324
|
324
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Machine Translation (F16)
|
1979
|
1979
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
|
Machine Translation (I8)
|
658
|
658
|
100.0%
|
|
vivo V2324A
|
|
|
vivo V2324A
|
|
