Upload Date | December 26 2024 01:32 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | vivo V2426A |
Model ID | vivo V2426A |
Motherboard | k6991v1_64 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3461 revision 1 |
Base Frequency | 2.40 GHz |
Cluster 1 | 4 Cores @ 2.40 GHz |
Cluster 2 | 3 Cores @ 3.30 GHz |
Cluster 3 | 1 Core @ 3.63 GHz |
Memory Information | |
---|---|
Size | 14.94 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
429
79.7 IPS |
|
Image Classification (HP)
|
100% |
522
97.0 IPS |
|
Image Classification (Q)
|
99% |
465
86.7 IPS |
|
Image Segmentation (SP)
|
100% |
1052
17.1 IPS |
|
Image Segmentation (HP)
|
100% |
1307
21.2 IPS |
|
Image Segmentation (Q)
|
98% |
1295
21.1 IPS |
|
Pose Estimation (SP)
|
100% |
968
1.13 IPS |
|
Pose Estimation (HP)
|
100% |
1500
1.75 IPS |
|
Pose Estimation (Q)
|
96% |
1494
1.75 IPS |
|
Object Detection (SP)
|
100% |
449
35.6 IPS |
|
Object Detection (HP)
|
100% |
545
43.2 IPS |
|
Object Detection (Q)
|
83% |
574
46.4 IPS |
|
Face Detection (SP)
|
100% |
2015
23.9 IPS |
|
Face Detection (HP)
|
100% |
2200
26.1 IPS |
|
Face Detection (Q)
|
97% |
2112
25.2 IPS |
|
Depth Estimation (SP)
|
100% |
1537
11.8 IPS |
|
Depth Estimation (HP)
|
99% |
1966
15.1 IPS |
|
Depth Estimation (Q)
|
62% |
1587
15.0 IPS |
|
Style Transfer (SP)
|
100% |
4519
5.81 IPS |
|
Style Transfer (HP)
|
100% |
6523
8.38 IPS |
|
Style Transfer (Q)
|
98% |
6488
8.37 IPS |
|
Image Super-Resolution (SP)
|
100% |
780
28.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
927
34.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
907
33.6 IPS |
|
Text Classification (SP)
|
100% |
592
790.0 IPS |
|
Text Classification (HP)
|
100% |
595
794.7 IPS |
|
Text Classification (Q)
|
91% |
814
1.09 KIPS |
|
Machine Translation (SP)
|
100% |
897
15.5 IPS |
|
Machine Translation (HP)
|
100% |
867
14.9 IPS |
|
Machine Translation (Q)
|
57% |
544
13.3 IPS |