Upload Date | December 27 2024 08:15 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | vivo V2408A |
Model ID | vivo V2408A |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 14.76 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1555
289.2 IPS |
|
Image Classification (HP)
|
100% |
1587
295.1 IPS |
|
Image Classification (Q)
|
100% |
3415
635.1 IPS |
|
Image Segmentation (SP)
|
100% |
1921
31.1 IPS |
|
Image Segmentation (HP)
|
100% |
1940
31.4 IPS |
|
Image Segmentation (Q)
|
98% |
4040
65.7 IPS |
|
Pose Estimation (SP)
|
100% |
4718
5.50 IPS |
|
Pose Estimation (HP)
|
100% |
4729
5.52 IPS |
|
Pose Estimation (Q)
|
84% |
10088
12.0 IPS |
|
Object Detection (SP)
|
98% |
1245
99.1 IPS |
|
Object Detection (HP)
|
98% |
1251
99.5 IPS |
|
Object Detection (Q)
|
83% |
2790
225.3 IPS |
|
Face Detection (SP)
|
100% |
3447
41.0 IPS |
|
Face Detection (HP)
|
100% |
3429
40.7 IPS |
|
Face Detection (Q)
|
95% |
6293
75.1 IPS |
|
Depth Estimation (SP)
|
99% |
3089
23.9 IPS |
|
Depth Estimation (HP)
|
99% |
3150
24.3 IPS |
|
Depth Estimation (Q)
|
64% |
6512
59.6 IPS |
|
Style Transfer (SP)
|
89% |
7782
10.1 IPS |
|
Style Transfer (HP)
|
89% |
7725
10.0 IPS |
|
Style Transfer (Q)
|
98% |
15984
20.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
1537
56.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
1548
57.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
3279
121.5 IPS |
|
Text Classification (SP)
|
100% |
649
865.6 IPS |
|
Text Classification (HP)
|
99% |
645
860.8 IPS |
|
Text Classification (Q)
|
88% |
468
631.0 IPS |
|
Machine Translation (SP)
|
100% |
989
17.0 IPS |
|
Machine Translation (HP)
|
100% |
969
16.7 IPS |
|
Machine Translation (Q)
|
50% |
387
13.8 IPS |