Upload Date | September 06 2025 06:24 PM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | vivo V2324A |
Model ID | vivo V2324A |
Motherboard | k6989v1_64 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.25 GHz |
Memory Information | |
---|---|
Size | 14.96 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
685
127.4 IPS |
|
Image Classification (HP)
|
100% |
778
144.6 IPS |
|
Image Classification (Q)
|
97% |
696
130.0 IPS |
|
Image Segmentation (SP)
|
100% |
1987
32.2 IPS |
|
Image Segmentation (HP)
|
100% |
2326
37.7 IPS |
|
Image Segmentation (Q)
|
98% |
2140
34.8 IPS |
|
Pose Estimation (SP)
|
100% |
10235
11.9 IPS |
|
Pose Estimation (HP)
|
100% |
16463
19.2 IPS |
|
Pose Estimation (Q)
|
95% |
14056
16.5 IPS |
|
Object Detection (SP)
|
100% |
539
42.7 IPS |
|
Object Detection (HP)
|
99% |
1033
81.9 IPS |
|
Object Detection (Q)
|
83% |
1073
86.6 IPS |
|
Face Detection (SP)
|
100% |
3301
39.2 IPS |
|
Face Detection (HP)
|
100% |
3267
38.8 IPS |
|
Face Detection (Q)
|
96% |
3016
36.0 IPS |
|
Depth Estimation (SP)
|
100% |
5388
41.5 IPS |
|
Depth Estimation (HP)
|
98% |
9269
71.6 IPS |
|
Depth Estimation (Q)
|
62% |
7138
67.8 IPS |
|
Style Transfer (SP)
|
100% |
15148
19.5 IPS |
|
Style Transfer (HP)
|
100% |
32547
41.8 IPS |
|
Style Transfer (Q)
|
98% |
31857
41.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
2541
93.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
3182
117.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
3125
115.8 IPS |
|
Text Classification (SP)
|
35% |
17
154.3 IPS |
|
Text Classification (HP)
|
29% |
8
145.2 IPS |
|
Text Classification (Q)
|
29% |
11
194.9 IPS |
|
Machine Translation (SP)
|
100% |
336
5.78 IPS |
|
Machine Translation (HP)
|
100% |
531
9.15 IPS |
|
Machine Translation (Q)
|
43% |
90
5.23 IPS |