Upload Date | August 21 2025 08:20 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 13 |
Model | samsung SM-G960F |
Model ID | samsung SM-G960F |
Motherboard | exynos9810 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 2 revision 0 |
Base Frequency | 1.79 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 4 Cores @ 2.70 GHz |
Memory Information | |
---|---|
Size | 3.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
0% |
0
67.1 IPS |
|
Image Classification (HP)
|
100% |
448
83.3 IPS |
|
Image Classification (Q)
|
97% |
387
72.3 IPS |
|
Image Segmentation (SP)
|
73% |
405
7.00 IPS |
|
Image Segmentation (HP)
|
100% |
729
11.8 IPS |
|
Image Segmentation (Q)
|
98% |
764
12.4 IPS |
|
Pose Estimation (SP)
|
100% |
2104
2.46 IPS |
|
Pose Estimation (HP)
|
100% |
4381
5.11 IPS |
|
Pose Estimation (Q)
|
95% |
3953
4.63 IPS |
|
Object Detection (SP)
|
1% |
0
18.7 IPS |
|
Object Detection (HP)
|
99% |
423
33.5 IPS |
|
Object Detection (Q)
|
83% |
392
31.7 IPS |
|
Face Detection (SP)
|
0% |
0
10.9 IPS |
|
Face Detection (HP)
|
100% |
1295
15.4 IPS |
|
Face Detection (Q)
|
96% |
1117
13.3 IPS |
|
Depth Estimation (SP)
|
1% |
3
6.83 IPS |
|
Depth Estimation (HP)
|
98% |
1907
14.7 IPS |
|
Depth Estimation (Q)
|
62% |
1513
14.4 IPS |
|
Style Transfer (SP)
|
100% |
2930
3.77 IPS |
|
Style Transfer (HP)
|
100% |
5443
7.00 IPS |
|
Style Transfer (Q)
|
98% |
6023
7.77 IPS |
|
Image Super-Resolution (SP)
|
100% |
464
17.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
1368
50.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1072
39.7 IPS |
|
Text Classification (SP)
|
35% |
17
154.1 IPS |
|
Text Classification (HP)
|
35% |
27
245.3 IPS |
|
Text Classification (Q)
|
32% |
18
237.7 IPS |
|
Machine Translation (SP)
|
100% |
260
4.49 IPS |
|
Machine Translation (HP)
|
100% |
364
6.27 IPS |
|
Machine Translation (Q)
|
43% |
88
5.11 IPS |