| Upload Date | November 15 2025 04:35 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | samsung SM-S721B |
| Model ID | samsung SM-S721B |
| Motherboard | s5e9945 |
| Governor | energy_aware |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 10 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
| Base Frequency | 1.96 GHz |
| Cluster 1 | 4 Cores @ 1.96 GHz |
| Cluster 2 | 3 Cores @ 2.59 GHz |
| Cluster 3 | 2 Cores @ 2.90 GHz |
| Cluster 4 | 1 Core @ 3.11 GHz |
| Memory Information | |
|---|---|
| Size | 7.06 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
909
169.1 IPS |
|
|
Image Classification (HP)
|
100% |
1716
319.2 IPS |
|
|
Image Classification (Q)
|
100% |
1311
243.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1798
29.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2848
46.2 IPS |
|
|
Image Segmentation (Q)
|
98% |
2442
39.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
6299
7.35 IPS |
|
|
Pose Estimation (HP)
|
99% |
12899
15.1 IPS |
|
|
Pose Estimation (Q)
|
95% |
12332
14.5 IPS |
|
|
Object Detection (SP)
|
100% |
605
48.0 IPS |
|
|
Object Detection (HP)
|
99% |
1046
83.0 IPS |
|
|
Object Detection (Q)
|
84% |
1080
87.1 IPS |
|
|
Face Detection (SP)
|
100% |
2680
31.8 IPS |
|
|
Face Detection (HP)
|
100% |
4592
54.6 IPS |
|
|
Face Detection (Q)
|
97% |
3886
46.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
3541
27.3 IPS |
|
|
Depth Estimation (HP)
|
98% |
6204
48.0 IPS |
|
|
Depth Estimation (Q)
|
62% |
4953
47.8 IPS |
|
|
Style Transfer (SP)
|
100% |
13905
17.9 IPS |
|
|
Style Transfer (HP)
|
100% |
27779
35.7 IPS |
|
|
Style Transfer (Q)
|
98% |
23388
30.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1875
69.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3709
137.0 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
3660
135.7 IPS |
|
|
Text Classification (SP)
|
29% |
26
442.1 IPS |
|
|
Text Classification (HP)
|
35% |
64
583.8 IPS |
|
|
Text Classification (Q)
|
29% |
37
632.0 IPS |
|
|
Machine Translation (SP)
|
100% |
706
12.2 IPS |
|
|
Machine Translation (HP)
|
100% |
1044
18.0 IPS |
|
|
Machine Translation (Q)
|
42% |
200
13.0 IPS |