| Upload Date | November 06 2025 04:23 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | SAMSUNG SM-G935A |
| Model ID | SAMSUNG SM-G935A |
| Motherboard | rk30sdk |
| Governor | performance |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 4 Cores @ 2.35 GHz |
| Memory Information | |
|---|---|
| Size | 3.61 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
517
96.1 IPS |
|
|
Image Classification (HP)
|
100% |
929
172.8 IPS |
|
|
Image Classification (Q)
|
97% |
850
158.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
863
14.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
1626
26.4 IPS |
|
|
Image Segmentation (Q)
|
98% |
1647
26.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
3020
3.52 IPS |
|
|
Pose Estimation (HP)
|
100% |
5851
6.83 IPS |
|
|
Pose Estimation (Q)
|
95% |
5686
6.66 IPS |
|
|
Object Detection (SP)
|
100% |
584
46.3 IPS |
|
|
Object Detection (HP)
|
99% |
907
71.9 IPS |
|
|
Object Detection (Q)
|
83% |
900
72.7 IPS |
|
|
Face Detection (SP)
|
100% |
1766
21.0 IPS |
|
|
Face Detection (HP)
|
100% |
2573
30.6 IPS |
|
|
Face Detection (Q)
|
96% |
2786
33.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
2177
16.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
3310
25.6 IPS |
|
|
Depth Estimation (Q)
|
62% |
2817
26.8 IPS |
|
|
Style Transfer (SP)
|
100% |
4912
6.31 IPS |
|
|
Style Transfer (HP)
|
100% |
12441
16.0 IPS |
|
|
Style Transfer (Q)
|
98% |
12152
15.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1184
43.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2293
84.7 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
2224
82.4 IPS |
|
|
Text Classification (SP)
|
35% |
28
256.0 IPS |
|
|
Text Classification (HP)
|
35% |
32
292.9 IPS |
|
|
Text Classification (Q)
|
32% |
28
361.2 IPS |
|
|
Machine Translation (SP)
|
100% |
546
9.41 IPS |
|
|
Machine Translation (HP)
|
100% |
596
10.3 IPS |
|
|
Machine Translation (Q)
|
43% |
155
9.03 IPS |