| User | aaron762 |
| Upload Date | March 25 2026 05:30 AM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Snapdragon 8 Gen 1 |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | Samsung Galaxy S22 Ultra |
| Model ID | samsung SM-S908U1 |
| Motherboard | taro |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.50 GHz |
| Cluster 3 | 1 Core @ 3.00 GHz |
| Memory Information | |
|---|---|
| Size | 10.94 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
884
164.4 IPS |
|
|
Image Classification (HP)
|
100% |
1366
254.1 IPS |
|
|
Image Classification (Q)
|
99% |
1273
237.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
1639
26.6 IPS |
|
|
Image Segmentation (HP)
|
100% |
2722
44.1 IPS |
|
|
Image Segmentation (Q)
|
98% |
2171
35.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
6081
7.10 IPS |
|
|
Pose Estimation (HP)
|
99% |
11480
13.4 IPS |
|
|
Pose Estimation (Q)
|
97% |
11133
13.0 IPS |
|
|
Object Detection (SP)
|
100% |
656
52.0 IPS |
|
|
Object Detection (HP)
|
99% |
1122
89.0 IPS |
|
|
Object Detection (Q)
|
85% |
1079
86.8 IPS |
|
|
Face Detection (SP)
|
100% |
2323
27.6 IPS |
|
|
Face Detection (HP)
|
100% |
4601
54.7 IPS |
|
|
Face Detection (Q)
|
97% |
3920
46.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
3053
23.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
5391
41.7 IPS |
|
|
Depth Estimation (Q)
|
65% |
4398
39.5 IPS |
|
|
Style Transfer (SP)
|
100% |
6933
8.91 IPS |
|
|
Style Transfer (HP)
|
100% |
13944
17.9 IPS |
|
|
Style Transfer (Q)
|
98% |
14059
18.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1323
48.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2521
93.1 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
2602
96.4 IPS |
|
|
Text Classification (SP)
|
35% |
46
446.4 IPS |
|
|
Text Classification (HP)
|
35% |
65
587.7 IPS |
|
|
Text Classification (Q)
|
35% |
64
577.7 IPS |
|
|
Machine Translation (SP)
|
100% |
469
8.08 IPS |
|
|
Machine Translation (HP)
|
97% |
615
10.6 IPS |
|
|
Machine Translation (Q)
|
64% |
430
8.84 IPS |