| User | vicpaulini |
| Upload Date | September 03 2025 01:19 PM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Snapdragon 8 Gen 2 |
| System Information | |
|---|---|
| Operating System | Android 15 |
| Model | Samsung Galaxy S23 Ultra |
| Model ID | samsung SM-S918B |
| Motherboard | kalama |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 3 Cores @ 2.02 GHz |
| Cluster 2 | 4 Cores @ 2.80 GHz |
| Cluster 3 | 1 Core @ 3.36 GHz |
| Memory Information | |
|---|---|
| Size | 10.79 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1095
203.6 IPS |
|
|
Image Classification (HP)
|
100% |
1609
299.2 IPS |
|
|
Image Classification (Q)
|
99% |
1501
280.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
2302
37.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
3798
61.6 IPS |
|
|
Image Segmentation (Q)
|
98% |
3113
50.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
8382
9.78 IPS |
|
|
Pose Estimation (HP)
|
99% |
15239
17.8 IPS |
|
|
Pose Estimation (Q)
|
97% |
12732
14.9 IPS |
|
|
Object Detection (SP)
|
100% |
832
66.0 IPS |
|
|
Object Detection (HP)
|
99% |
1266
100.4 IPS |
|
|
Object Detection (Q)
|
82% |
1199
97.1 IPS |
|
|
Face Detection (SP)
|
100% |
3659
43.5 IPS |
|
|
Face Detection (HP)
|
100% |
5731
68.1 IPS |
|
|
Face Detection (Q)
|
97% |
4384
52.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
4208
32.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
6151
47.5 IPS |
|
|
Depth Estimation (Q)
|
63% |
4939
46.3 IPS |
|
|
Style Transfer (SP)
|
100% |
9675
12.4 IPS |
|
|
Style Transfer (HP)
|
100% |
19722
25.4 IPS |
|
|
Style Transfer (Q)
|
98% |
15092
19.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1619
59.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2456
90.7 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
2477
91.8 IPS |
|
|
Text Classification (SP)
|
35% |
34
330.3 IPS |
|
|
Text Classification (HP)
|
35% |
45
413.5 IPS |
|
|
Text Classification (Q)
|
35% |
44
424.4 IPS |
|
|
Machine Translation (SP)
|
100% |
679
11.7 IPS |
|
|
Machine Translation (HP)
|
97% |
670
11.6 IPS |
|
|
Machine Translation (Q)
|
49% |
232
8.70 IPS |