Upload Date | July 11 2025 11:52 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm Snapdragon 8 Elite |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy S25 |
Model ID | samsung SM-S931U1 |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.47 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
428
79.5 IPS |
|
Image Classification (HP)
|
100% |
431
80.2 IPS |
|
Image Classification (Q)
|
99% |
1073
200.1 IPS |
|
Image Segmentation (SP)
|
100% |
498
8.07 IPS |
|
Image Segmentation (HP)
|
100% |
544
8.82 IPS |
|
Image Segmentation (Q)
|
98% |
970
15.8 IPS |
|
Pose Estimation (SP)
|
100% |
721
0.84 IPS |
|
Pose Estimation (HP)
|
100% |
686
0.80 IPS |
|
Pose Estimation (Q)
|
98% |
2674
3.13 IPS |
|
Object Detection (SP)
|
100% |
381
30.3 IPS |
|
Object Detection (HP)
|
100% |
377
29.9 IPS |
|
Object Detection (Q)
|
87% |
945
75.8 IPS |
|
Face Detection (SP)
|
100% |
971
11.5 IPS |
|
Face Detection (HP)
|
100% |
972
11.5 IPS |
|
Face Detection (Q)
|
97% |
2225
26.5 IPS |
|
Depth Estimation (SP)
|
100% |
855
6.59 IPS |
|
Depth Estimation (HP)
|
99% |
757
5.83 IPS |
|
Depth Estimation (Q)
|
64% |
1733
15.7 IPS |
|
Style Transfer (SP)
|
100% |
1482
1.90 IPS |
|
Style Transfer (HP)
|
100% |
1350
1.74 IPS |
|
Style Transfer (Q)
|
98% |
3329
4.29 IPS |
|
Image Super-Resolution (SP)
|
100% |
402
14.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
403
14.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1402
52.0 IPS |
|
Text Classification (SP)
|
100% |
503
671.8 IPS |
|
Text Classification (HP)
|
100% |
504
672.8 IPS |
|
Text Classification (Q)
|
91% |
830
1.12 KIPS |
|
Machine Translation (SP)
|
100% |
1015
17.5 IPS |
|
Machine Translation (HP)
|
100% |
1020
17.6 IPS |
|
Machine Translation (Q)
|
57% |
553
13.5 IPS |