Upload Date | September 13 2025 11:26 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S931Z |
Model ID | samsung SM-S931Z |
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% |
412
76.7 IPS |
|
Image Classification (HP)
|
100% |
406
75.5 IPS |
|
Image Classification (Q)
|
99% |
1052
196.3 IPS |
|
Image Segmentation (SP)
|
100% |
524
8.50 IPS |
|
Image Segmentation (HP)
|
100% |
526
8.52 IPS |
|
Image Segmentation (Q)
|
98% |
1057
17.2 IPS |
|
Pose Estimation (SP)
|
100% |
706
0.82 IPS |
|
Pose Estimation (HP)
|
100% |
685
0.80 IPS |
|
Pose Estimation (Q)
|
98% |
2667
3.12 IPS |
|
Object Detection (SP)
|
100% |
377
29.9 IPS |
|
Object Detection (HP)
|
100% |
378
30.0 IPS |
|
Object Detection (Q)
|
87% |
956
76.7 IPS |
|
Face Detection (SP)
|
100% |
949
11.3 IPS |
|
Face Detection (HP)
|
100% |
984
11.7 IPS |
|
Face Detection (Q)
|
97% |
2394
28.6 IPS |
|
Depth Estimation (SP)
|
100% |
864
6.66 IPS |
|
Depth Estimation (HP)
|
99% |
797
6.14 IPS |
|
Depth Estimation (Q)
|
64% |
1941
17.6 IPS |
|
Style Transfer (SP)
|
100% |
1485
1.91 IPS |
|
Style Transfer (HP)
|
100% |
1419
1.82 IPS |
|
Style Transfer (Q)
|
98% |
3627
4.68 IPS |
|
Image Super-Resolution (SP)
|
100% |
427
15.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
428
15.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1400
51.9 IPS |
|
Text Classification (SP)
|
100% |
504
672.2 IPS |
|
Text Classification (HP)
|
100% |
503
671.8 IPS |
|
Text Classification (Q)
|
91% |
776
1.04 KIPS |
|
Machine Translation (SP)
|
100% |
1006
17.3 IPS |
|
Machine Translation (HP)
|
100% |
881
15.2 IPS |
|
Machine Translation (Q)
|
57% |
493
12.0 IPS |