Upload Date | September 18 2025 09:03 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S938B |
Model ID | samsung SM-S938B |
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% |
439
81.7 IPS |
|
Image Classification (HP)
|
100% |
437
81.2 IPS |
|
Image Classification (Q)
|
99% |
1105
206.2 IPS |
|
Image Segmentation (SP)
|
100% |
555
9.00 IPS |
|
Image Segmentation (HP)
|
100% |
493
8.00 IPS |
|
Image Segmentation (Q)
|
98% |
957
15.6 IPS |
|
Pose Estimation (SP)
|
100% |
618
0.72 IPS |
|
Pose Estimation (HP)
|
100% |
524
0.61 IPS |
|
Pose Estimation (Q)
|
98% |
1701
1.99 IPS |
|
Object Detection (SP)
|
100% |
283
22.4 IPS |
|
Object Detection (HP)
|
100% |
284
22.5 IPS |
|
Object Detection (Q)
|
87% |
765
61.4 IPS |
|
Face Detection (SP)
|
100% |
757
9.00 IPS |
|
Face Detection (HP)
|
100% |
680
8.08 IPS |
|
Face Detection (Q)
|
97% |
1560
18.6 IPS |
|
Depth Estimation (SP)
|
100% |
612
4.72 IPS |
|
Depth Estimation (HP)
|
99% |
538
4.15 IPS |
|
Depth Estimation (Q)
|
64% |
1060
9.62 IPS |
|
Style Transfer (SP)
|
100% |
1102
1.42 IPS |
|
Style Transfer (HP)
|
100% |
900
1.16 IPS |
|
Style Transfer (Q)
|
98% |
2284
2.95 IPS |
|
Image Super-Resolution (SP)
|
100% |
290
10.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
313
11.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1107
41.0 IPS |
|
Text Classification (SP)
|
100% |
400
533.9 IPS |
|
Text Classification (HP)
|
100% |
400
534.4 IPS |
|
Text Classification (Q)
|
91% |
616
827.7 IPS |
|
Machine Translation (SP)
|
100% |
678
11.7 IPS |
|
Machine Translation (HP)
|
100% |
732
12.6 IPS |
|
Machine Translation (Q)
|
57% |
517
12.6 IPS |