Upload Date | September 16 2025 04:04 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S937B |
Model ID | samsung SM-S937B |
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% |
441
82.0 IPS |
|
Image Classification (HP)
|
100% |
438
81.5 IPS |
|
Image Classification (Q)
|
99% |
1096
204.4 IPS |
|
Image Segmentation (SP)
|
100% |
569
9.22 IPS |
|
Image Segmentation (HP)
|
100% |
567
9.19 IPS |
|
Image Segmentation (Q)
|
98% |
1113
18.1 IPS |
|
Pose Estimation (SP)
|
100% |
633
0.74 IPS |
|
Pose Estimation (HP)
|
100% |
626
0.73 IPS |
|
Pose Estimation (Q)
|
98% |
2368
2.77 IPS |
|
Object Detection (SP)
|
100% |
334
26.5 IPS |
|
Object Detection (HP)
|
100% |
335
26.6 IPS |
|
Object Detection (Q)
|
87% |
832
66.8 IPS |
|
Face Detection (SP)
|
100% |
903
10.7 IPS |
|
Face Detection (HP)
|
100% |
904
10.7 IPS |
|
Face Detection (Q)
|
97% |
1686
20.1 IPS |
|
Depth Estimation (SP)
|
100% |
763
5.88 IPS |
|
Depth Estimation (HP)
|
99% |
662
5.10 IPS |
|
Depth Estimation (Q)
|
64% |
1466
13.3 IPS |
|
Style Transfer (SP)
|
100% |
1348
1.73 IPS |
|
Style Transfer (HP)
|
100% |
1177
1.51 IPS |
|
Style Transfer (Q)
|
98% |
3128
4.03 IPS |
|
Image Super-Resolution (SP)
|
100% |
364
13.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
354
13.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
1202
44.6 IPS |
|
Text Classification (SP)
|
100% |
434
579.4 IPS |
|
Text Classification (HP)
|
100% |
502
670.4 IPS |
|
Text Classification (Q)
|
91% |
775
1.04 KIPS |
|
Machine Translation (SP)
|
100% |
837
14.4 IPS |
|
Machine Translation (HP)
|
100% |
780
13.4 IPS |
|
Machine Translation (Q)
|
57% |
518
12.6 IPS |