Upload Date | May 29 2025 05:30 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
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% |
511
95.1 IPS |
|
Image Classification (HP)
|
100% |
997
185.3 IPS |
|
Image Classification (Q)
|
99% |
737
137.4 IPS |
|
Image Segmentation (SP)
|
100% |
1162
18.8 IPS |
|
Image Segmentation (HP)
|
100% |
2026
32.8 IPS |
|
Image Segmentation (Q)
|
98% |
1701
27.7 IPS |
|
Pose Estimation (SP)
|
100% |
1125
1.31 IPS |
|
Pose Estimation (HP)
|
100% |
1924
2.25 IPS |
|
Pose Estimation (Q)
|
96% |
1926
2.26 IPS |
|
Object Detection (SP)
|
100% |
419
33.2 IPS |
|
Object Detection (HP)
|
100% |
989
78.5 IPS |
|
Object Detection (Q)
|
86% |
967
77.6 IPS |
|
Face Detection (SP)
|
100% |
2395
28.5 IPS |
|
Face Detection (HP)
|
100% |
3373
40.1 IPS |
|
Face Detection (Q)
|
97% |
3367
40.2 IPS |
|
Depth Estimation (SP)
|
100% |
1291
9.95 IPS |
|
Depth Estimation (HP)
|
99% |
3369
26.0 IPS |
|
Depth Estimation (Q)
|
63% |
2875
26.7 IPS |
|
Style Transfer (SP)
|
100% |
4137
5.32 IPS |
|
Style Transfer (HP)
|
100% |
9098
11.7 IPS |
|
Style Transfer (Q)
|
98% |
9057
11.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
570
21.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
1454
53.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1491
55.3 IPS |
|
Text Classification (SP)
|
100% |
577
770.5 IPS |
|
Text Classification (HP)
|
100% |
578
771.7 IPS |
|
Text Classification (Q)
|
91% |
889
1.19 KIPS |
|
Machine Translation (SP)
|
100% |
929
16.0 IPS |
|
Machine Translation (HP)
|
100% |
940
16.2 IPS |
|
Machine Translation (Q)
|
57% |
672
16.4 IPS |