Upload Date | May 08 2025 06:37 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S938U1 |
Model ID | samsung SM-S938U1 |
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% |
1811
336.7 IPS |
|
Image Classification (HP)
|
100% |
2061
383.3 IPS |
|
Image Classification (Q)
|
100% |
3033
564.0 IPS |
|
Image Segmentation (SP)
|
100% |
2645
42.9 IPS |
|
Image Segmentation (HP)
|
100% |
2613
42.4 IPS |
|
Image Segmentation (Q)
|
98% |
5592
90.9 IPS |
|
Pose Estimation (SP)
|
100% |
5993
6.99 IPS |
|
Pose Estimation (HP)
|
100% |
5726
6.68 IPS |
|
Pose Estimation (Q)
|
84% |
14420
17.1 IPS |
|
Object Detection (SP)
|
98% |
1807
143.8 IPS |
|
Object Detection (HP)
|
98% |
1843
146.6 IPS |
|
Object Detection (Q)
|
83% |
4279
345.7 IPS |
|
Face Detection (SP)
|
100% |
4643
55.2 IPS |
|
Face Detection (HP)
|
100% |
4555
54.1 IPS |
|
Face Detection (Q)
|
95% |
10589
126.4 IPS |
|
Depth Estimation (SP)
|
99% |
4874
37.7 IPS |
|
Depth Estimation (HP)
|
99% |
4715
36.4 IPS |
|
Depth Estimation (Q)
|
64% |
11293
103.4 IPS |
|
Style Transfer (SP)
|
89% |
12249
15.9 IPS |
|
Style Transfer (HP)
|
89% |
12039
15.6 IPS |
|
Style Transfer (Q)
|
98% |
25108
32.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2497
92.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
2510
92.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
6732
249.5 IPS |
|
Text Classification (SP)
|
100% |
1029
1.37 KIPS |
|
Text Classification (HP)
|
99% |
1027
1.37 KIPS |
|
Text Classification (Q)
|
88% |
1076
1.45 KIPS |
|
Machine Translation (SP)
|
100% |
1416
24.4 IPS |
|
Machine Translation (HP)
|
100% |
1400
24.1 IPS |
|
Machine Translation (Q)
|
50% |
600
21.3 IPS |