Upload Date | April 13 2025 02:17 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S936B |
Model ID | samsung SM-S936B |
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% |
720
134.0 IPS |
|
Image Classification (HP)
|
100% |
826
153.6 IPS |
|
Image Classification (Q)
|
99% |
940
175.4 IPS |
|
Image Segmentation (SP)
|
100% |
1624
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
2028
32.9 IPS |
|
Image Segmentation (Q)
|
98% |
1784
29.0 IPS |
|
Pose Estimation (SP)
|
100% |
1709
1.99 IPS |
|
Pose Estimation (HP)
|
100% |
2968
3.46 IPS |
|
Pose Estimation (Q)
|
96% |
2538
2.97 IPS |
|
Object Detection (SP)
|
100% |
504
39.9 IPS |
|
Object Detection (HP)
|
100% |
1093
86.7 IPS |
|
Object Detection (Q)
|
86% |
1014
81.4 IPS |
|
Face Detection (SP)
|
100% |
2861
34.0 IPS |
|
Face Detection (HP)
|
100% |
4013
47.7 IPS |
|
Face Detection (Q)
|
97% |
3419
40.8 IPS |
|
Depth Estimation (SP)
|
100% |
1605
12.4 IPS |
|
Depth Estimation (HP)
|
99% |
4551
35.2 IPS |
|
Depth Estimation (Q)
|
63% |
3766
35.0 IPS |
|
Style Transfer (SP)
|
100% |
5261
6.76 IPS |
|
Style Transfer (HP)
|
100% |
10953
14.1 IPS |
|
Style Transfer (Q)
|
98% |
11110
14.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
644
23.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
1903
70.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
1925
71.3 IPS |
|
Text Classification (SP)
|
100% |
679
906.3 IPS |
|
Text Classification (HP)
|
100% |
681
908.5 IPS |
|
Text Classification (Q)
|
91% |
1074
1.44 KIPS |
|
Machine Translation (SP)
|
100% |
1045
18.0 IPS |
|
Machine Translation (HP)
|
100% |
1028
17.7 IPS |
|
Machine Translation (Q)
|
57% |
727
17.8 IPS |