Upload Date | June 17 2025 05:15 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-S936N |
Model ID | samsung SM-S936N |
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 | 10.85 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
727
135.3 IPS |
|
Image Classification (HP)
|
100% |
818
152.0 IPS |
|
Image Classification (Q)
|
99% |
874
163.1 IPS |
|
Image Segmentation (SP)
|
100% |
1515
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
1433
23.2 IPS |
|
Image Segmentation (Q)
|
98% |
1184
19.2 IPS |
|
Pose Estimation (SP)
|
100% |
1706
1.99 IPS |
|
Pose Estimation (HP)
|
100% |
2959
3.45 IPS |
|
Pose Estimation (Q)
|
96% |
2941
3.45 IPS |
|
Object Detection (SP)
|
100% |
500
39.7 IPS |
|
Object Detection (HP)
|
100% |
1167
92.6 IPS |
|
Object Detection (Q)
|
86% |
1154
92.7 IPS |
|
Face Detection (SP)
|
100% |
3134
37.2 IPS |
|
Face Detection (HP)
|
100% |
3972
47.2 IPS |
|
Face Detection (Q)
|
97% |
4332
51.7 IPS |
|
Depth Estimation (SP)
|
100% |
1649
12.7 IPS |
|
Depth Estimation (HP)
|
99% |
4456
34.4 IPS |
|
Depth Estimation (Q)
|
63% |
3599
33.5 IPS |
|
Style Transfer (SP)
|
100% |
5832
7.50 IPS |
|
Style Transfer (HP)
|
100% |
12352
15.9 IPS |
|
Style Transfer (Q)
|
98% |
11616
15.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
622
23.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
2024
74.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
2083
77.2 IPS |
|
Text Classification (SP)
|
100% |
653
871.8 IPS |
|
Text Classification (HP)
|
100% |
670
894.2 IPS |
|
Text Classification (Q)
|
91% |
1064
1.43 KIPS |
|
Machine Translation (SP)
|
100% |
1013
17.4 IPS |
|
Machine Translation (HP)
|
100% |
998
17.2 IPS |
|
Machine Translation (Q)
|
57% |
678
16.6 IPS |