Upload Date | June 16 2025 05:43 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-S936U1 |
Model ID | samsung SM-S936U1 |
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% |
1300
241.7 IPS |
|
Image Classification (HP)
|
100% |
1317
245.0 IPS |
|
Image Classification (Q)
|
100% |
3676
683.7 IPS |
|
Image Segmentation (SP)
|
100% |
1767
28.7 IPS |
|
Image Segmentation (HP)
|
100% |
1901
30.8 IPS |
|
Image Segmentation (Q)
|
98% |
4036
65.6 IPS |
|
Pose Estimation (SP)
|
100% |
3830
4.47 IPS |
|
Pose Estimation (HP)
|
100% |
2693
3.14 IPS |
|
Pose Estimation (Q)
|
84% |
7501
8.90 IPS |
|
Object Detection (SP)
|
98% |
894
71.2 IPS |
|
Object Detection (HP)
|
98% |
974
77.5 IPS |
|
Object Detection (Q)
|
83% |
2140
172.9 IPS |
|
Face Detection (SP)
|
100% |
2923
34.7 IPS |
|
Face Detection (HP)
|
100% |
3140
37.3 IPS |
|
Face Detection (Q)
|
95% |
5107
61.0 IPS |
|
Depth Estimation (SP)
|
99% |
2707
20.9 IPS |
|
Depth Estimation (HP)
|
99% |
2390
18.5 IPS |
|
Depth Estimation (Q)
|
64% |
6303
57.7 IPS |
|
Style Transfer (SP)
|
89% |
7833
10.2 IPS |
|
Style Transfer (HP)
|
89% |
8472
11.0 IPS |
|
Style Transfer (Q)
|
98% |
11760
15.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
1070
39.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
1285
47.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
2813
104.2 IPS |
|
Text Classification (SP)
|
100% |
704
939.3 IPS |
|
Text Classification (HP)
|
99% |
421
561.3 IPS |
|
Text Classification (Q)
|
88% |
683
921.1 IPS |
|
Machine Translation (SP)
|
100% |
1053
18.1 IPS |
|
Machine Translation (HP)
|
100% |
621
10.7 IPS |
|
Machine Translation (Q)
|
50% |
161
5.70 IPS |