Upload Date | July 12 2025 08:52 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-F9660 |
Model ID | samsung SM-F9660 |
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% |
1768
328.8 IPS |
|
Image Classification (HP)
|
100% |
2170
403.5 IPS |
|
Image Classification (Q)
|
100% |
4476
832.5 IPS |
|
Image Segmentation (SP)
|
100% |
2433
39.4 IPS |
|
Image Segmentation (HP)
|
100% |
2327
37.7 IPS |
|
Image Segmentation (Q)
|
98% |
5016
81.6 IPS |
|
Pose Estimation (SP)
|
100% |
4887
5.70 IPS |
|
Pose Estimation (HP)
|
100% |
3614
4.22 IPS |
|
Pose Estimation (Q)
|
84% |
9644
11.4 IPS |
|
Object Detection (SP)
|
98% |
1198
95.3 IPS |
|
Object Detection (HP)
|
98% |
1223
97.3 IPS |
|
Object Detection (Q)
|
83% |
3184
257.2 IPS |
|
Face Detection (SP)
|
100% |
3834
45.6 IPS |
|
Face Detection (HP)
|
100% |
3841
45.6 IPS |
|
Face Detection (Q)
|
95% |
7825
93.4 IPS |
|
Depth Estimation (SP)
|
99% |
4314
33.3 IPS |
|
Depth Estimation (HP)
|
99% |
4076
31.5 IPS |
|
Depth Estimation (Q)
|
64% |
7945
72.8 IPS |
|
Style Transfer (SP)
|
89% |
9311
12.1 IPS |
|
Style Transfer (HP)
|
89% |
8518
11.1 IPS |
|
Style Transfer (Q)
|
98% |
17630
22.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1906
70.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
2006
74.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
4861
180.1 IPS |
|
Text Classification (SP)
|
100% |
905
1.21 KIPS |
|
Text Classification (HP)
|
99% |
596
795.5 IPS |
|
Text Classification (Q)
|
88% |
647
872.0 IPS |
|
Machine Translation (SP)
|
100% |
1386
23.9 IPS |
|
Machine Translation (HP)
|
100% |
1075
18.5 IPS |
|
Machine Translation (Q)
|
50% |
454
16.1 IPS |