Upload Date | September 14 2025 02:15 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 16 |
Model | samsung SM-F966U |
Model ID | samsung SM-F966U |
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% |
792
147.3 IPS |
|
Image Classification (HP)
|
100% |
772
143.5 IPS |
|
Image Classification (Q)
|
100% |
1026
190.7 IPS |
|
Image Segmentation (SP)
|
100% |
579
9.39 IPS |
|
Image Segmentation (HP)
|
100% |
707
11.5 IPS |
|
Image Segmentation (Q)
|
98% |
1553
25.3 IPS |
|
Pose Estimation (SP)
|
100% |
1718
2.01 IPS |
|
Pose Estimation (HP)
|
100% |
1448
1.69 IPS |
|
Pose Estimation (Q)
|
84% |
4858
5.76 IPS |
|
Object Detection (SP)
|
98% |
691
55.0 IPS |
|
Object Detection (HP)
|
98% |
839
66.8 IPS |
|
Object Detection (Q)
|
83% |
2098
169.5 IPS |
|
Face Detection (SP)
|
100% |
4373
52.0 IPS |
|
Face Detection (HP)
|
100% |
4323
51.4 IPS |
|
Face Detection (Q)
|
95% |
8798
105.0 IPS |
|
Depth Estimation (SP)
|
99% |
4271
33.0 IPS |
|
Depth Estimation (HP)
|
99% |
3711
28.7 IPS |
|
Depth Estimation (Q)
|
64% |
6291
57.6 IPS |
|
Style Transfer (SP)
|
89% |
7985
10.4 IPS |
|
Style Transfer (HP)
|
89% |
8549
11.1 IPS |
|
Style Transfer (Q)
|
98% |
13748
17.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1694
62.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
1706
63.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
4564
169.1 IPS |
|
Text Classification (SP)
|
100% |
720
960.9 IPS |
|
Text Classification (HP)
|
99% |
841
1.12 KIPS |
|
Text Classification (Q)
|
88% |
699
942.5 IPS |
|
Machine Translation (SP)
|
100% |
1328
22.9 IPS |
|
Machine Translation (HP)
|
100% |
960
16.5 IPS |
|
Machine Translation (Q)
|
50% |
388
13.8 IPS |