Upload Date | September 18 2024 03:13 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Samsung Exynos 2200 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S22 Ultra |
Model ID | samsung SM-S908B |
Motherboard | s5e9925 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.82 GHz |
Cluster 1 | 4 Cores @ 1.82 GHz |
Cluster 2 | 3 Cores @ 2.52 GHz |
Cluster 3 | 1 Core @ 2.80 GHz |
Memory Information | |
---|---|
Size | 10.27 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1497
278.4 IPS |
|
Image Classification (HP)
|
100% |
1316
244.8 IPS |
|
Image Classification (Q)
|
100% |
2083
387.3 IPS |
|
Image Segmentation (SP)
|
100% |
1457
23.6 IPS |
|
Image Segmentation (HP)
|
100% |
1451
23.5 IPS |
|
Image Segmentation (Q)
|
98% |
2396
39.0 IPS |
|
Pose Estimation (SP)
|
100% |
2488
2.90 IPS |
|
Pose Estimation (HP)
|
100% |
2424
2.83 IPS |
|
Pose Estimation (Q)
|
84% |
5391
6.39 IPS |
|
Object Detection (SP)
|
98% |
1207
96.0 IPS |
|
Object Detection (HP)
|
98% |
1134
90.2 IPS |
|
Object Detection (Q)
|
83% |
1857
150.0 IPS |
|
Face Detection (SP)
|
100% |
2196
26.1 IPS |
|
Face Detection (HP)
|
100% |
2125
25.2 IPS |
|
Face Detection (Q)
|
95% |
3930
46.9 IPS |
|
Depth Estimation (SP)
|
99% |
2402
18.6 IPS |
|
Depth Estimation (HP)
|
99% |
2497
19.3 IPS |
|
Depth Estimation (Q)
|
64% |
3538
32.4 IPS |
|
Style Transfer (SP)
|
89% |
5053
6.56 IPS |
|
Style Transfer (HP)
|
89% |
4250
5.52 IPS |
|
Style Transfer (Q)
|
98% |
7597
9.80 IPS |
|
Image Super-Resolution (SP)
|
100% |
908
33.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
969
35.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1816
67.3 IPS |
|
Text Classification (SP)
|
100% |
373
498.4 IPS |
|
Text Classification (HP)
|
99% |
340
454.1 IPS |
|
Text Classification (Q)
|
88% |
689
928.9 IPS |
|
Machine Translation (SP)
|
100% |
831
14.3 IPS |
|
Machine Translation (HP)
|
100% |
790
13.6 IPS |
|
Machine Translation (Q)
|
50% |
406
14.4 IPS |