Upload Date | December 25 2024 04:15 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-N975F |
Model ID | samsung SM-N975F |
Motherboard | exynos9825 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 3 revision 0 |
Base Frequency | 1.95 GHz |
Cluster 1 | 4 Cores @ 1.95 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 11.15 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
270
50.3 IPS |
|
Image Classification (HP)
|
100% |
246
45.7 IPS |
|
Image Classification (Q)
|
100% |
496
92.3 IPS |
|
Image Segmentation (SP)
|
100% |
294
4.77 IPS |
|
Image Segmentation (HP)
|
100% |
290
4.70 IPS |
|
Image Segmentation (Q)
|
98% |
615
10.0 IPS |
|
Pose Estimation (SP)
|
100% |
1060
1.24 IPS |
|
Pose Estimation (HP)
|
100% |
1035
1.21 IPS |
|
Pose Estimation (Q)
|
84% |
949
1.13 IPS |
|
Object Detection (SP)
|
100% |
210
16.7 IPS |
|
Object Detection (HP)
|
100% |
207
16.4 IPS |
|
Object Detection (Q)
|
83% |
456
36.8 IPS |
|
Face Detection (SP)
|
100% |
708
8.41 IPS |
|
Face Detection (HP)
|
100% |
684
8.12 IPS |
|
Face Detection (Q)
|
95% |
1257
15.0 IPS |
|
Depth Estimation (SP)
|
100% |
901
6.94 IPS |
|
Depth Estimation (HP)
|
99% |
882
6.79 IPS |
|
Depth Estimation (Q)
|
64% |
1000
9.15 IPS |
|
Style Transfer (SP)
|
89% |
1707
2.22 IPS |
|
Style Transfer (HP)
|
89% |
1713
2.22 IPS |
|
Style Transfer (Q)
|
98% |
2284
2.95 IPS |
|
Image Super-Resolution (SP)
|
100% |
511
18.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
495
18.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
561
20.8 IPS |
|
Text Classification (SP)
|
100% |
253
337.4 IPS |
|
Text Classification (HP)
|
100% |
232
309.3 IPS |
|
Text Classification (Q)
|
88% |
379
510.6 IPS |
|
Machine Translation (SP)
|
100% |
356
6.14 IPS |
|
Machine Translation (HP)
|
100% |
346
5.96 IPS |
|
Machine Translation (Q)
|
50% |
213
7.55 IPS |