Upload Date | September 08 2024 12:22 PM |
Views | 10 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
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% |
110
20.5 IPS |
|
Image Classification (HP)
|
100% |
88
16.3 IPS |
|
Image Classification (Q)
|
99% |
77
14.3 IPS |
|
Image Segmentation (SP)
|
100% |
174
2.82 IPS |
|
Image Segmentation (HP)
|
100% |
219
3.55 IPS |
|
Image Segmentation (Q)
|
98% |
89
1.46 IPS |
|
Pose Estimation (SP)
|
100% |
583
0.68 IPS |
|
Pose Estimation (HP)
|
100% |
2562
2.99 IPS |
|
Pose Estimation (Q)
|
98% |
505
0.59 IPS |
|
Object Detection (SP)
|
100% |
85
6.75 IPS |
|
Object Detection (HP)
|
100% |
86
6.85 IPS |
|
Object Detection (Q)
|
87% |
78
6.28 IPS |
|
Face Detection (SP)
|
100% |
220
2.62 IPS |
|
Face Detection (HP)
|
100% |
218
2.60 IPS |
|
Face Detection (Q)
|
97% |
415
4.95 IPS |
|
Depth Estimation (SP)
|
100% |
190
1.47 IPS |
|
Depth Estimation (HP)
|
99% |
190
1.46 IPS |
|
Depth Estimation (Q)
|
64% |
392
3.55 IPS |
|
Style Transfer (SP)
|
100% |
243
0.31 IPS |
|
Style Transfer (HP)
|
100% |
341
0.44 IPS |
|
Style Transfer (Q)
|
98% |
172
0.22 IPS |
|
Image Super-Resolution (SP)
|
100% |
294
10.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
643
23.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
294
10.9 IPS |
|
Text Classification (SP)
|
100% |
38
50.6 IPS |
|
Text Classification (HP)
|
100% |
58
76.9 IPS |
|
Text Classification (Q)
|
91% |
30
40.9 IPS |
|
Machine Translation (SP)
|
100% |
100
1.72 IPS |
|
Machine Translation (HP)
|
100% |
192
3.31 IPS |
|
Machine Translation (Q)
|
57% |
161
3.93 IPS |