Upload Date | July 03 2025 08:25 AM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-G970F |
Model ID | samsung SM-G970F |
Motherboard | exynos9820 |
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 @ 2.31 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 5.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
84
15.7 IPS |
|
Image Classification (HP)
|
100% |
88
16.3 IPS |
|
Image Classification (Q)
|
99% |
215
40.0 IPS |
|
Image Segmentation (SP)
|
100% |
175
2.84 IPS |
|
Image Segmentation (HP)
|
100% |
211
3.41 IPS |
|
Image Segmentation (Q)
|
98% |
402
6.54 IPS |
|
Pose Estimation (SP)
|
100% |
1065
1.24 IPS |
|
Pose Estimation (HP)
|
100% |
4317
5.04 IPS |
|
Pose Estimation (Q)
|
98% |
945
1.11 IPS |
|
Object Detection (SP)
|
100% |
156
12.4 IPS |
|
Object Detection (HP)
|
100% |
158
12.6 IPS |
|
Object Detection (Q)
|
87% |
373
29.9 IPS |
|
Face Detection (SP)
|
100% |
400
4.75 IPS |
|
Face Detection (HP)
|
100% |
409
4.86 IPS |
|
Face Detection (Q)
|
97% |
666
7.94 IPS |
|
Depth Estimation (SP)
|
100% |
218
1.68 IPS |
|
Depth Estimation (HP)
|
99% |
192
1.48 IPS |
|
Depth Estimation (Q)
|
64% |
508
4.61 IPS |
|
Style Transfer (SP)
|
100% |
673
0.87 IPS |
|
Style Transfer (HP)
|
100% |
595
0.77 IPS |
|
Style Transfer (Q)
|
98% |
380
0.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
378
13.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
722
26.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
564
20.9 IPS |
|
Text Classification (SP)
|
100% |
25
33.7 IPS |
|
Text Classification (HP)
|
100% |
234
312.9 IPS |
|
Text Classification (Q)
|
91% |
24
32.5 IPS |
|
Machine Translation (SP)
|
100% |
381
6.57 IPS |
|
Machine Translation (HP)
|
100% |
334
5.76 IPS |
|
Machine Translation (Q)
|
57% |
291
7.11 IPS |