| User | anewold |
| Upload Date | May 29 2025 12:29 PM |
| Views | 25 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Samsung Exynos 9820 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Samsung Galaxy S10 |
| Model ID | samsung SM-G973F |
| 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 | 7.25 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
221
41.1 IPS |
|
|
Image Classification (HP)
|
100% |
230
42.7 IPS |
|
|
Image Classification (Q)
|
100% |
478
88.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
280
4.53 IPS |
|
|
Image Segmentation (HP)
|
100% |
267
4.33 IPS |
|
|
Image Segmentation (Q)
|
98% |
585
9.51 IPS |
|
|
Pose Estimation (SP)
|
100% |
1039
1.21 IPS |
|
|
Pose Estimation (HP)
|
100% |
1007
1.18 IPS |
|
|
Pose Estimation (Q)
|
84% |
890
1.06 IPS |
|
|
Object Detection (SP)
|
100% |
198
15.7 IPS |
|
|
Object Detection (HP)
|
100% |
197
15.6 IPS |
|
|
Object Detection (Q)
|
83% |
431
34.8 IPS |
|
|
Face Detection (SP)
|
100% |
659
7.83 IPS |
|
|
Face Detection (HP)
|
100% |
639
7.59 IPS |
|
|
Face Detection (Q)
|
95% |
1172
14.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
842
6.49 IPS |
|
|
Depth Estimation (HP)
|
99% |
864
6.65 IPS |
|
|
Depth Estimation (Q)
|
64% |
951
8.71 IPS |
|
|
Style Transfer (SP)
|
89% |
1625
2.11 IPS |
|
|
Style Transfer (HP)
|
89% |
1614
2.09 IPS |
|
|
Style Transfer (Q)
|
98% |
2290
2.95 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
486
18.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
489
18.1 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
530
19.6 IPS |
|
|
Text Classification (SP)
|
100% |
199
265.4 IPS |
|
|
Text Classification (HP)
|
100% |
232
310.0 IPS |
|
|
Text Classification (Q)
|
88% |
321
433.5 IPS |
|
|
Machine Translation (SP)
|
100% |
364
6.27 IPS |
|
|
Machine Translation (HP)
|
100% |
352
6.06 IPS |
|
|
Machine Translation (Q)
|
50% |
206
7.30 IPS |