| User | robo4iken |
| Upload Date | September 27 2024 08:22 PM |
| Views | 12 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Qualcomm Snapdragon 855 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Samsung Galaxy S10+ |
| Model ID | samsung SM-G9750 |
| Motherboard | msmnile |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 7.29 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
434
80.6 IPS |
|
|
Image Classification (HP)
|
100% |
444
82.6 IPS |
|
|
Image Classification (Q)
|
100% |
1180
219.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
544
8.82 IPS |
|
|
Image Segmentation (HP)
|
100% |
541
8.78 IPS |
|
|
Image Segmentation (Q)
|
98% |
1457
23.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
1884
2.20 IPS |
|
|
Pose Estimation (HP)
|
100% |
1768
2.06 IPS |
|
|
Pose Estimation (Q)
|
84% |
2924
3.47 IPS |
|
|
Object Detection (SP)
|
100% |
364
28.9 IPS |
|
|
Object Detection (HP)
|
100% |
392
31.1 IPS |
|
|
Object Detection (Q)
|
83% |
1157
93.5 IPS |
|
|
Face Detection (SP)
|
100% |
1270
15.1 IPS |
|
|
Face Detection (HP)
|
100% |
1274
15.1 IPS |
|
|
Face Detection (Q)
|
95% |
2743
32.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
1498
11.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
1539
11.9 IPS |
|
|
Depth Estimation (Q)
|
64% |
2656
24.3 IPS |
|
|
Style Transfer (SP)
|
89% |
3035
3.94 IPS |
|
|
Style Transfer (HP)
|
89% |
3120
4.05 IPS |
|
|
Style Transfer (Q)
|
98% |
5766
7.43 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
890
32.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
288
10.6 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
623
23.1 IPS |
|
|
Text Classification (SP)
|
100% |
156
207.8 IPS |
|
|
Text Classification (HP)
|
100% |
156
208.4 IPS |
|
|
Text Classification (Q)
|
88% |
270
363.5 IPS |
|
|
Machine Translation (SP)
|
100% |
256
4.40 IPS |
|
|
Machine Translation (HP)
|
100% |
252
4.34 IPS |
|
|
Machine Translation (Q)
|
50% |
163
5.78 IPS |