| User | robo4iken |
| Upload Date | September 27 2024 08:30 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Qualcomm Snapdragon 8 Gen 1 |
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S22 Ultra |
| Model ID | samsung SM-S908U1 |
| Motherboard | taro |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.50 GHz |
| Cluster 3 | 1 Core @ 3.00 GHz |
| Memory Information | |
|---|---|
| Size | 7.06 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1241
230.9 IPS |
|
|
Image Classification (HP)
|
100% |
973
180.9 IPS |
|
|
Image Classification (Q)
|
100% |
1391
258.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1050
17.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
1046
17.0 IPS |
|
|
Image Segmentation (Q)
|
98% |
1513
24.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2034
2.37 IPS |
|
|
Pose Estimation (HP)
|
100% |
2013
2.35 IPS |
|
|
Pose Estimation (Q)
|
84% |
3983
4.72 IPS |
|
|
Object Detection (SP)
|
98% |
789
62.8 IPS |
|
|
Object Detection (HP)
|
98% |
882
70.2 IPS |
|
|
Object Detection (Q)
|
83% |
1092
88.2 IPS |
|
|
Face Detection (SP)
|
100% |
1670
19.8 IPS |
|
|
Face Detection (HP)
|
100% |
1698
20.2 IPS |
|
|
Face Detection (Q)
|
95% |
2547
30.4 IPS |
|
|
Depth Estimation (SP)
|
99% |
1921
14.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
1704
13.2 IPS |
|
|
Depth Estimation (Q)
|
64% |
2718
24.9 IPS |
|
|
Style Transfer (SP)
|
89% |
4003
5.20 IPS |
|
|
Style Transfer (HP)
|
89% |
4028
5.23 IPS |
|
|
Style Transfer (Q)
|
98% |
7166
9.24 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
935
34.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
940
34.7 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1804
66.8 IPS |
|
|
Text Classification (SP)
|
100% |
347
463.1 IPS |
|
|
Text Classification (HP)
|
99% |
369
492.5 IPS |
|
|
Text Classification (Q)
|
88% |
591
797.4 IPS |
|
|
Machine Translation (SP)
|
100% |
959
16.5 IPS |
|
|
Machine Translation (HP)
|
100% |
934
16.1 IPS |
|
|
Machine Translation (Q)
|
50% |
419
14.9 IPS |