Upload Date | September 18 2024 05:22 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 Ultra |
Model ID | samsung SM-S918U1 |
Motherboard | kalama |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.36 GHz |
Memory Information | |
---|---|
Size | 10.77 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1010
187.9 IPS |
|
Image Classification (HP)
|
100% |
692
128.7 IPS |
|
Image Classification (Q)
|
100% |
1215
225.9 IPS |
|
Image Segmentation (SP)
|
100% |
656
10.6 IPS |
|
Image Segmentation (HP)
|
100% |
438
7.09 IPS |
|
Image Segmentation (Q)
|
98% |
1697
27.6 IPS |
|
Pose Estimation (SP)
|
100% |
1951
2.28 IPS |
|
Pose Estimation (HP)
|
100% |
1295
1.51 IPS |
|
Pose Estimation (Q)
|
84% |
3621
4.29 IPS |
|
Object Detection (SP)
|
98% |
682
54.2 IPS |
|
Object Detection (HP)
|
98% |
623
49.6 IPS |
|
Object Detection (Q)
|
83% |
1181
95.4 IPS |
|
Face Detection (SP)
|
100% |
1069
12.7 IPS |
|
Face Detection (HP)
|
100% |
1104
13.1 IPS |
|
Face Detection (Q)
|
95% |
1689
20.2 IPS |
|
Depth Estimation (SP)
|
99% |
1408
10.9 IPS |
|
Depth Estimation (HP)
|
99% |
1137
8.78 IPS |
|
Depth Estimation (Q)
|
64% |
2311
21.2 IPS |
|
Style Transfer (SP)
|
89% |
2858
3.71 IPS |
|
Style Transfer (HP)
|
89% |
2940
3.82 IPS |
|
Style Transfer (Q)
|
98% |
4520
5.83 IPS |
|
Image Super-Resolution (SP)
|
100% |
755
27.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
678
25.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
1198
44.4 IPS |
|
Text Classification (SP)
|
100% |
349
466.1 IPS |
|
Text Classification (HP)
|
99% |
349
465.6 IPS |
|
Text Classification (Q)
|
88% |
544
733.4 IPS |
|
Machine Translation (SP)
|
100% |
679
11.7 IPS |
|
Machine Translation (HP)
|
100% |
706
12.2 IPS |
|
Machine Translation (Q)
|
50% |
391
13.9 IPS |