Upload Date | December 22 2024 01:37 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 |
Model ID | samsung SM-S911B |
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 | 6.89 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1049
195.1 IPS |
|
Image Classification (HP)
|
100% |
692
128.7 IPS |
|
Image Classification (Q)
|
100% |
1337
248.6 IPS |
|
Image Segmentation (SP)
|
100% |
757
12.3 IPS |
|
Image Segmentation (HP)
|
100% |
441
7.14 IPS |
|
Image Segmentation (Q)
|
98% |
1675
27.2 IPS |
|
Pose Estimation (SP)
|
100% |
2063
2.41 IPS |
|
Pose Estimation (HP)
|
100% |
1819
2.12 IPS |
|
Pose Estimation (Q)
|
84% |
3730
4.42 IPS |
|
Object Detection (SP)
|
98% |
719
57.2 IPS |
|
Object Detection (HP)
|
98% |
663
52.7 IPS |
|
Object Detection (Q)
|
83% |
1260
101.8 IPS |
|
Face Detection (SP)
|
100% |
1218
14.5 IPS |
|
Face Detection (HP)
|
100% |
1214
14.4 IPS |
|
Face Detection (Q)
|
95% |
2738
32.7 IPS |
|
Depth Estimation (SP)
|
99% |
1361
10.5 IPS |
|
Depth Estimation (HP)
|
99% |
1080
8.34 IPS |
|
Depth Estimation (Q)
|
64% |
2629
24.1 IPS |
|
Style Transfer (SP)
|
89% |
2510
3.26 IPS |
|
Style Transfer (HP)
|
89% |
3727
4.84 IPS |
|
Style Transfer (Q)
|
98% |
7462
9.62 IPS |
|
Image Super-Resolution (SP)
|
100% |
698
25.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
832
30.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1828
67.7 IPS |
|
Text Classification (SP)
|
100% |
458
611.7 IPS |
|
Text Classification (HP)
|
99% |
456
608.1 IPS |
|
Text Classification (Q)
|
88% |
686
925.2 IPS |
|
Machine Translation (SP)
|
100% |
875
15.1 IPS |
|
Machine Translation (HP)
|
100% |
863
14.9 IPS |
|
Machine Translation (Q)
|
50% |
518
18.4 IPS |