User | KDA |
Upload Date | January 27 2025 12:24 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 8 Gen 2 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy S23 Plus |
Model ID | samsung SM-S916B |
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% |
567
105.4 IPS |
|
Image Classification (HP)
|
100% |
733
136.4 IPS |
|
Image Classification (Q)
|
96% |
676
126.2 IPS |
|
Image Segmentation (SP)
|
100% |
1128
18.3 IPS |
|
Image Segmentation (HP)
|
100% |
1649
26.7 IPS |
|
Image Segmentation (Q)
|
98% |
1544
25.1 IPS |
|
Pose Estimation (SP)
|
100% |
711
0.83 IPS |
|
Pose Estimation (HP)
|
100% |
1150
1.34 IPS |
|
Pose Estimation (Q)
|
96% |
1145
1.34 IPS |
|
Object Detection (SP)
|
100% |
401
31.8 IPS |
|
Object Detection (HP)
|
100% |
649
51.5 IPS |
|
Object Detection (Q)
|
87% |
709
56.9 IPS |
|
Face Detection (SP)
|
100% |
1942
23.1 IPS |
|
Face Detection (HP)
|
100% |
2930
34.8 IPS |
|
Face Detection (Q)
|
97% |
2659
31.7 IPS |
|
Depth Estimation (SP)
|
100% |
1295
9.98 IPS |
|
Depth Estimation (HP)
|
99% |
2441
18.9 IPS |
|
Depth Estimation (Q)
|
63% |
1982
18.4 IPS |
|
Style Transfer (SP)
|
100% |
3193
4.10 IPS |
|
Style Transfer (HP)
|
100% |
7417
9.53 IPS |
|
Style Transfer (Q)
|
98% |
7351
9.48 IPS |
|
Image Super-Resolution (SP)
|
100% |
351
13.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
208
7.67 IPS |
|
Image Super-Resolution (Q)
|
97% |
250
9.28 IPS |
|
Text Classification (SP)
|
100% |
437
582.8 IPS |
|
Text Classification (HP)
|
100% |
438
584.6 IPS |
|
Text Classification (Q)
|
91% |
619
832.5 IPS |
|
Machine Translation (SP)
|
100% |
648
11.2 IPS |
|
Machine Translation (HP)
|
100% |
643
11.1 IPS |
|
Machine Translation (Q)
|
57% |
486
11.9 IPS |