Upload Date | April 10 2025 04:02 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S938B |
Model ID | samsung SM-S938B |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.47 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1303
242.4 IPS |
|
Image Classification (HP)
|
100% |
1733
322.3 IPS |
|
Image Classification (Q)
|
100% |
3679
684.2 IPS |
|
Image Segmentation (SP)
|
100% |
1591
25.8 IPS |
|
Image Segmentation (HP)
|
100% |
1949
31.6 IPS |
|
Image Segmentation (Q)
|
98% |
4848
78.8 IPS |
|
Pose Estimation (SP)
|
100% |
4524
5.28 IPS |
|
Pose Estimation (HP)
|
100% |
4527
5.28 IPS |
|
Pose Estimation (Q)
|
84% |
10445
12.4 IPS |
|
Object Detection (SP)
|
98% |
1431
113.9 IPS |
|
Object Detection (HP)
|
98% |
1501
119.4 IPS |
|
Object Detection (Q)
|
83% |
2353
190.1 IPS |
|
Face Detection (SP)
|
100% |
3663
43.5 IPS |
|
Face Detection (HP)
|
100% |
3864
45.9 IPS |
|
Face Detection (Q)
|
95% |
8275
98.8 IPS |
|
Depth Estimation (SP)
|
99% |
3979
30.8 IPS |
|
Depth Estimation (HP)
|
99% |
3852
29.8 IPS |
|
Depth Estimation (Q)
|
64% |
9093
83.3 IPS |
|
Style Transfer (SP)
|
89% |
10612
13.8 IPS |
|
Style Transfer (HP)
|
89% |
10769
14.0 IPS |
|
Style Transfer (Q)
|
98% |
24506
31.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2263
83.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
2000
73.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
4571
169.4 IPS |
|
Text Classification (SP)
|
100% |
710
947.5 IPS |
|
Text Classification (HP)
|
99% |
670
894.7 IPS |
|
Text Classification (Q)
|
88% |
576
776.8 IPS |
|
Machine Translation (SP)
|
100% |
1402
24.1 IPS |
|
Machine Translation (HP)
|
100% |
1294
22.3 IPS |
|
Machine Translation (Q)
|
50% |
554
19.7 IPS |