Upload Date | April 22 2025 03:28 AM |
Views | 1 |
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% |
2015
374.6 IPS |
|
Image Classification (HP)
|
100% |
1947
362.1 IPS |
|
Image Classification (Q)
|
100% |
4189
778.9 IPS |
|
Image Segmentation (SP)
|
100% |
2399
38.9 IPS |
|
Image Segmentation (HP)
|
100% |
2411
39.1 IPS |
|
Image Segmentation (Q)
|
98% |
3015
49.0 IPS |
|
Pose Estimation (SP)
|
100% |
5616
6.55 IPS |
|
Pose Estimation (HP)
|
100% |
5122
5.98 IPS |
|
Pose Estimation (Q)
|
84% |
9688
11.5 IPS |
|
Object Detection (SP)
|
98% |
1181
94.0 IPS |
|
Object Detection (HP)
|
98% |
1151
91.6 IPS |
|
Object Detection (Q)
|
83% |
2401
194.0 IPS |
|
Face Detection (SP)
|
100% |
3615
43.0 IPS |
|
Face Detection (HP)
|
100% |
3396
40.3 IPS |
|
Face Detection (Q)
|
95% |
7608
90.8 IPS |
|
Depth Estimation (SP)
|
99% |
4458
34.5 IPS |
|
Depth Estimation (HP)
|
99% |
4525
35.0 IPS |
|
Depth Estimation (Q)
|
64% |
10391
95.2 IPS |
|
Style Transfer (SP)
|
89% |
11514
14.9 IPS |
|
Style Transfer (HP)
|
89% |
11441
14.9 IPS |
|
Style Transfer (Q)
|
98% |
17759
22.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
1597
59.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1236
45.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
3427
127.0 IPS |
|
Text Classification (SP)
|
100% |
647
863.5 IPS |
|
Text Classification (HP)
|
99% |
626
835.3 IPS |
|
Text Classification (Q)
|
88% |
413
557.0 IPS |
|
Machine Translation (SP)
|
100% |
1314
22.6 IPS |
|
Machine Translation (HP)
|
100% |
1322
22.8 IPS |
|
Machine Translation (Q)
|
50% |
474
16.8 IPS |