Upload Date | March 30 2025 10:47 AM |
Views | 2 |
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% |
1965
365.4 IPS |
|
Image Classification (HP)
|
100% |
2028
377.1 IPS |
|
Image Classification (Q)
|
100% |
4667
868.0 IPS |
|
Image Segmentation (SP)
|
100% |
2500
40.5 IPS |
|
Image Segmentation (HP)
|
100% |
2539
41.2 IPS |
|
Image Segmentation (Q)
|
98% |
5422
88.2 IPS |
|
Pose Estimation (SP)
|
100% |
5455
6.37 IPS |
|
Pose Estimation (HP)
|
100% |
5371
6.27 IPS |
|
Pose Estimation (Q)
|
84% |
13277
15.7 IPS |
|
Object Detection (SP)
|
98% |
1640
130.5 IPS |
|
Object Detection (HP)
|
98% |
1718
136.7 IPS |
|
Object Detection (Q)
|
83% |
3870
312.6 IPS |
|
Face Detection (SP)
|
100% |
4380
52.0 IPS |
|
Face Detection (HP)
|
100% |
4101
48.7 IPS |
|
Face Detection (Q)
|
95% |
7331
87.5 IPS |
|
Depth Estimation (SP)
|
99% |
3733
28.8 IPS |
|
Depth Estimation (HP)
|
99% |
4541
35.1 IPS |
|
Depth Estimation (Q)
|
64% |
7688
70.4 IPS |
|
Style Transfer (SP)
|
89% |
10919
14.2 IPS |
|
Style Transfer (HP)
|
89% |
11053
14.3 IPS |
|
Style Transfer (Q)
|
98% |
24942
32.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
2221
82.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
2099
77.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
4695
174.0 IPS |
|
Text Classification (SP)
|
100% |
827
1.10 KIPS |
|
Text Classification (HP)
|
99% |
799
1.07 KIPS |
|
Text Classification (Q)
|
88% |
688
927.2 IPS |
|
Machine Translation (SP)
|
100% |
1286
22.1 IPS |
|
Machine Translation (HP)
|
100% |
1344
23.2 IPS |
|
Machine Translation (Q)
|
50% |
543
19.3 IPS |