Upload Date | June 24 2025 06:41 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
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% |
452
84.0 IPS |
|
Image Classification (HP)
|
100% |
450
83.8 IPS |
|
Image Classification (Q)
|
99% |
1122
209.2 IPS |
|
Image Segmentation (SP)
|
100% |
583
9.45 IPS |
|
Image Segmentation (HP)
|
100% |
585
9.48 IPS |
|
Image Segmentation (Q)
|
98% |
1185
19.3 IPS |
|
Pose Estimation (SP)
|
100% |
762
0.89 IPS |
|
Pose Estimation (HP)
|
100% |
747
0.87 IPS |
|
Pose Estimation (Q)
|
98% |
2880
3.37 IPS |
|
Object Detection (SP)
|
100% |
409
32.4 IPS |
|
Object Detection (HP)
|
100% |
409
32.5 IPS |
|
Object Detection (Q)
|
87% |
1087
87.2 IPS |
|
Face Detection (SP)
|
100% |
1022
12.1 IPS |
|
Face Detection (HP)
|
100% |
1014
12.0 IPS |
|
Face Detection (Q)
|
97% |
2408
28.7 IPS |
|
Depth Estimation (SP)
|
100% |
904
6.96 IPS |
|
Depth Estimation (HP)
|
99% |
875
6.74 IPS |
|
Depth Estimation (Q)
|
64% |
1833
16.6 IPS |
|
Style Transfer (SP)
|
100% |
1582
2.03 IPS |
|
Style Transfer (HP)
|
100% |
1479
1.90 IPS |
|
Style Transfer (Q)
|
98% |
3805
4.91 IPS |
|
Image Super-Resolution (SP)
|
100% |
426
15.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
454
16.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1603
59.4 IPS |
|
Text Classification (SP)
|
100% |
574
766.3 IPS |
|
Text Classification (HP)
|
100% |
576
768.2 IPS |
|
Text Classification (Q)
|
91% |
888
1.19 KIPS |
|
Machine Translation (SP)
|
100% |
1011
17.4 IPS |
|
Machine Translation (HP)
|
100% |
1021
17.6 IPS |
|
Machine Translation (Q)
|
57% |
666
16.3 IPS |