Upload Date | January 12 2025 12:12 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A356B |
Model ID | samsung SM-A356B |
Motherboard | s5e8835 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
382
71.0 IPS |
|
Image Classification (HP)
|
100% |
381
70.9 IPS |
|
Image Classification (Q)
|
100% |
1199
222.9 IPS |
|
Image Segmentation (SP)
|
100% |
505
8.19 IPS |
|
Image Segmentation (HP)
|
100% |
493
8.00 IPS |
|
Image Segmentation (Q)
|
98% |
1525
24.8 IPS |
|
Pose Estimation (SP)
|
100% |
1765
2.06 IPS |
|
Pose Estimation (HP)
|
100% |
1813
2.12 IPS |
|
Pose Estimation (Q)
|
84% |
3394
4.02 IPS |
|
Object Detection (SP)
|
100% |
386
30.6 IPS |
|
Object Detection (HP)
|
100% |
385
30.5 IPS |
|
Object Detection (Q)
|
83% |
1098
88.7 IPS |
|
Face Detection (SP)
|
100% |
934
11.1 IPS |
|
Face Detection (HP)
|
100% |
939
11.2 IPS |
|
Face Detection (Q)
|
95% |
2839
33.9 IPS |
|
Depth Estimation (SP)
|
100% |
1322
10.2 IPS |
|
Depth Estimation (HP)
|
99% |
1321
10.2 IPS |
|
Depth Estimation (Q)
|
64% |
2831
25.9 IPS |
|
Style Transfer (SP)
|
89% |
3187
4.14 IPS |
|
Style Transfer (HP)
|
89% |
3164
4.11 IPS |
|
Style Transfer (Q)
|
98% |
7159
9.23 IPS |
|
Image Super-Resolution (SP)
|
100% |
812
30.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
723
26.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1623
60.2 IPS |
|
Text Classification (SP)
|
100% |
385
513.9 IPS |
|
Text Classification (HP)
|
100% |
385
514.5 IPS |
|
Text Classification (Q)
|
88% |
714
963.0 IPS |
|
Machine Translation (SP)
|
100% |
621
10.7 IPS |
|
Machine Translation (HP)
|
100% |
606
10.4 IPS |
|
Machine Translation (Q)
|
50% |
359
12.8 IPS |