Upload Date | December 26 2024 03:16 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X518U |
Model ID | samsung SM-X518U |
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 | 5.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
415
77.1 IPS |
|
Image Classification (HP)
|
100% |
421
78.3 IPS |
|
Image Classification (Q)
|
100% |
1340
249.3 IPS |
|
Image Segmentation (SP)
|
100% |
506
8.20 IPS |
|
Image Segmentation (HP)
|
100% |
516
8.36 IPS |
|
Image Segmentation (Q)
|
98% |
1509
24.5 IPS |
|
Pose Estimation (SP)
|
100% |
1797
2.10 IPS |
|
Pose Estimation (HP)
|
100% |
1737
2.03 IPS |
|
Pose Estimation (Q)
|
84% |
3412
4.05 IPS |
|
Object Detection (SP)
|
100% |
338
26.8 IPS |
|
Object Detection (HP)
|
100% |
378
30.0 IPS |
|
Object Detection (Q)
|
83% |
1164
94.0 IPS |
|
Face Detection (SP)
|
100% |
843
10.0 IPS |
|
Face Detection (HP)
|
100% |
875
10.4 IPS |
|
Face Detection (Q)
|
95% |
2807
33.5 IPS |
|
Depth Estimation (SP)
|
100% |
1306
10.1 IPS |
|
Depth Estimation (HP)
|
99% |
1239
9.55 IPS |
|
Depth Estimation (Q)
|
64% |
2944
27.0 IPS |
|
Style Transfer (SP)
|
89% |
3042
3.95 IPS |
|
Style Transfer (HP)
|
89% |
2961
3.84 IPS |
|
Style Transfer (Q)
|
98% |
7190
9.27 IPS |
|
Image Super-Resolution (SP)
|
100% |
828
30.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
683
25.2 IPS |
|
Image Super-Resolution (Q)
|
97% |
1704
63.1 IPS |
|
Text Classification (SP)
|
100% |
413
551.7 IPS |
|
Text Classification (HP)
|
100% |
420
560.7 IPS |
|
Text Classification (Q)
|
88% |
806
1.09 KIPS |
|
Machine Translation (SP)
|
100% |
610
10.5 IPS |
|
Machine Translation (HP)
|
100% |
559
9.62 IPS |
|
Machine Translation (Q)
|
50% |
371
13.2 IPS |