Upload Date | November 20 2024 03:38 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X510 |
Model ID | samsung SM-X510 |
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 | 5.57 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
401
74.6 IPS |
|
Image Classification (HP)
|
100% |
389
72.3 IPS |
|
Image Classification (Q)
|
100% |
1217
226.2 IPS |
|
Image Segmentation (SP)
|
100% |
470
7.62 IPS |
|
Image Segmentation (HP)
|
100% |
498
8.08 IPS |
|
Image Segmentation (Q)
|
98% |
1455
23.7 IPS |
|
Pose Estimation (SP)
|
100% |
1849
2.16 IPS |
|
Pose Estimation (HP)
|
100% |
1767
2.06 IPS |
|
Pose Estimation (Q)
|
84% |
3081
3.65 IPS |
|
Object Detection (SP)
|
100% |
334
26.5 IPS |
|
Object Detection (HP)
|
100% |
339
26.9 IPS |
|
Object Detection (Q)
|
83% |
1018
82.2 IPS |
|
Face Detection (SP)
|
100% |
905
10.8 IPS |
|
Face Detection (HP)
|
100% |
1025
12.2 IPS |
|
Face Detection (Q)
|
95% |
2790
33.3 IPS |
|
Depth Estimation (SP)
|
100% |
1159
8.93 IPS |
|
Depth Estimation (HP)
|
99% |
1178
9.08 IPS |
|
Depth Estimation (Q)
|
64% |
2641
24.2 IPS |
|
Style Transfer (SP)
|
89% |
2782
3.61 IPS |
|
Style Transfer (HP)
|
89% |
2705
3.51 IPS |
|
Style Transfer (Q)
|
98% |
6238
8.04 IPS |
|
Image Super-Resolution (SP)
|
100% |
619
22.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
625
23.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
1420
52.6 IPS |
|
Text Classification (SP)
|
100% |
333
444.7 IPS |
|
Text Classification (HP)
|
100% |
353
470.6 IPS |
|
Text Classification (Q)
|
88% |
651
878.2 IPS |
|
Machine Translation (SP)
|
100% |
552
9.51 IPS |
|
Machine Translation (HP)
|
100% |
495
8.53 IPS |
|
Machine Translation (Q)
|
50% |
296
10.5 IPS |