Upload Date | November 07 2024 07:04 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A556B |
Model ID | samsung SM-A556B |
Motherboard | s5e8845 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 2.05 GHz |
Cluster 1 | 4 Cores @ 2.05 GHz |
Cluster 2 | 4 Cores @ 2.75 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
491
91.2 IPS |
|
Image Classification (HP)
|
100% |
491
91.4 IPS |
|
Image Classification (Q)
|
100% |
1489
276.8 IPS |
|
Image Segmentation (SP)
|
100% |
560
9.08 IPS |
|
Image Segmentation (HP)
|
100% |
557
9.02 IPS |
|
Image Segmentation (Q)
|
98% |
1423
23.1 IPS |
|
Pose Estimation (SP)
|
100% |
1974
2.30 IPS |
|
Pose Estimation (HP)
|
100% |
1876
2.19 IPS |
|
Pose Estimation (Q)
|
84% |
2896
3.43 IPS |
|
Object Detection (SP)
|
100% |
396
31.5 IPS |
|
Object Detection (HP)
|
100% |
403
32.0 IPS |
|
Object Detection (Q)
|
83% |
1184
95.6 IPS |
|
Face Detection (SP)
|
100% |
1162
13.8 IPS |
|
Face Detection (HP)
|
100% |
1141
13.6 IPS |
|
Face Detection (Q)
|
95% |
2706
32.3 IPS |
|
Depth Estimation (SP)
|
100% |
1535
11.8 IPS |
|
Depth Estimation (HP)
|
99% |
1580
12.2 IPS |
|
Depth Estimation (Q)
|
64% |
2686
24.6 IPS |
|
Style Transfer (SP)
|
89% |
3220
4.18 IPS |
|
Style Transfer (HP)
|
89% |
3215
4.17 IPS |
|
Style Transfer (Q)
|
98% |
6837
8.82 IPS |
|
Image Super-Resolution (SP)
|
100% |
824
30.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
849
31.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1633
60.5 IPS |
|
Text Classification (SP)
|
100% |
427
570.1 IPS |
|
Text Classification (HP)
|
100% |
424
566.0 IPS |
|
Text Classification (Q)
|
88% |
783
1.06 KIPS |
|
Machine Translation (SP)
|
100% |
706
12.2 IPS |
|
Machine Translation (HP)
|
100% |
742
12.8 IPS |
|
Machine Translation (Q)
|
50% |
457
16.2 IPS |