Upload Date | March 28 2025 09:33 AM |
Views | 13 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Allwinner A537 K83 |
Model ID | Allwinner A537 K83 |
Motherboard | exdroid |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3337 revision 0 |
Base Frequency | 1.42 GHz |
Cluster 1 | 4 Cores @ 1.42 GHz |
Cluster 2 | 2 Cores @ 1.51 GHz |
Cluster 3 | 2 Cores @ 1.80 GHz |
Memory Information | |
---|---|
Size | 3.80 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
76
14.2 IPS |
|
Image Classification (HP)
|
100% |
78
14.5 IPS |
|
Image Classification (Q)
|
100% |
108
20.1 IPS |
|
Image Segmentation (SP)
|
100% |
99
1.61 IPS |
|
Image Segmentation (HP)
|
100% |
99
1.61 IPS |
|
Image Segmentation (Q)
|
98% |
142
2.31 IPS |
|
Pose Estimation (SP)
|
100% |
338
0.39 IPS |
|
Pose Estimation (HP)
|
100% |
342
0.40 IPS |
|
Pose Estimation (Q)
|
84% |
256
0.30 IPS |
|
Object Detection (SP)
|
100% |
77
6.14 IPS |
|
Object Detection (HP)
|
100% |
79
6.24 IPS |
|
Object Detection (Q)
|
83% |
109
8.78 IPS |
|
Face Detection (SP)
|
100% |
187
2.23 IPS |
|
Face Detection (HP)
|
100% |
181
2.15 IPS |
|
Face Detection (Q)
|
95% |
258
3.07 IPS |
|
Depth Estimation (SP)
|
100% |
183
1.41 IPS |
|
Depth Estimation (HP)
|
99% |
230
1.77 IPS |
|
Depth Estimation (Q)
|
64% |
252
2.31 IPS |
|
Style Transfer (SP)
|
89% |
644
0.84 IPS |
|
Style Transfer (HP)
|
89% |
643
0.83 IPS |
|
Style Transfer (Q)
|
98% |
679
0.88 IPS |
|
Image Super-Resolution (SP)
|
100% |
130
4.81 IPS |
|
Image Super-Resolution (HP)
|
100% |
131
4.84 IPS |
|
Image Super-Resolution (Q)
|
97% |
147
5.45 IPS |
|
Text Classification (SP)
|
100% |
76
101.4 IPS |
|
Text Classification (HP)
|
100% |
73
97.7 IPS |
|
Text Classification (Q)
|
88% |
78
105.4 IPS |
|
Machine Translation (SP)
|
100% |
120
2.07 IPS |
|
Machine Translation (HP)
|
100% |
116
2.00 IPS |
|
Machine Translation (Q)
|
50% |
50
1.77 IPS |