Upload Date | April 11 2025 04:11 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Allwinner A537 PRO |
Model ID | Allwinner A537 PRO |
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 | 1.20 GHz |
Cluster 1 | 4 Cores @ 1.20 GHz |
Cluster 2 | 2 Cores @ 1.51 GHz |
Cluster 3 | 2 Cores @ 1.54 GHz |
Memory Information | |
---|---|
Size | 5.62 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
80
14.9 IPS |
|
Image Classification (HP)
|
100% |
82
15.2 IPS |
|
Image Classification (Q)
|
100% |
99
18.4 IPS |
|
Image Segmentation (SP)
|
100% |
105
1.70 IPS |
|
Image Segmentation (HP)
|
100% |
108
1.76 IPS |
|
Image Segmentation (Q)
|
98% |
139
2.26 IPS |
|
Pose Estimation (SP)
|
100% |
379
0.44 IPS |
|
Pose Estimation (HP)
|
100% |
357
0.42 IPS |
|
Pose Estimation (Q)
|
84% |
244
0.29 IPS |
|
Object Detection (SP)
|
100% |
86
6.82 IPS |
|
Object Detection (HP)
|
100% |
87
6.88 IPS |
|
Object Detection (Q)
|
83% |
110
8.92 IPS |
|
Face Detection (SP)
|
100% |
213
2.53 IPS |
|
Face Detection (HP)
|
100% |
213
2.53 IPS |
|
Face Detection (Q)
|
95% |
258
3.08 IPS |
|
Depth Estimation (SP)
|
100% |
244
1.88 IPS |
|
Depth Estimation (HP)
|
99% |
259
1.99 IPS |
|
Depth Estimation (Q)
|
64% |
252
2.30 IPS |
|
Style Transfer (SP)
|
89% |
642
0.83 IPS |
|
Style Transfer (HP)
|
89% |
663
0.86 IPS |
|
Style Transfer (Q)
|
98% |
712
0.92 IPS |
|
Image Super-Resolution (SP)
|
100% |
139
5.14 IPS |
|
Image Super-Resolution (HP)
|
100% |
142
5.24 IPS |
|
Image Super-Resolution (Q)
|
97% |
141
5.21 IPS |
|
Text Classification (SP)
|
100% |
93
124.5 IPS |
|
Text Classification (HP)
|
100% |
91
120.8 IPS |
|
Text Classification (Q)
|
88% |
101
136.5 IPS |
|
Machine Translation (SP)
|
100% |
174
2.99 IPS |
|
Machine Translation (HP)
|
100% |
173
2.98 IPS |
|
Machine Translation (Q)
|
50% |
71
2.51 IPS |