Upload Date | April 15 2025 07:16 AM |
Views | 3 |
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% |
69
12.8 IPS |
|
Image Classification (HP)
|
100% |
75
14.0 IPS |
|
Image Classification (Q)
|
100% |
99
18.5 IPS |
|
Image Segmentation (SP)
|
100% |
103
1.68 IPS |
|
Image Segmentation (HP)
|
100% |
105
1.70 IPS |
|
Image Segmentation (Q)
|
98% |
143
2.32 IPS |
|
Pose Estimation (SP)
|
100% |
352
0.41 IPS |
|
Pose Estimation (HP)
|
100% |
352
0.41 IPS |
|
Pose Estimation (Q)
|
84% |
243
0.29 IPS |
|
Object Detection (SP)
|
100% |
89
7.06 IPS |
|
Object Detection (HP)
|
100% |
88
6.95 IPS |
|
Object Detection (Q)
|
83% |
110
8.86 IPS |
|
Face Detection (SP)
|
100% |
214
2.55 IPS |
|
Face Detection (HP)
|
100% |
207
2.46 IPS |
|
Face Detection (Q)
|
95% |
256
3.06 IPS |
|
Depth Estimation (SP)
|
100% |
196
1.51 IPS |
|
Depth Estimation (HP)
|
99% |
191
1.47 IPS |
|
Depth Estimation (Q)
|
64% |
252
2.31 IPS |
|
Style Transfer (SP)
|
89% |
661
0.86 IPS |
|
Style Transfer (HP)
|
89% |
650
0.84 IPS |
|
Style Transfer (Q)
|
98% |
712
0.92 IPS |
|
Image Super-Resolution (SP)
|
100% |
130
4.80 IPS |
|
Image Super-Resolution (HP)
|
100% |
151
5.57 IPS |
|
Image Super-Resolution (Q)
|
97% |
140
5.20 IPS |
|
Text Classification (SP)
|
100% |
90
120.4 IPS |
|
Text Classification (HP)
|
100% |
89
119.4 IPS |
|
Text Classification (Q)
|
88% |
102
137.5 IPS |
|
Machine Translation (SP)
|
100% |
177
3.06 IPS |
|
Machine Translation (HP)
|
100% |
157
2.71 IPS |
|
Machine Translation (Q)
|
50% |
74
2.64 IPS |