Upload Date | April 14 2025 04:41 AM |
Views | 1 |
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% |
81
15.1 IPS |
|
Image Classification (HP)
|
100% |
81
15.1 IPS |
|
Image Classification (Q)
|
100% |
111
20.6 IPS |
|
Image Segmentation (SP)
|
100% |
102
1.66 IPS |
|
Image Segmentation (HP)
|
100% |
103
1.68 IPS |
|
Image Segmentation (Q)
|
98% |
138
2.24 IPS |
|
Pose Estimation (SP)
|
100% |
378
0.44 IPS |
|
Pose Estimation (HP)
|
100% |
369
0.43 IPS |
|
Pose Estimation (Q)
|
84% |
244
0.29 IPS |
|
Object Detection (SP)
|
100% |
86
6.86 IPS |
|
Object Detection (HP)
|
100% |
87
6.86 IPS |
|
Object Detection (Q)
|
83% |
110
8.92 IPS |
|
Face Detection (SP)
|
100% |
212
2.52 IPS |
|
Face Detection (HP)
|
100% |
221
2.63 IPS |
|
Face Detection (Q)
|
95% |
259
3.09 IPS |
|
Depth Estimation (SP)
|
100% |
185
1.42 IPS |
|
Depth Estimation (HP)
|
99% |
187
1.44 IPS |
|
Depth Estimation (Q)
|
64% |
249
2.28 IPS |
|
Style Transfer (SP)
|
89% |
668
0.87 IPS |
|
Style Transfer (HP)
|
89% |
668
0.87 IPS |
|
Style Transfer (Q)
|
98% |
712
0.92 IPS |
|
Image Super-Resolution (SP)
|
100% |
152
5.61 IPS |
|
Image Super-Resolution (HP)
|
100% |
154
5.67 IPS |
|
Image Super-Resolution (Q)
|
97% |
141
5.23 IPS |
|
Text Classification (SP)
|
100% |
91
121.4 IPS |
|
Text Classification (HP)
|
100% |
90
120.2 IPS |
|
Text Classification (Q)
|
88% |
101
136.8 IPS |
|
Machine Translation (SP)
|
100% |
178
3.07 IPS |
|
Machine Translation (HP)
|
100% |
176
3.03 IPS |
|
Machine Translation (Q)
|
50% |
73
2.58 IPS |