Upload Date | April 15 2025 07:38 AM |
Views | 4 |
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% |
74
13.7 IPS |
|
Image Classification (HP)
|
100% |
73
13.6 IPS |
|
Image Classification (Q)
|
100% |
111
20.6 IPS |
|
Image Segmentation (SP)
|
100% |
91
1.48 IPS |
|
Image Segmentation (HP)
|
100% |
91
1.48 IPS |
|
Image Segmentation (Q)
|
98% |
137
2.23 IPS |
|
Pose Estimation (SP)
|
100% |
314
0.37 IPS |
|
Pose Estimation (HP)
|
100% |
311
0.36 IPS |
|
Pose Estimation (Q)
|
84% |
245
0.29 IPS |
|
Object Detection (SP)
|
100% |
77
6.12 IPS |
|
Object Detection (HP)
|
100% |
78
6.18 IPS |
|
Object Detection (Q)
|
83% |
113
9.10 IPS |
|
Face Detection (SP)
|
100% |
175
2.07 IPS |
|
Face Detection (HP)
|
100% |
176
2.09 IPS |
|
Face Detection (Q)
|
95% |
256
3.06 IPS |
|
Depth Estimation (SP)
|
100% |
173
1.33 IPS |
|
Depth Estimation (HP)
|
99% |
217
1.67 IPS |
|
Depth Estimation (Q)
|
64% |
255
2.34 IPS |
|
Style Transfer (SP)
|
89% |
600
0.78 IPS |
|
Style Transfer (HP)
|
89% |
598
0.78 IPS |
|
Style Transfer (Q)
|
98% |
667
0.86 IPS |
|
Image Super-Resolution (SP)
|
100% |
125
4.61 IPS |
|
Image Super-Resolution (HP)
|
100% |
122
4.49 IPS |
|
Image Super-Resolution (Q)
|
97% |
143
5.32 IPS |
|
Text Classification (SP)
|
100% |
86
115.0 IPS |
|
Text Classification (HP)
|
100% |
84
112.4 IPS |
|
Text Classification (Q)
|
88% |
109
146.7 IPS |
|
Machine Translation (SP)
|
100% |
149
2.57 IPS |
|
Machine Translation (HP)
|
100% |
152
2.62 IPS |
|
Machine Translation (Q)
|
50% |
66
2.35 IPS |