Upload Date | April 08 2025 06:27 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% |
75
14.0 IPS |
|
Image Classification (HP)
|
100% |
76
14.1 IPS |
|
Image Classification (Q)
|
100% |
96
17.8 IPS |
|
Image Segmentation (SP)
|
100% |
92
1.49 IPS |
|
Image Segmentation (HP)
|
100% |
93
1.51 IPS |
|
Image Segmentation (Q)
|
98% |
135
2.19 IPS |
|
Pose Estimation (SP)
|
100% |
302
0.35 IPS |
|
Pose Estimation (HP)
|
100% |
320
0.37 IPS |
|
Pose Estimation (Q)
|
84% |
238
0.28 IPS |
|
Object Detection (SP)
|
100% |
79
6.28 IPS |
|
Object Detection (HP)
|
100% |
78
6.22 IPS |
|
Object Detection (Q)
|
83% |
108
8.72 IPS |
|
Face Detection (SP)
|
100% |
180
2.14 IPS |
|
Face Detection (HP)
|
100% |
182
2.16 IPS |
|
Face Detection (Q)
|
95% |
233
2.79 IPS |
|
Depth Estimation (SP)
|
100% |
176
1.35 IPS |
|
Depth Estimation (HP)
|
99% |
171
1.32 IPS |
|
Depth Estimation (Q)
|
64% |
241
2.20 IPS |
|
Style Transfer (SP)
|
89% |
589
0.76 IPS |
|
Style Transfer (HP)
|
89% |
591
0.77 IPS |
|
Style Transfer (Q)
|
98% |
663
0.85 IPS |
|
Image Super-Resolution (SP)
|
100% |
119
4.40 IPS |
|
Image Super-Resolution (HP)
|
100% |
119
4.39 IPS |
|
Image Super-Resolution (Q)
|
97% |
136
5.05 IPS |
|
Text Classification (SP)
|
100% |
87
115.5 IPS |
|
Text Classification (HP)
|
100% |
69
92.5 IPS |
|
Text Classification (Q)
|
88% |
100
134.8 IPS |
|
Machine Translation (SP)
|
100% |
147
2.53 IPS |
|
Machine Translation (HP)
|
100% |
147
2.54 IPS |
|
Machine Translation (Q)
|
50% |
71
2.51 IPS |