Upload Date | April 16 2025 01:38 AM |
Views | 5 |
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 | 1.51 GHz |
Cluster 1 | 4 Cores @ 1.51 GHz |
Cluster 2 | 2 Cores @ 1.75 GHz |
Cluster 3 | 2 Cores @ 1.94 GHz |
Memory Information | |
---|---|
Size | 5.62 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
81
15.1 IPS |
|
Image Classification (HP)
|
100% |
78
14.6 IPS |
|
Image Classification (Q)
|
100% |
103
19.1 IPS |
|
Image Segmentation (SP)
|
100% |
101
1.63 IPS |
|
Image Segmentation (HP)
|
100% |
101
1.63 IPS |
|
Image Segmentation (Q)
|
98% |
129
2.09 IPS |
|
Pose Estimation (SP)
|
100% |
360
0.42 IPS |
|
Pose Estimation (HP)
|
100% |
355
0.41 IPS |
|
Pose Estimation (Q)
|
84% |
226
0.27 IPS |
|
Object Detection (SP)
|
100% |
86
6.80 IPS |
|
Object Detection (HP)
|
100% |
85
6.78 IPS |
|
Object Detection (Q)
|
83% |
103
8.34 IPS |
|
Face Detection (SP)
|
100% |
198
2.35 IPS |
|
Face Detection (HP)
|
100% |
204
2.42 IPS |
|
Face Detection (Q)
|
95% |
236
2.82 IPS |
|
Depth Estimation (SP)
|
100% |
194
1.50 IPS |
|
Depth Estimation (HP)
|
99% |
209
1.61 IPS |
|
Depth Estimation (Q)
|
64% |
235
2.15 IPS |
|
Style Transfer (SP)
|
89% |
624
0.81 IPS |
|
Style Transfer (HP)
|
89% |
625
0.81 IPS |
|
Style Transfer (Q)
|
98% |
660
0.85 IPS |
|
Image Super-Resolution (SP)
|
100% |
151
5.59 IPS |
|
Image Super-Resolution (HP)
|
100% |
154
5.70 IPS |
|
Image Super-Resolution (Q)
|
97% |
132
4.89 IPS |
|
Text Classification (SP)
|
100% |
87
116.5 IPS |
|
Text Classification (HP)
|
100% |
87
116.3 IPS |
|
Text Classification (Q)
|
88% |
97
130.5 IPS |
|
Machine Translation (SP)
|
100% |
172
2.96 IPS |
|
Machine Translation (HP)
|
100% |
170
2.93 IPS |
|
Machine Translation (Q)
|
50% |
76
2.68 IPS |