Upload Date | April 02 2025 07:27 AM |
Views | 2 |
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 | 1.42 GHz |
Cluster 1 | 4 Cores @ 1.42 GHz |
Cluster 2 | 2 Cores @ 1.51 GHz |
Cluster 3 | 2 Cores @ 1.80 GHz |
Memory Information | |
---|---|
Size | 5.62 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
101
18.7 IPS |
|
Image Classification (HP)
|
100% |
104
19.3 IPS |
|
Image Classification (Q)
|
100% |
181
33.7 IPS |
|
Image Segmentation (SP)
|
100% |
128
2.08 IPS |
|
Image Segmentation (HP)
|
100% |
122
1.98 IPS |
|
Image Segmentation (Q)
|
98% |
214
3.49 IPS |
|
Pose Estimation (SP)
|
100% |
359
0.42 IPS |
|
Pose Estimation (HP)
|
100% |
331
0.39 IPS |
|
Pose Estimation (Q)
|
84% |
255
0.30 IPS |
|
Object Detection (SP)
|
100% |
79
6.27 IPS |
|
Object Detection (HP)
|
100% |
76
6.04 IPS |
|
Object Detection (Q)
|
83% |
125
10.1 IPS |
|
Face Detection (SP)
|
100% |
204
2.43 IPS |
|
Face Detection (HP)
|
100% |
201
2.39 IPS |
|
Face Detection (Q)
|
95% |
306
3.66 IPS |
|
Depth Estimation (SP)
|
100% |
192
1.48 IPS |
|
Depth Estimation (HP)
|
99% |
197
1.52 IPS |
|
Depth Estimation (Q)
|
64% |
259
2.38 IPS |
|
Style Transfer (SP)
|
89% |
638
0.83 IPS |
|
Style Transfer (HP)
|
89% |
658
0.85 IPS |
|
Style Transfer (Q)
|
98% |
693
0.89 IPS |
|
Image Super-Resolution (SP)
|
100% |
141
5.20 IPS |
|
Image Super-Resolution (HP)
|
100% |
143
5.30 IPS |
|
Image Super-Resolution (Q)
|
97% |
163
6.04 IPS |
|
Text Classification (SP)
|
100% |
100
133.0 IPS |
|
Text Classification (HP)
|
100% |
102
136.1 IPS |
|
Text Classification (Q)
|
88% |
102
138.1 IPS |
|
Machine Translation (SP)
|
100% |
130
2.24 IPS |
|
Machine Translation (HP)
|
100% |
128
2.20 IPS |
|
Machine Translation (Q)
|
50% |
56
1.98 IPS |