Upload Date | April 15 2025 02:41 PM |
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 | 1.51 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% |
78
14.5 IPS |
|
Image Classification (HP)
|
100% |
78
14.5 IPS |
|
Image Classification (Q)
|
100% |
103
19.1 IPS |
|
Image Segmentation (SP)
|
100% |
100
1.62 IPS |
|
Image Segmentation (HP)
|
100% |
99
1.61 IPS |
|
Image Segmentation (Q)
|
98% |
125
2.04 IPS |
|
Pose Estimation (SP)
|
100% |
348
0.41 IPS |
|
Pose Estimation (HP)
|
100% |
317
0.37 IPS |
|
Pose Estimation (Q)
|
84% |
221
0.26 IPS |
|
Object Detection (SP)
|
100% |
89
7.07 IPS |
|
Object Detection (HP)
|
100% |
86
6.79 IPS |
|
Object Detection (Q)
|
83% |
103
8.32 IPS |
|
Face Detection (SP)
|
100% |
205
2.44 IPS |
|
Face Detection (HP)
|
100% |
202
2.40 IPS |
|
Face Detection (Q)
|
95% |
241
2.88 IPS |
|
Depth Estimation (SP)
|
100% |
182
1.40 IPS |
|
Depth Estimation (HP)
|
99% |
189
1.46 IPS |
|
Depth Estimation (Q)
|
64% |
235
2.16 IPS |
|
Style Transfer (SP)
|
89% |
618
0.80 IPS |
|
Style Transfer (HP)
|
89% |
616
0.80 IPS |
|
Style Transfer (Q)
|
98% |
661
0.85 IPS |
|
Image Super-Resolution (SP)
|
100% |
127
4.68 IPS |
|
Image Super-Resolution (HP)
|
100% |
146
5.39 IPS |
|
Image Super-Resolution (Q)
|
97% |
132
4.90 IPS |
|
Text Classification (SP)
|
100% |
74
98.9 IPS |
|
Text Classification (HP)
|
100% |
75
100.0 IPS |
|
Text Classification (Q)
|
88% |
96
129.1 IPS |
|
Machine Translation (SP)
|
100% |
173
2.98 IPS |
|
Machine Translation (HP)
|
100% |
171
2.95 IPS |
|
Machine Translation (Q)
|
50% |
72
2.55 IPS |