Upload Date | March 28 2025 09:07 AM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Allwinner A537 K83 |
Model ID | Allwinner A537 K83 |
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 | 3.80 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
80
14.8 IPS |
|
Image Classification (HP)
|
100% |
80
14.8 IPS |
|
Image Classification (Q)
|
100% |
109
20.3 IPS |
|
Image Segmentation (SP)
|
100% |
100
1.63 IPS |
|
Image Segmentation (HP)
|
100% |
100
1.62 IPS |
|
Image Segmentation (Q)
|
98% |
145
2.35 IPS |
|
Pose Estimation (SP)
|
100% |
350
0.41 IPS |
|
Pose Estimation (HP)
|
100% |
342
0.40 IPS |
|
Pose Estimation (Q)
|
84% |
255
0.30 IPS |
|
Object Detection (SP)
|
100% |
78
6.16 IPS |
|
Object Detection (HP)
|
100% |
80
6.35 IPS |
|
Object Detection (Q)
|
83% |
113
9.09 IPS |
|
Face Detection (SP)
|
100% |
194
2.30 IPS |
|
Face Detection (HP)
|
100% |
197
2.34 IPS |
|
Face Detection (Q)
|
95% |
264
3.15 IPS |
|
Depth Estimation (SP)
|
100% |
185
1.42 IPS |
|
Depth Estimation (HP)
|
99% |
191
1.47 IPS |
|
Depth Estimation (Q)
|
64% |
258
2.36 IPS |
|
Style Transfer (SP)
|
89% |
655
0.85 IPS |
|
Style Transfer (HP)
|
89% |
650
0.84 IPS |
|
Style Transfer (Q)
|
98% |
679
0.87 IPS |
|
Image Super-Resolution (SP)
|
100% |
137
5.07 IPS |
|
Image Super-Resolution (HP)
|
100% |
139
5.12 IPS |
|
Image Super-Resolution (Q)
|
97% |
148
5.47 IPS |
|
Text Classification (SP)
|
100% |
76
102.0 IPS |
|
Text Classification (HP)
|
100% |
76
102.1 IPS |
|
Text Classification (Q)
|
88% |
82
110.8 IPS |
|
Machine Translation (SP)
|
100% |
120
2.07 IPS |
|
Machine Translation (HP)
|
100% |
120
2.07 IPS |
|
Machine Translation (Q)
|
50% |
48
1.70 IPS |