Upload Date | March 28 2025 07:00 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% |
92
17.2 IPS |
|
Image Classification (HP)
|
100% |
94
17.5 IPS |
|
Image Classification (Q)
|
100% |
158
29.3 IPS |
|
Image Segmentation (SP)
|
100% |
95
1.55 IPS |
|
Image Segmentation (HP)
|
100% |
119
1.93 IPS |
|
Image Segmentation (Q)
|
98% |
212
3.45 IPS |
|
Pose Estimation (SP)
|
100% |
272
0.32 IPS |
|
Pose Estimation (HP)
|
100% |
263
0.31 IPS |
|
Pose Estimation (Q)
|
84% |
230
0.27 IPS |
|
Object Detection (SP)
|
100% |
50
3.94 IPS |
|
Object Detection (HP)
|
100% |
51
4.01 IPS |
|
Object Detection (Q)
|
83% |
66
5.36 IPS |
|
Face Detection (SP)
|
100% |
132
1.57 IPS |
|
Face Detection (HP)
|
100% |
213
2.53 IPS |
|
Face Detection (Q)
|
95% |
361
4.31 IPS |
|
Depth Estimation (SP)
|
100% |
215
1.65 IPS |
|
Depth Estimation (HP)
|
99% |
181
1.39 IPS |
|
Depth Estimation (Q)
|
64% |
235
2.15 IPS |
|
Style Transfer (SP)
|
89% |
516
0.67 IPS |
|
Style Transfer (HP)
|
89% |
528
0.68 IPS |
|
Style Transfer (Q)
|
98% |
619
0.80 IPS |
|
Image Super-Resolution (SP)
|
100% |
110
4.07 IPS |
|
Image Super-Resolution (HP)
|
100% |
124
4.59 IPS |
|
Image Super-Resolution (Q)
|
97% |
146
5.41 IPS |
|
Text Classification (SP)
|
100% |
62
82.5 IPS |
|
Text Classification (HP)
|
100% |
80
107.0 IPS |
|
Text Classification (Q)
|
88% |
92
124.0 IPS |
|
Machine Translation (SP)
|
100% |
104
1.79 IPS |
|
Machine Translation (HP)
|
100% |
109
1.88 IPS |
|
Machine Translation (Q)
|
50% |
49
1.76 IPS |