Upload Date | March 28 2025 10:36 AM |
Views | 7 |
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% |
70
13.0 IPS |
|
Image Classification (HP)
|
100% |
77
14.3 IPS |
|
Image Classification (Q)
|
100% |
108
20.0 IPS |
|
Image Segmentation (SP)
|
100% |
96
1.56 IPS |
|
Image Segmentation (HP)
|
100% |
98
1.58 IPS |
|
Image Segmentation (Q)
|
98% |
145
2.35 IPS |
|
Pose Estimation (SP)
|
100% |
339
0.40 IPS |
|
Pose Estimation (HP)
|
100% |
349
0.41 IPS |
|
Pose Estimation (Q)
|
84% |
254
0.30 IPS |
|
Object Detection (SP)
|
100% |
81
6.40 IPS |
|
Object Detection (HP)
|
100% |
81
6.39 IPS |
|
Object Detection (Q)
|
83% |
112
9.02 IPS |
|
Face Detection (SP)
|
100% |
189
2.24 IPS |
|
Face Detection (HP)
|
100% |
197
2.34 IPS |
|
Face Detection (Q)
|
95% |
247
2.95 IPS |
|
Depth Estimation (SP)
|
100% |
191
1.48 IPS |
|
Depth Estimation (HP)
|
99% |
179
1.38 IPS |
|
Depth Estimation (Q)
|
64% |
256
2.34 IPS |
|
Style Transfer (SP)
|
89% |
650
0.84 IPS |
|
Style Transfer (HP)
|
89% |
648
0.84 IPS |
|
Style Transfer (Q)
|
98% |
673
0.87 IPS |
|
Image Super-Resolution (SP)
|
100% |
139
5.12 IPS |
|
Image Super-Resolution (HP)
|
100% |
139
5.14 IPS |
|
Image Super-Resolution (Q)
|
97% |
147
5.45 IPS |
|
Text Classification (SP)
|
100% |
76
101.5 IPS |
|
Text Classification (HP)
|
100% |
76
101.5 IPS |
|
Text Classification (Q)
|
88% |
82
110.1 IPS |
|
Machine Translation (SP)
|
100% |
119
2.05 IPS |
|
Machine Translation (HP)
|
100% |
118
2.02 IPS |
|
Machine Translation (Q)
|
50% |
47
1.65 IPS |