Upload Date | November 18 2024 08:39 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM Unisoc |
System Information | |
---|---|
Operating System | Android 12 |
Model | LAVA LAVA LZX411 |
Model ID | LAVA LAVA LZX411 |
Motherboard | LZX411 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Unisoc |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.61 GHz |
Cluster 1 | 8 Cores @ 1.61 GHz |
Memory Information | |
---|---|
Size | 2.71 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
185
34.3 IPS |
|
Image Classification (HP)
|
100% |
184
34.2 IPS |
|
Image Classification (Q)
|
100% |
488
90.8 IPS |
|
Image Segmentation (SP)
|
100% |
217
3.51 IPS |
|
Image Segmentation (HP)
|
100% |
216
3.50 IPS |
|
Image Segmentation (Q)
|
98% |
591
9.62 IPS |
|
Pose Estimation (SP)
|
100% |
811
0.95 IPS |
|
Pose Estimation (HP)
|
100% |
818
0.96 IPS |
|
Pose Estimation (Q)
|
84% |
1338
1.59 IPS |
|
Object Detection (SP)
|
100% |
198
15.7 IPS |
|
Object Detection (HP)
|
100% |
194
15.4 IPS |
|
Object Detection (Q)
|
83% |
448
36.2 IPS |
|
Face Detection (SP)
|
100% |
450
5.35 IPS |
|
Face Detection (HP)
|
100% |
444
5.27 IPS |
|
Face Detection (Q)
|
95% |
984
11.8 IPS |
|
Depth Estimation (SP)
|
100% |
464
3.58 IPS |
|
Depth Estimation (HP)
|
99% |
520
4.01 IPS |
|
Depth Estimation (Q)
|
64% |
921
8.44 IPS |
|
Style Transfer (SP)
|
89% |
1345
1.75 IPS |
|
Style Transfer (HP)
|
89% |
1386
1.80 IPS |
|
Style Transfer (Q)
|
98% |
2312
2.98 IPS |
|
Image Super-Resolution (SP)
|
100% |
288
10.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
289
10.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
598
22.2 IPS |
|
Text Classification (SP)
|
100% |
161
215.2 IPS |
|
Text Classification (HP)
|
100% |
166
221.9 IPS |
|
Text Classification (Q)
|
88% |
228
307.2 IPS |
|
Machine Translation (SP)
|
100% |
246
4.24 IPS |
|
Machine Translation (HP)
|
100% |
232
4.00 IPS |
|
Machine Translation (Q)
|
50% |
127
4.50 IPS |