Upload Date | November 18 2024 08:50 AM |
Views | 3 |
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% |
174
32.4 IPS |
|
Image Classification (HP)
|
100% |
150
27.8 IPS |
|
Image Classification (Q)
|
100% |
420
78.0 IPS |
|
Image Segmentation (SP)
|
100% |
185
3.00 IPS |
|
Image Segmentation (HP)
|
100% |
192
3.12 IPS |
|
Image Segmentation (Q)
|
98% |
532
8.65 IPS |
|
Pose Estimation (SP)
|
100% |
696
0.81 IPS |
|
Pose Estimation (HP)
|
100% |
697
0.81 IPS |
|
Pose Estimation (Q)
|
84% |
905
1.07 IPS |
|
Object Detection (SP)
|
100% |
147
11.7 IPS |
|
Object Detection (HP)
|
100% |
152
12.1 IPS |
|
Object Detection (Q)
|
83% |
370
29.9 IPS |
|
Face Detection (SP)
|
100% |
420
4.99 IPS |
|
Face Detection (HP)
|
100% |
417
4.95 IPS |
|
Face Detection (Q)
|
95% |
1018
12.2 IPS |
|
Depth Estimation (SP)
|
100% |
536
4.13 IPS |
|
Depth Estimation (HP)
|
99% |
513
3.95 IPS |
|
Depth Estimation (Q)
|
64% |
883
8.09 IPS |
|
Style Transfer (SP)
|
89% |
1345
1.75 IPS |
|
Style Transfer (HP)
|
89% |
1351
1.75 IPS |
|
Style Transfer (Q)
|
98% |
2208
2.85 IPS |
|
Image Super-Resolution (SP)
|
100% |
292
10.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
288
10.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
558
20.7 IPS |
|
Text Classification (SP)
|
100% |
150
199.7 IPS |
|
Text Classification (HP)
|
100% |
158
211.4 IPS |
|
Text Classification (Q)
|
88% |
214
288.3 IPS |
|
Machine Translation (SP)
|
100% |
231
3.97 IPS |
|
Machine Translation (HP)
|
100% |
225
3.88 IPS |
|
Machine Translation (Q)
|
50% |
120
4.26 IPS |