Upload Date | August 06 2025 06:05 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI ADY-LX9 |
Model ID | HUAWEI ADY-LX9 |
Motherboard | ADY |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 72 architecture 8 variant 2 part 3330 revision 2 |
Base Frequency | 1.53 GHz |
Cluster 1 | 4 Cores @ 1.53 GHz |
Cluster 2 | 3 Cores @ 2.15 GHz |
Cluster 3 | 1 Core @ 2.49 GHz |
Memory Information | |
---|---|
Size | 11.30 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
467
86.9 IPS |
|
Image Classification (HP)
|
100% |
506
94.1 IPS |
|
Image Classification (Q)
|
100% |
1312
244.0 IPS |
|
Image Segmentation (SP)
|
100% |
589
9.55 IPS |
|
Image Segmentation (HP)
|
100% |
591
9.57 IPS |
|
Image Segmentation (Q)
|
98% |
1564
25.4 IPS |
|
Pose Estimation (SP)
|
100% |
2315
2.70 IPS |
|
Pose Estimation (HP)
|
100% |
2258
2.63 IPS |
|
Pose Estimation (Q)
|
84% |
2976
3.53 IPS |
|
Object Detection (SP)
|
100% |
443
35.2 IPS |
|
Object Detection (HP)
|
100% |
463
36.8 IPS |
|
Object Detection (Q)
|
83% |
1262
101.9 IPS |
|
Face Detection (SP)
|
100% |
1474
17.5 IPS |
|
Face Detection (HP)
|
100% |
1453
17.3 IPS |
|
Face Detection (Q)
|
95% |
3091
36.9 IPS |
|
Depth Estimation (SP)
|
100% |
2088
16.1 IPS |
|
Depth Estimation (HP)
|
99% |
2057
15.8 IPS |
|
Depth Estimation (Q)
|
64% |
2876
26.3 IPS |
|
Style Transfer (SP)
|
89% |
3837
4.98 IPS |
|
Style Transfer (HP)
|
89% |
3835
4.98 IPS |
|
Style Transfer (Q)
|
98% |
6957
8.97 IPS |
|
Image Super-Resolution (SP)
|
100% |
1206
44.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
1189
43.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1747
64.7 IPS |
|
Text Classification (SP)
|
100% |
564
752.8 IPS |
|
Text Classification (HP)
|
100% |
566
755.5 IPS |
|
Text Classification (Q)
|
88% |
897
1.21 KIPS |
|
Machine Translation (SP)
|
100% |
828
14.3 IPS |
|
Machine Translation (HP)
|
100% |
818
14.1 IPS |
|
Machine Translation (Q)
|
50% |
467
16.6 IPS |