Upload Date | December 03 2024 12:28 PM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI ADA-AL00U |
Model ID | HUAWEI ADA-AL00U |
Motherboard | ADL |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 6 Cores |
Identifier | ARM implementer 72 architecture 8 variant 2 part 3330 revision 2 |
Base Frequency | 1.53 GHz |
Cluster 1 | 3 Cores @ 1.53 GHz |
Cluster 2 | 2 Cores @ 2.15 GHz |
Cluster 3 | 1 Core @ 2.35 GHz |
Memory Information | |
---|---|
Size | 11.31 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
121
22.5 IPS |
|
Image Classification (HP)
|
100% |
65
12.1 IPS |
|
Image Classification (Q)
|
96% |
58
10.8 IPS |
|
Image Segmentation (SP)
|
100% |
201
3.26 IPS |
|
Image Segmentation (HP)
|
100% |
120
1.94 IPS |
|
Image Segmentation (Q)
|
98% |
120
1.96 IPS |
|
Pose Estimation (SP)
|
100% |
361
0.42 IPS |
|
Pose Estimation (HP)
|
100% |
154
0.18 IPS |
|
Pose Estimation (Q)
|
96% |
153
0.18 IPS |
|
Object Detection (SP)
|
100% |
86
6.79 IPS |
|
Object Detection (HP)
|
100% |
55
4.36 IPS |
|
Object Detection (Q)
|
85% |
53
4.26 IPS |
|
Face Detection (SP)
|
100% |
346
4.11 IPS |
|
Face Detection (HP)
|
100% |
244
2.90 IPS |
|
Face Detection (Q)
|
97% |
239
2.85 IPS |
|
Depth Estimation (SP)
|
100% |
430
3.31 IPS |
|
Depth Estimation (HP)
|
99% |
184
1.42 IPS |
|
Depth Estimation (Q)
|
63% |
148
1.40 IPS |
|
Style Transfer (SP)
|
100% |
1035
1.33 IPS |
|
Style Transfer (HP)
|
100% |
498
0.64 IPS |
|
Style Transfer (Q)
|
98% |
493
0.64 IPS |
|
Image Super-Resolution (SP)
|
100% |
162
5.96 IPS |
|
Image Super-Resolution (HP)
|
100% |
96
3.55 IPS |
|
Image Super-Resolution (Q)
|
97% |
91
3.36 IPS |
|
Text Classification (SP)
|
100% |
270
360.5 IPS |
|
Text Classification (HP)
|
100% |
268
357.9 IPS |
|
Text Classification (Q)
|
91% |
449
603.5 IPS |
|
Machine Translation (SP)
|
100% |
467
8.04 IPS |
|
Machine Translation (HP)
|
100% |
460
7.93 IPS |
|
Machine Translation (Q)
|
57% |
298
7.29 IPS |