User | springkim |
Upload Date | April 18 2025 05:55 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARMv8 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI GRL-AL10 |
Model ID | HUAWEI GRL-AL10 |
Motherboard | GRL |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 72 architecture 8 variant 2 part 3331 revision 0 |
Base Frequency | 1.55 GHz |
Cluster 1 | 4 Cores @ 1.55 GHz |
Cluster 2 | 3 Cores @ 2.18 GHz |
Cluster 3 | 1 Core @ 2.30 GHz |
Memory Information | |
---|---|
Size | 15.24 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
204
37.9 IPS |
|
Image Classification (HP)
|
100% |
204
37.9 IPS |
|
Image Classification (Q)
|
99% |
486
90.7 IPS |
|
Image Segmentation (SP)
|
100% |
268
4.35 IPS |
|
Image Segmentation (HP)
|
100% |
270
4.38 IPS |
|
Image Segmentation (Q)
|
98% |
491
7.99 IPS |
|
Pose Estimation (SP)
|
100% |
357
0.42 IPS |
|
Pose Estimation (HP)
|
100% |
350
0.41 IPS |
|
Pose Estimation (Q)
|
98% |
1162
1.36 IPS |
|
Object Detection (SP)
|
100% |
193
15.3 IPS |
|
Object Detection (HP)
|
100% |
195
15.5 IPS |
|
Object Detection (Q)
|
87% |
530
42.5 IPS |
|
Face Detection (SP)
|
100% |
494
5.87 IPS |
|
Face Detection (HP)
|
100% |
500
5.94 IPS |
|
Face Detection (Q)
|
97% |
1045
12.5 IPS |
|
Depth Estimation (SP)
|
100% |
424
3.27 IPS |
|
Depth Estimation (HP)
|
99% |
433
3.33 IPS |
|
Depth Estimation (Q)
|
64% |
908
8.23 IPS |
|
Style Transfer (SP)
|
100% |
747
0.96 IPS |
|
Style Transfer (HP)
|
100% |
756
0.97 IPS |
|
Style Transfer (Q)
|
98% |
1773
2.29 IPS |
|
Image Super-Resolution (SP)
|
100% |
217
8.01 IPS |
|
Image Super-Resolution (HP)
|
100% |
218
8.04 IPS |
|
Image Super-Resolution (Q)
|
97% |
730
27.0 IPS |
|
Text Classification (SP)
|
100% |
316
421.6 IPS |
|
Text Classification (HP)
|
100% |
312
416.9 IPS |
|
Text Classification (Q)
|
91% |
483
648.8 IPS |
|
Machine Translation (SP)
|
100% |
475
8.18 IPS |
|
Machine Translation (HP)
|
100% |
468
8.07 IPS |
|
Machine Translation (Q)
|
57% |
364
8.89 IPS |