| Upload Date | December 13 2024 09:39 AM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | HUAWEI PLA-AL10 |
| Model ID | HUAWEI PLA-AL10 |
| Motherboard | PLA |
| CPU Information | |
|---|---|
| Name | ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 72 architecture 8 variant 2 part 3333 revision 1 |
| Base Frequency | 1.60 GHz |
| Cluster 1 | 4 Cores @ 1.60 GHz |
| Cluster 2 | 3 Cores @ 2.15 GHz |
| Cluster 3 | 1 Core @ 2.50 GHz |
| Memory Information | |
|---|---|
| Size | 15.28 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
241
44.9 IPS |
|
|
Image Classification (HP)
|
100% |
243
45.1 IPS |
|
|
Image Classification (Q)
|
99% |
572
106.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
330
5.35 IPS |
|
|
Image Segmentation (HP)
|
100% |
312
5.06 IPS |
|
|
Image Segmentation (Q)
|
98% |
309
5.03 IPS |
|
|
Pose Estimation (SP)
|
100% |
192
0.22 IPS |
|
|
Pose Estimation (HP)
|
100% |
192
0.22 IPS |
|
|
Pose Estimation (Q)
|
98% |
728
0.85 IPS |
|
|
Object Detection (SP)
|
100% |
110
8.73 IPS |
|
|
Object Detection (HP)
|
100% |
110
8.75 IPS |
|
|
Object Detection (Q)
|
87% |
312
25.0 IPS |
|
|
Face Detection (SP)
|
100% |
309
3.67 IPS |
|
|
Face Detection (HP)
|
100% |
312
3.71 IPS |
|
|
Face Detection (Q)
|
97% |
674
8.03 IPS |
|
|
Depth Estimation (SP)
|
100% |
249
1.92 IPS |
|
|
Depth Estimation (HP)
|
99% |
250
1.93 IPS |
|
|
Depth Estimation (Q)
|
64% |
613
5.57 IPS |
|
|
Style Transfer (SP)
|
100% |
445
0.57 IPS |
|
|
Style Transfer (HP)
|
100% |
446
0.57 IPS |
|
|
Style Transfer (Q)
|
98% |
1240
1.60 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
124
4.59 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
124
4.58 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
434
16.1 IPS |
|
|
Text Classification (SP)
|
100% |
162
216.8 IPS |
|
|
Text Classification (HP)
|
100% |
163
217.4 IPS |
|
|
Text Classification (Q)
|
91% |
283
380.5 IPS |
|
|
Machine Translation (SP)
|
100% |
260
4.47 IPS |
|
|
Machine Translation (HP)
|
100% |
273
4.70 IPS |
|
|
Machine Translation (Q)
|
57% |
237
5.78 IPS |