| Upload Date | December 13 2024 10:07 AM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| 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% |
296
55.0 IPS |
|
|
Image Classification (HP)
|
100% |
178
33.1 IPS |
|
|
Image Classification (Q)
|
96% |
160
29.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
436
7.07 IPS |
|
|
Image Segmentation (HP)
|
100% |
265
4.30 IPS |
|
|
Image Segmentation (Q)
|
98% |
264
4.30 IPS |
|
|
Pose Estimation (SP)
|
100% |
520
0.61 IPS |
|
|
Pose Estimation (HP)
|
100% |
300
0.35 IPS |
|
|
Pose Estimation (Q)
|
96% |
297
0.35 IPS |
|
|
Object Detection (SP)
|
100% |
209
16.6 IPS |
|
|
Object Detection (HP)
|
100% |
118
9.34 IPS |
|
|
Object Detection (Q)
|
85% |
113
9.06 IPS |
|
|
Face Detection (SP)
|
100% |
761
9.05 IPS |
|
|
Face Detection (HP)
|
100% |
575
6.84 IPS |
|
|
Face Detection (Q)
|
97% |
522
6.22 IPS |
|
|
Depth Estimation (SP)
|
100% |
708
5.46 IPS |
|
|
Depth Estimation (HP)
|
99% |
389
3.01 IPS |
|
|
Depth Estimation (Q)
|
63% |
324
3.05 IPS |
|
|
Style Transfer (SP)
|
100% |
1538
1.98 IPS |
|
|
Style Transfer (HP)
|
100% |
944
1.21 IPS |
|
|
Style Transfer (Q)
|
98% |
941
1.21 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
293
10.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
193
7.13 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
189
7.00 IPS |
|
|
Text Classification (SP)
|
100% |
379
505.7 IPS |
|
|
Text Classification (HP)
|
100% |
380
506.7 IPS |
|
|
Text Classification (Q)
|
91% |
529
711.7 IPS |
|
|
Machine Translation (SP)
|
100% |
544
9.37 IPS |
|
|
Machine Translation (HP)
|
100% |
534
9.20 IPS |
|
|
Machine Translation (Q)
|
57% |
236
5.76 IPS |