User | 46fy45 |
Upload Date | October 03 2025 07:00 AM |
Views | 10 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | vendor |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI PLA-AL10 |
Model ID | HUAWEI PLA-AL10 |
Motherboard | PLA |
CPU Information | |
---|---|
Name | vendor |
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% |
223
41.5 IPS |
|
Image Classification (HP)
|
100% |
265
49.3 IPS |
|
Image Classification (Q)
|
100% |
247
45.9 IPS |
|
Image Segmentation (SP)
|
100% |
394
6.39 IPS |
|
Image Segmentation (HP)
|
100% |
485
7.87 IPS |
|
Image Segmentation (Q)
|
98% |
425
6.91 IPS |
|
Pose Estimation (SP)
|
100% |
1960
2.29 IPS |
|
Pose Estimation (HP)
|
99% |
2391
2.79 IPS |
|
Pose Estimation (Q)
|
95% |
2334
2.74 IPS |
|
Object Detection (SP)
|
100% |
185
14.7 IPS |
|
Object Detection (HP)
|
99% |
221
17.5 IPS |
|
Object Detection (Q)
|
85% |
177
14.2 IPS |
|
Face Detection (SP)
|
100% |
713
8.47 IPS |
|
Face Detection (HP)
|
100% |
728
8.65 IPS |
|
Face Detection (Q)
|
97% |
864
10.3 IPS |
|
Depth Estimation (SP)
|
100% |
979
7.54 IPS |
|
Depth Estimation (HP)
|
98% |
1077
8.33 IPS |
|
Depth Estimation (Q)
|
61% |
842
8.32 IPS |
|
Style Transfer (SP)
|
100% |
3015
3.88 IPS |
|
Style Transfer (HP)
|
100% |
4154
5.34 IPS |
|
Style Transfer (Q)
|
98% |
4064
5.24 IPS |
|
Image Super-Resolution (SP)
|
100% |
596
22.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
700
25.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
604
22.4 IPS |
|
Text Classification (SP)
|
35% |
9
80.5 IPS |
|
Text Classification (HP)
|
29% |
4
74.6 IPS |
|
Text Classification (Q)
|
29% |
5
83.4 IPS |
|
Machine Translation (SP)
|
100% |
102
1.75 IPS |
|
Machine Translation (HP)
|
100% |
67
1.15 IPS |
|
Machine Translation (Q)
|
48% |
32
1.22 IPS |