Upload Date | March 19 2025 04:25 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM SM7325 |
System Information | |
---|---|
Operating System | Android 12 |
Model | HUAWEI FOA-LX9 |
Model ID | HUAWEI FOA-LX9 |
Motherboard | FOA |
CPU Information | |
---|---|
Name | ARM SM7325 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.19 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
199
37.1 IPS |
|
Image Classification (HP)
|
100% |
271
50.3 IPS |
|
Image Classification (Q)
|
97% |
251
46.9 IPS |
|
Image Segmentation (SP)
|
100% |
321
5.20 IPS |
|
Image Segmentation (HP)
|
100% |
441
7.15 IPS |
|
Image Segmentation (Q)
|
98% |
418
6.80 IPS |
|
Pose Estimation (SP)
|
100% |
323
0.38 IPS |
|
Pose Estimation (HP)
|
100% |
226
0.26 IPS |
|
Pose Estimation (Q)
|
95% |
226
0.27 IPS |
|
Object Detection (SP)
|
100% |
153
12.2 IPS |
|
Object Detection (HP)
|
100% |
188
14.9 IPS |
|
Object Detection (Q)
|
89% |
181
14.4 IPS |
|
Face Detection (SP)
|
100% |
633
7.52 IPS |
|
Face Detection (HP)
|
100% |
852
10.1 IPS |
|
Face Detection (Q)
|
97% |
791
9.43 IPS |
|
Depth Estimation (SP)
|
100% |
492
3.79 IPS |
|
Depth Estimation (HP)
|
99% |
743
5.74 IPS |
|
Depth Estimation (Q)
|
62% |
604
5.71 IPS |
|
Style Transfer (SP)
|
100% |
975
1.25 IPS |
|
Style Transfer (HP)
|
100% |
1641
2.11 IPS |
|
Style Transfer (Q)
|
98% |
1647
2.12 IPS |
|
Image Super-Resolution (SP)
|
100% |
209
7.72 IPS |
|
Image Super-Resolution (HP)
|
100% |
378
14.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
361
13.4 IPS |
|
Text Classification (SP)
|
100% |
180
240.7 IPS |
|
Text Classification (HP)
|
100% |
180
240.6 IPS |
|
Text Classification (Q)
|
91% |
347
465.8 IPS |
|
Machine Translation (SP)
|
100% |
300
5.17 IPS |
|
Machine Translation (HP)
|
100% |
301
5.19 IPS |
|
Machine Translation (Q)
|
57% |
265
6.48 IPS |