| Upload Date | November 13 2025 11:48 AM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | HUAWEI HBP-LX9 |
| Model ID | HUAWEI HBP-LX9 |
| Motherboard | HBP |
| 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 | 15.23 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
219
40.7 IPS |
|
|
Image Classification (HP)
|
100% |
222
41.2 IPS |
|
|
Image Classification (Q)
|
99% |
525
97.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
291
4.72 IPS |
|
|
Image Segmentation (HP)
|
100% |
294
4.76 IPS |
|
|
Image Segmentation (Q)
|
98% |
536
8.71 IPS |
|
|
Pose Estimation (SP)
|
100% |
389
0.45 IPS |
|
|
Pose Estimation (HP)
|
100% |
381
0.44 IPS |
|
|
Pose Estimation (Q)
|
98% |
1243
1.46 IPS |
|
|
Object Detection (SP)
|
100% |
207
16.4 IPS |
|
|
Object Detection (HP)
|
100% |
206
16.3 IPS |
|
|
Object Detection (Q)
|
87% |
541
43.4 IPS |
|
|
Face Detection (SP)
|
100% |
536
6.37 IPS |
|
|
Face Detection (HP)
|
100% |
541
6.42 IPS |
|
|
Face Detection (Q)
|
97% |
1090
13.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
460
3.54 IPS |
|
|
Depth Estimation (HP)
|
99% |
460
3.54 IPS |
|
|
Depth Estimation (Q)
|
64% |
975
8.84 IPS |
|
|
Style Transfer (SP)
|
100% |
810
1.04 IPS |
|
|
Style Transfer (HP)
|
100% |
802
1.03 IPS |
|
|
Style Transfer (Q)
|
98% |
1855
2.39 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
229
8.46 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
229
8.45 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
743
27.5 IPS |
|
|
Text Classification (SP)
|
100% |
315
420.4 IPS |
|
|
Text Classification (HP)
|
100% |
318
425.0 IPS |
|
|
Text Classification (Q)
|
91% |
498
668.8 IPS |
|
|
Machine Translation (SP)
|
100% |
496
8.54 IPS |
|
|
Machine Translation (HP)
|
100% |
489
8.42 IPS |
|
|
Machine Translation (Q)
|
57% |
383
9.37 IPS |