| Upload Date | November 20 2026 09:46 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Qualcomm SM8975 |
| System Information | |
|---|---|
| Operating System | Android 17 |
| Model | HONOR WKL-N59 |
| Model ID | HONOR WKL-N59 |
| Motherboard | WKL |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | Qualcomm SM8975 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 0 part 3 revision 1 |
| Base Frequency | 3.74 GHz |
| Cluster 1 | 3 Cores @ 3.74 GHz |
| Cluster 2 | 3 Cores @ 4.03 GHz |
| Cluster 3 | 2 Cores @ 5.01 GHz |
| Memory Information | |
|---|---|
| Size | 10.90 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1380
256.6 IPS |
|
|
Image Classification (HP)
|
100% |
334
62.1 IPS |
|
|
Image Classification (Q)
|
99% |
155
28.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
676
11.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
585
9.48 IPS |
|
|
Image Segmentation (Q)
|
98% |
775
12.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
2123
2.48 IPS |
|
|
Pose Estimation (HP)
|
92% |
2949
3.46 IPS |
|
|
Pose Estimation (Q)
|
96% |
3883
4.55 IPS |
|
|
Object Detection (SP)
|
98% |
219
17.5 IPS |
|
|
Object Detection (HP)
|
97% |
193
15.3 IPS |
|
|
Object Detection (Q)
|
85% |
158
12.7 IPS |
|
|
Face Detection (SP)
|
100% |
650
7.72 IPS |
|
|
Face Detection (HP)
|
100% |
542
6.44 IPS |
|
|
Face Detection (Q)
|
97% |
649
7.74 IPS |
|
|
Depth Estimation (SP)
|
99% |
684
5.29 IPS |
|
|
Depth Estimation (HP)
|
98% |
691
5.34 IPS |
|
|
Depth Estimation (Q)
|
64% |
732
6.72 IPS |
|
|
Style Transfer (SP)
|
89% |
4746
6.16 IPS |
|
|
Style Transfer (HP)
|
88% |
5386
6.99 IPS |
|
|
Style Transfer (Q)
|
98% |
7612
9.82 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
239
8.84 IPS |
|
|
Image Super-Resolution (HP)
|
92% |
236
8.79 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
332
12.3 IPS |
|
|
Text Classification (SP)
|
100% |
22
29.8 IPS |
|
|
Text Classification (HP)
|
100% |
23
31.4 IPS |
|
|
Text Classification (Q)
|
93% |
23
30.4 IPS |
|
|
Machine Translation (SP)
|
100% |
34
0.58 IPS |
|
|
Machine Translation (HP)
|
96% |
33
0.57 IPS |
|
|
Machine Translation (Q)
|
55% |
925
24.8 IPS |