Upload Date | August 16 2024 08:54 PM |
Views | 5 |
AI Information | |
---|---|
Framework | ONNX |
Backend | QNN |
Device | Snapdragon (TM) 8cx Gen 3 @ 3.0 GHz |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | LENOVO 21BX001LGE |
Motherboard | LENOVO 21BX001LGE |
Power Plan | Ausbalanciert |
CPU Information | |
---|---|
Name | Snapdragon (TM) 8cx Gen 3 @ 3.0 GHz |
Topology | 1 Processor, 8 Cores |
Identifier | ARMv8 (64-bit) Family 8 Model D4B Revision 0 |
Base Frequency | 3.00 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
387
72.0 IPS |
|
Image Classification (HP)
|
100% |
102
19.0 IPS |
|
Image Classification (Q)
|
100% |
191
35.5 IPS |
|
Image Segmentation (SP)
|
100% |
514
8.33 IPS |
|
Image Segmentation (HP)
|
100% |
162
2.63 IPS |
|
Image Segmentation (Q)
|
98% |
229
3.73 IPS |
|
Pose Estimation (SP)
|
100% |
1981
2.31 IPS |
|
Pose Estimation (HP)
|
100% |
614
0.72 IPS |
|
Pose Estimation (Q)
|
95% |
483
0.57 IPS |
|
Object Detection (SP)
|
100% |
488
38.7 IPS |
|
Object Detection (HP)
|
99% |
125
9.93 IPS |
|
Object Detection (Q)
|
89% |
162
13.0 IPS |
|
Face Detection (SP)
|
100% |
1106
13.1 IPS |
|
Face Detection (HP)
|
100% |
190
2.26 IPS |
|
Face Detection (Q)
|
97% |
426
5.08 IPS |
|
Depth Estimation (SP)
|
100% |
1389
10.7 IPS |
|
Depth Estimation (HP)
|
99% |
462
3.57 IPS |
|
Depth Estimation (Q)
|
73% |
473
3.87 IPS |
|
Style Transfer (SP)
|
100% |
4928
6.34 IPS |
|
Style Transfer (HP)
|
100% |
1711
2.20 IPS |
|
Style Transfer (Q)
|
98% |
1136
1.46 IPS |
|
Image Super-Resolution (SP)
|
100% |
1012
37.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
357
13.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
273
10.1 IPS |
|
Text Classification (SP)
|
100% |
776
1.04 KIPS |
|
Text Classification (HP)
|
100% |
217
290.2 IPS |
|
Text Classification (Q)
|
97% |
199
265.9 IPS |
|
Machine Translation (SP)
|
100% |
914
15.7 IPS |
|
Machine Translation (HP)
|
99% |
400
6.92 IPS |
|
Machine Translation (Q)
|
59% |
239
5.52 IPS |