Upload Date | August 23 2025 11:39 AM |
Views | 4 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD Ryzen AI 9 HX 370 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | GEEKOM A9 Max |
Motherboard | Standard A9 Max |
Power Plan | Ausbalanciert |
CPU Information | |
---|---|
Name | AMD Ryzen AI 9 HX 370 |
Topology | 1 Processor, 12 Cores, 24 Threads |
Identifier | AuthenticAMD Family 26 Model 36 Stepping 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3372
627.0 IPS |
|
Image Classification (HP)
|
100% |
813
151.1 IPS |
|
Image Classification (Q)
|
99% |
8022
1.50 KIPS |
|
Image Segmentation (SP)
|
100% |
1498
24.3 IPS |
|
Image Segmentation (HP)
|
100% |
1300
21.1 IPS |
|
Image Segmentation (Q)
|
98% |
11241
182.8 IPS |
|
Pose Estimation (SP)
|
100% |
8387
9.79 IPS |
|
Pose Estimation (HP)
|
100% |
6778
7.91 IPS |
|
Pose Estimation (Q)
|
94% |
28624
33.6 IPS |
|
Object Detection (SP)
|
100% |
3520
279.2 IPS |
|
Object Detection (HP)
|
100% |
1025
81.3 IPS |
|
Object Detection (Q)
|
86% |
8403
675.3 IPS |
|
Face Detection (SP)
|
100% |
5907
70.2 IPS |
|
Face Detection (HP)
|
100% |
2135
25.4 IPS |
|
Face Detection (Q)
|
97% |
11952
142.5 IPS |
|
Depth Estimation (SP)
|
100% |
9548
73.6 IPS |
|
Depth Estimation (HP)
|
99% |
2708
20.9 IPS |
|
Depth Estimation (Q)
|
78% |
17997
143.6 IPS |
|
Style Transfer (SP)
|
100% |
19096
24.5 IPS |
|
Style Transfer (HP)
|
100% |
16861
21.7 IPS |
|
Style Transfer (Q)
|
98% |
34839
44.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2804
103.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
2659
98.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
1565
58.0 IPS |
|
Text Classification (SP)
|
100% |
1733
2.31 KIPS |
|
Text Classification (HP)
|
100% |
870
1.16 KIPS |
|
Text Classification (Q)
|
97% |
1517
2.03 KIPS |
|
Machine Translation (SP)
|
100% |
2794
48.1 IPS |
|
Machine Translation (HP)
|
100% |
1146
19.7 IPS |
|
Machine Translation (Q)
|
65% |
3509
70.5 IPS |