Upload Date | December 03 2024 11:49 PM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD Ryzen 9 8945HS |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | GEEKOM AE8 |
Motherboard | Default string AE8 |
CPU Information | |
---|---|
Name | AMD Ryzen 9 8945HS |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 25 Model 117 Stepping 2 |
Base Frequency | 4.00 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2954
549.3 IPS |
|
Image Classification (HP)
|
100% |
639
118.8 IPS |
|
Image Classification (Q)
|
99% |
8010
1.49 KIPS |
|
Image Segmentation (SP)
|
100% |
1228
19.9 IPS |
|
Image Segmentation (HP)
|
100% |
770
12.5 IPS |
|
Image Segmentation (Q)
|
98% |
3613
58.7 IPS |
|
Pose Estimation (SP)
|
100% |
6470
7.55 IPS |
|
Pose Estimation (HP)
|
100% |
5088
5.94 IPS |
|
Pose Estimation (Q)
|
94% |
24627
28.9 IPS |
|
Object Detection (SP)
|
100% |
3015
239.2 IPS |
|
Object Detection (HP)
|
100% |
715
56.7 IPS |
|
Object Detection (Q)
|
86% |
7566
608.0 IPS |
|
Face Detection (SP)
|
100% |
5758
68.4 IPS |
|
Face Detection (HP)
|
100% |
1695
20.1 IPS |
|
Face Detection (Q)
|
97% |
10789
128.6 IPS |
|
Depth Estimation (SP)
|
100% |
8807
67.9 IPS |
|
Depth Estimation (HP)
|
99% |
2536
19.5 IPS |
|
Depth Estimation (Q)
|
78% |
7670
61.2 IPS |
|
Style Transfer (SP)
|
100% |
14415
18.5 IPS |
|
Style Transfer (HP)
|
100% |
13559
17.4 IPS |
|
Style Transfer (Q)
|
98% |
25078
32.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
2453
90.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
2173
80.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
3422
126.7 IPS |
|
Text Classification (SP)
|
100% |
1835
2.45 KIPS |
|
Text Classification (HP)
|
100% |
838
1.12 KIPS |
|
Text Classification (Q)
|
97% |
1850
2.48 KIPS |
|
Machine Translation (SP)
|
100% |
2005
34.5 IPS |
|
Machine Translation (HP)
|
100% |
695
12.0 IPS |
|
Machine Translation (Q)
|
65% |
2198
44.2 IPS |