User | Uat4 |
Upload Date | July 04 2025 09:01 AM |
Views | 5 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD EPYC 9575F 64-Core Processor |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | OEM Rack Server |
Motherboard | OEM T2SEEP |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | AMD EPYC 9575F 64-Core Processor |
Topology | 1 Processor, 64 Cores |
Identifier | AuthenticAMD Family 26 Model 2 Stepping 1 |
Base Frequency | 3.30 GHz |
Cluster 1 | 64 Cores |
Memory Information | |
---|---|
Size | 384.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3641
677.1 IPS |
|
Image Classification (HP)
|
100% |
659
122.6 IPS |
|
Image Classification (Q)
|
99% |
4104
765.5 IPS |
|
Image Segmentation (SP)
|
100% |
1421
23.0 IPS |
|
Image Segmentation (HP)
|
100% |
1193
19.3 IPS |
|
Image Segmentation (Q)
|
98% |
15358
249.7 IPS |
|
Pose Estimation (SP)
|
100% |
49927
58.3 IPS |
|
Pose Estimation (HP)
|
100% |
15612
18.2 IPS |
|
Pose Estimation (Q)
|
94% |
95438
111.9 IPS |
|
Object Detection (SP)
|
100% |
3656
290.0 IPS |
|
Object Detection (HP)
|
100% |
881
69.9 IPS |
|
Object Detection (Q)
|
86% |
6203
498.6 IPS |
|
Face Detection (SP)
|
100% |
12539
149.0 IPS |
|
Face Detection (HP)
|
100% |
2042
24.3 IPS |
|
Face Detection (Q)
|
97% |
11356
135.4 IPS |
|
Depth Estimation (SP)
|
100% |
16046
123.6 IPS |
|
Depth Estimation (HP)
|
99% |
3628
28.0 IPS |
|
Depth Estimation (Q)
|
78% |
18164
144.9 IPS |
|
Style Transfer (SP)
|
100% |
49377
63.5 IPS |
|
Style Transfer (HP)
|
100% |
30069
38.7 IPS |
|
Style Transfer (Q)
|
98% |
81816
105.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3033
112.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
2502
92.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
1691
62.6 IPS |
|
Text Classification (SP)
|
100% |
762
1.02 KIPS |
|
Text Classification (HP)
|
100% |
519
692.2 IPS |
|
Text Classification (Q)
|
97% |
695
930.6 IPS |
|
Machine Translation (SP)
|
100% |
1183
20.4 IPS |
|
Machine Translation (HP)
|
100% |
994
17.1 IPS |
|
Machine Translation (Q)
|
65% |
2582
51.9 IPS |