Upload Date | July 02 2025 10:14 PM |
Views | 4 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | Intel Xeon Gold 6246R |
System Information | |
---|---|
Operating System | Microsoft Windows Server 2022 Datacenter (64-bit) |
Model | Dell Inc. PowerEdge R740 |
Motherboard | Dell Inc. 0WXD1Y |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Xeon Gold 6246R |
Topology | 2 Processors, 32 Cores, 64 Threads |
Identifier | GenuineIntel Family 6 Model 85 Stepping 7 |
Base Frequency | 3.39 GHz |
Cluster 1 | 32 Cores |
Memory Information | |
---|---|
Size | 768.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2463
458.0 IPS |
|
Image Classification (HP)
|
100% |
220
40.9 IPS |
|
Image Classification (Q)
|
99% |
2925
545.6 IPS |
|
Image Segmentation (SP)
|
100% |
935
15.2 IPS |
|
Image Segmentation (HP)
|
100% |
411
6.66 IPS |
|
Image Segmentation (Q)
|
98% |
5803
94.4 IPS |
|
Pose Estimation (SP)
|
100% |
16690
19.5 IPS |
|
Pose Estimation (HP)
|
100% |
7194
8.39 IPS |
|
Pose Estimation (Q)
|
94% |
41705
48.9 IPS |
|
Object Detection (SP)
|
100% |
2689
213.3 IPS |
|
Object Detection (HP)
|
100% |
310
24.6 IPS |
|
Object Detection (Q)
|
86% |
3841
308.7 IPS |
|
Face Detection (SP)
|
100% |
7052
83.8 IPS |
|
Face Detection (HP)
|
100% |
686
8.15 IPS |
|
Face Detection (Q)
|
97% |
6335
75.5 IPS |
|
Depth Estimation (SP)
|
100% |
9888
76.2 IPS |
|
Depth Estimation (HP)
|
99% |
1026
7.91 IPS |
|
Depth Estimation (Q)
|
78% |
10209
81.5 IPS |
|
Style Transfer (SP)
|
100% |
21294
27.4 IPS |
|
Style Transfer (HP)
|
100% |
17381
22.3 IPS |
|
Style Transfer (Q)
|
98% |
15484
20.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
1783
65.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
1424
52.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
2622
97.1 IPS |
|
Text Classification (SP)
|
100% |
425
567.5 IPS |
|
Text Classification (HP)
|
100% |
252
335.8 IPS |
|
Text Classification (Q)
|
97% |
184
246.2 IPS |
|
Machine Translation (SP)
|
100% |
703
12.1 IPS |
|
Machine Translation (HP)
|
100% |
346
5.97 IPS |
|
Machine Translation (Q)
|
65% |
1159
23.3 IPS |