Upload Date | April 23 2025 06:00 AM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | Intel Xeon Silver 4416+ |
System Information | |
---|---|
Operating System | Microsoft Windows Server 2022 Datacenter (64-bit) |
Model | HPE ProLiant DL380 Gen11 |
Motherboard | HPE ProLiant DL380 Gen11 |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Xeon Silver 4416+ |
Topology | 1 Processor, 20 Cores |
Identifier | GenuineIntel Family 6 Model 143 Stepping 8 |
Base Frequency | 2.00 GHz |
Cluster 1 | 20 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3855
716.8 IPS |
|
Image Classification (HP)
|
100% |
383
71.2 IPS |
|
Image Classification (Q)
|
99% |
5821
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1461
23.7 IPS |
|
Image Segmentation (HP)
|
100% |
642
10.4 IPS |
|
Image Segmentation (Q)
|
98% |
2401
39.0 IPS |
|
Pose Estimation (SP)
|
100% |
16487
19.2 IPS |
|
Pose Estimation (HP)
|
100% |
8268
9.65 IPS |
|
Pose Estimation (Q)
|
94% |
46284
54.3 IPS |
|
Object Detection (SP)
|
100% |
3560
282.4 IPS |
|
Object Detection (HP)
|
100% |
514
40.8 IPS |
|
Object Detection (Q)
|
86% |
5889
473.3 IPS |
|
Face Detection (SP)
|
100% |
8450
100.4 IPS |
|
Face Detection (HP)
|
100% |
1201
14.3 IPS |
|
Face Detection (Q)
|
97% |
7593
90.5 IPS |
|
Depth Estimation (SP)
|
100% |
11809
91.0 IPS |
|
Depth Estimation (HP)
|
99% |
1714
13.2 IPS |
|
Depth Estimation (Q)
|
78% |
18316
146.2 IPS |
|
Style Transfer (SP)
|
100% |
28128
36.2 IPS |
|
Style Transfer (HP)
|
100% |
17581
22.6 IPS |
|
Style Transfer (Q)
|
98% |
23761
30.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3497
129.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
2553
94.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
3520
130.3 IPS |
|
Text Classification (SP)
|
100% |
999
1.33 KIPS |
|
Text Classification (HP)
|
100% |
483
644.6 IPS |
|
Text Classification (Q)
|
97% |
351
470.7 IPS |
|
Machine Translation (SP)
|
100% |
1659
28.6 IPS |
|
Machine Translation (HP)
|
100% |
571
9.84 IPS |
|
Machine Translation (Q)
|
65% |
1872
37.6 IPS |