Upload Date | September 09 2025 02:20 AM |
Views | 5 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | Intel Xeon W-2140B |
System Information | |
---|---|
Operating System | Microsoft Windows Server 2022 Standard (64-bit) |
Model | Dell Inc. Precision 5820 Tower |
Motherboard | Dell Inc. 0X8DXD |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Xeon W-2140B |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | GenuineIntel Family 6 Model 85 Stepping 4 |
Base Frequency | 3.19 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3296
612.9 IPS |
|
Image Classification (HP)
|
100% |
312
58.0 IPS |
|
Image Classification (Q)
|
96% |
3796
708.8 IPS |
|
Image Segmentation (SP)
|
100% |
992
16.1 IPS |
|
Image Segmentation (HP)
|
100% |
515
8.34 IPS |
|
Image Segmentation (Q)
|
97% |
3269
53.2 IPS |
|
Pose Estimation (SP)
|
100% |
7757
9.05 IPS |
|
Pose Estimation (HP)
|
100% |
5701
6.65 IPS |
|
Pose Estimation (Q)
|
86% |
12872
15.2 IPS |
|
Object Detection (SP)
|
100% |
2407
191.0 IPS |
|
Object Detection (HP)
|
100% |
441
35.0 IPS |
|
Object Detection (Q)
|
58% |
2310
252.4 IPS |
|
Face Detection (SP)
|
100% |
6211
73.8 IPS |
|
Face Detection (HP)
|
100% |
937
11.1 IPS |
|
Face Detection (Q)
|
96% |
6410
76.5 IPS |
|
Depth Estimation (SP)
|
100% |
9093
70.1 IPS |
|
Depth Estimation (HP)
|
99% |
1283
9.89 IPS |
|
Depth Estimation (Q)
|
78% |
8250
65.8 IPS |
|
Style Transfer (SP)
|
100% |
15329
19.7 IPS |
|
Style Transfer (HP)
|
100% |
10528
13.5 IPS |
|
Style Transfer (Q)
|
87% |
15220
19.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
2040
75.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
1841
68.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
3456
128.0 IPS |
|
Text Classification (SP)
|
100% |
1043
1.39 KIPS |
|
Text Classification (HP)
|
100% |
569
759.3 IPS |
|
Text Classification (Q)
|
97% |
268
358.6 IPS |
|
Machine Translation (SP)
|
100% |
1396
24.0 IPS |
|
Machine Translation (HP)
|
100% |
476
8.21 IPS |
|
Machine Translation (Q)
|
68% |
1392
26.9 IPS |