Upload Date | November 11 2024 02:28 AM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA Quadro RTX 5000 |
System Information | |
---|---|
Operating System | Microsoft Windows 10 Enterprise (64-bit) |
Model | HP HP Z6 G4 Workstation |
Motherboard | HP 81C6 |
CPU Information | |
---|---|
Name | Intel Xeon Gold 6242 |
Topology | 1 Processor, 16 Cores, 32 Threads |
Identifier | GenuineIntel Family 6 Model 85 Stepping 7 |
Base Frequency | 2.79 GHz |
Cluster 1 | 16 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5357
996.3 IPS |
|
Image Classification (HP)
|
100% |
7672
1.43 KIPS |
|
Image Classification (Q)
|
100% |
3941
732.9 IPS |
|
Image Segmentation (SP)
|
100% |
6809
110.4 IPS |
|
Image Segmentation (HP)
|
100% |
7917
128.3 IPS |
|
Image Segmentation (Q)
|
98% |
5515
89.7 IPS |
|
Pose Estimation (SP)
|
100% |
78928
92.1 IPS |
|
Pose Estimation (HP)
|
100% |
202962
236.8 IPS |
|
Pose Estimation (Q)
|
97% |
62024
72.6 IPS |
|
Object Detection (SP)
|
100% |
6185
490.6 IPS |
|
Object Detection (HP)
|
100% |
9666
766.7 IPS |
|
Object Detection (Q)
|
89% |
4551
364.3 IPS |
|
Face Detection (SP)
|
100% |
12973
154.1 IPS |
|
Face Detection (HP)
|
100% |
19181
227.9 IPS |
|
Face Detection (Q)
|
97% |
9649
115.0 IPS |
|
Depth Estimation (SP)
|
100% |
32778
252.5 IPS |
|
Depth Estimation (HP)
|
99% |
57032
439.4 IPS |
|
Depth Estimation (Q)
|
76% |
22208
178.8 IPS |
|
Style Transfer (SP)
|
100% |
134685
173.1 IPS |
|
Style Transfer (HP)
|
100% |
296918
381.7 IPS |
|
Style Transfer (Q)
|
98% |
103490
133.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
22714
838.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
32197
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
13398
496.1 IPS |
|
Text Classification (SP)
|
100% |
1326
1.77 KIPS |
|
Text Classification (HP)
|
99% |
1954
2.61 KIPS |
|
Text Classification (Q)
|
97% |
910
1.22 KIPS |
|
Machine Translation (SP)
|
100% |
2388
41.1 IPS |
|
Machine Translation (HP)
|
100% |
2372
40.9 IPS |
|
Machine Translation (Q)
|
60% |
1014
22.6 IPS |