User | RunBoris |
Upload Date | July 26 2025 01:13 AM |
Views | 8 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA Quadro P1000 |
System Information | |
---|---|
Operating System | Microsoft Windows Server 2025 Standard Evaluation (64-bit) |
Model | Unknown |
Motherboard | 0TKD84 |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Xeon Gold 6130 |
Topology | 2 Processors, 32 Cores, 64 Threads |
Identifier | GenuineIntel Family 6 Model 85 Stepping 4 |
Base Frequency | 2.10 GHz |
Cluster 1 | 32 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
582
108.2 IPS |
|
Image Classification (HP)
|
100% |
1075
199.9 IPS |
|
Image Classification (Q)
|
99% |
543
101.3 IPS |
|
Image Segmentation (SP)
|
100% |
1659
26.9 IPS |
|
Image Segmentation (HP)
|
100% |
1488
24.1 IPS |
|
Image Segmentation (Q)
|
98% |
1393
22.7 IPS |
|
Pose Estimation (SP)
|
100% |
15115
17.6 IPS |
|
Pose Estimation (HP)
|
100% |
9016
10.5 IPS |
|
Pose Estimation (Q)
|
96% |
12492
14.6 IPS |
|
Object Detection (SP)
|
100% |
827
65.6 IPS |
|
Object Detection (HP)
|
100% |
1355
107.5 IPS |
|
Object Detection (Q)
|
83% |
753
60.8 IPS |
|
Face Detection (SP)
|
100% |
1638
19.5 IPS |
|
Face Detection (HP)
|
100% |
2459
29.2 IPS |
|
Face Detection (Q)
|
97% |
1466
17.5 IPS |
|
Depth Estimation (SP)
|
100% |
5494
42.3 IPS |
|
Depth Estimation (HP)
|
99% |
5187
40.1 IPS |
|
Depth Estimation (Q)
|
78% |
4463
35.6 IPS |
|
Style Transfer (SP)
|
100% |
26871
34.5 IPS |
|
Style Transfer (HP)
|
100% |
16508
21.2 IPS |
|
Style Transfer (Q)
|
98% |
21107
27.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4995
184.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
4053
149.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
3412
126.4 IPS |
|
Text Classification (SP)
|
100% |
812
1.08 KIPS |
|
Text Classification (HP)
|
100% |
918
1.22 KIPS |
|
Text Classification (Q)
|
97% |
478
640.8 IPS |
|
Machine Translation (SP)
|
100% |
1425
24.5 IPS |
|
Machine Translation (HP)
|
96% |
1483
25.7 IPS |
|
Machine Translation (Q)
|
70% |
701
13.1 IPS |