Upload Date | June 15 2025 05:39 PM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 2060 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | INTEL |
Motherboard | INTEL E5-A99 |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Xeon E5-2697 v4 |
Topology | 1 Processor, 18 Cores, 36 Threads |
Identifier | GenuineIntel Family 6 Model 79 Stepping 1 |
Base Frequency | 2.30 GHz |
Cluster 1 | 18 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4195
780.2 IPS |
|
Image Classification (HP)
|
100% |
6827
1.27 KIPS |
|
Image Classification (Q)
|
99% |
3360
626.7 IPS |
|
Image Segmentation (SP)
|
100% |
6226
100.9 IPS |
|
Image Segmentation (HP)
|
100% |
8207
133.0 IPS |
|
Image Segmentation (Q)
|
98% |
5250
85.4 IPS |
|
Pose Estimation (SP)
|
100% |
56189
65.6 IPS |
|
Pose Estimation (HP)
|
100% |
175397
204.7 IPS |
|
Pose Estimation (Q)
|
96% |
46317
54.3 IPS |
|
Object Detection (SP)
|
100% |
5183
411.1 IPS |
|
Object Detection (HP)
|
100% |
8031
637.0 IPS |
|
Object Detection (Q)
|
84% |
4136
333.6 IPS |
|
Face Detection (SP)
|
100% |
11600
137.8 IPS |
|
Face Detection (HP)
|
100% |
16748
199.0 IPS |
|
Face Detection (Q)
|
97% |
9572
114.1 IPS |
|
Depth Estimation (SP)
|
100% |
28616
220.5 IPS |
|
Depth Estimation (HP)
|
99% |
51449
396.4 IPS |
|
Depth Estimation (Q)
|
77% |
20091
160.8 IPS |
|
Style Transfer (SP)
|
100% |
100638
129.4 IPS |
|
Style Transfer (HP)
|
100% |
226437
291.1 IPS |
|
Style Transfer (Q)
|
98% |
80154
103.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
15283
564.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
23527
868.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
9864
365.2 IPS |
|
Text Classification (SP)
|
100% |
1563
2.09 KIPS |
|
Text Classification (HP)
|
99% |
2187
2.92 KIPS |
|
Text Classification (Q)
|
97% |
859
1.15 KIPS |
|
Machine Translation (SP)
|
100% |
2153
37.1 IPS |
|
Machine Translation (HP)
|
100% |
2111
36.4 IPS |
|
Machine Translation (Q)
|
70% |
1052
19.7 IPS |