User | krofa |
Upload Date | February 05 2025 11:00 PM |
Views | 10 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 3090 |
System Information | |
---|---|
Operating System | Microsoft Windows 10 Pro (64-bit) |
Model | Generic |
Motherboard | ASRock X79 Professional |
Power Plan | High performance |
CPU Information | |
---|---|
Name | Intel Xeon E5-1680 v2 |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | GenuineIntel Family 6 Model 62 Stepping 4 |
Base Frequency | 3.80 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7190
1.34 KIPS |
|
Image Classification (HP)
|
100% |
9133
1.70 KIPS |
|
Image Classification (Q)
|
100% |
5127
953.4 IPS |
|
Image Segmentation (SP)
|
100% |
8360
135.5 IPS |
|
Image Segmentation (HP)
|
100% |
9556
154.9 IPS |
|
Image Segmentation (Q)
|
98% |
6874
111.8 IPS |
|
Pose Estimation (SP)
|
100% |
160643
187.4 IPS |
|
Pose Estimation (HP)
|
100% |
290030
338.4 IPS |
|
Pose Estimation (Q)
|
96% |
122386
143.4 IPS |
|
Object Detection (SP)
|
100% |
9326
739.8 IPS |
|
Object Detection (HP)
|
100% |
12013
952.9 IPS |
|
Object Detection (Q)
|
85% |
6765
544.2 IPS |
|
Face Detection (SP)
|
100% |
20157
239.5 IPS |
|
Face Detection (HP)
|
100% |
24400
289.9 IPS |
|
Face Detection (Q)
|
97% |
15415
183.8 IPS |
|
Depth Estimation (SP)
|
100% |
56984
439.0 IPS |
|
Depth Estimation (HP)
|
99% |
85537
660.9 IPS |
|
Depth Estimation (Q)
|
77% |
35044
280.4 IPS |
|
Style Transfer (SP)
|
100% |
253278
325.6 IPS |
|
Style Transfer (HP)
|
100% |
520790
669.5 IPS |
|
Style Transfer (Q)
|
98% |
185121
238.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
33782
1.25 KIPS |
|
Image Super-Resolution (HP)
|
100% |
41687
1.54 KIPS |
|
Image Super-Resolution (Q)
|
99% |
19832
734.4 IPS |
|
Text Classification (SP)
|
100% |
2199
2.94 KIPS |
|
Text Classification (HP)
|
100% |
2702
3.61 KIPS |
|
Text Classification (Q)
|
97% |
1177
1.58 KIPS |
|
Machine Translation (SP)
|
100% |
2213
38.1 IPS |
|
Machine Translation (HP)
|
96% |
2187
37.8 IPS |
|
Machine Translation (Q)
|
70% |
1118
21.0 IPS |