User | eclipse10000 |
Upload Date | December 11 2024 05:48 PM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA T400 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | QEMU Standard PC (Q35 + ICH9, 2009) |
Motherboard | |
Power Plan | High performance |
CPU Information | |
---|---|
Name | Intel Core i9-13900K |
Topology | 1 Processor, 16 Cores |
Identifier | GenuineIntel Family 6 Model 183 Stepping 1 |
Base Frequency | 3.00 GHz |
Cluster 1 | 16 Cores |
Memory Information | |
---|---|
Size | 31.25 GB |
Type | RAM |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1229
228.6 IPS |
|
Image Classification (HP)
|
100% |
1083
201.3 IPS |
|
Image Classification (Q)
|
99% |
1140
212.6 IPS |
|
Image Segmentation (SP)
|
100% |
1446
23.4 IPS |
|
Image Segmentation (HP)
|
100% |
1210
19.6 IPS |
|
Image Segmentation (Q)
|
98% |
1310
21.3 IPS |
|
Pose Estimation (SP)
|
100% |
10075
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
6147
7.17 IPS |
|
Pose Estimation (Q)
|
96% |
9052
10.6 IPS |
|
Object Detection (SP)
|
100% |
1356
107.6 IPS |
|
Object Detection (HP)
|
100% |
1204
95.5 IPS |
|
Object Detection (Q)
|
83% |
1224
98.9 IPS |
|
Face Detection (SP)
|
100% |
2824
33.6 IPS |
|
Face Detection (HP)
|
100% |
2253
26.8 IPS |
|
Face Detection (Q)
|
97% |
2554
30.4 IPS |
|
Depth Estimation (SP)
|
100% |
6835
52.7 IPS |
|
Depth Estimation (HP)
|
99% |
4691
36.1 IPS |
|
Depth Estimation (Q)
|
78% |
5652
45.1 IPS |
|
Style Transfer (SP)
|
100% |
17651
22.7 IPS |
|
Style Transfer (HP)
|
100% |
11918
15.3 IPS |
|
Style Transfer (Q)
|
98% |
15625
20.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3937
145.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
3210
118.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
2932
108.6 IPS |
|
Text Classification (SP)
|
100% |
1245
1.66 KIPS |
|
Text Classification (HP)
|
100% |
607
810.8 IPS |
|
Text Classification (Q)
|
97% |
654
876.3 IPS |
|
Machine Translation (SP)
|
100% |
686
11.8 IPS |
|
Machine Translation (HP)
|
98% |
687
11.9 IPS |
|
Machine Translation (Q)
|
70% |
444
8.33 IPS |