Upload Date | June 21 2025 06:31 AM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 5060 Ti |
System Information | |
---|---|
Operating System | Microsoft Windows 10 (64-bit) |
Model | HUANANZHI |
Motherboard | HUANANZHI X99-QD4 |
CPU Information | |
---|---|
Name | Intel Xeon E5-2699A v4 |
Topology | 1 Processor, 22 Cores, 44 Threads |
Identifier | GenuineIntel Family 6 Model 79 Stepping 1 |
Base Frequency | 2.40 GHz |
Cluster 1 | 22 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6542
1.22 KIPS |
|
Image Classification (HP)
|
100% |
9840
1.83 KIPS |
|
Image Classification (Q)
|
100% |
5679
1.06 KIPS |
|
Image Segmentation (SP)
|
100% |
11136
180.5 IPS |
|
Image Segmentation (HP)
|
100% |
14256
231.1 IPS |
|
Image Segmentation (Q)
|
98% |
10388
168.9 IPS |
|
Pose Estimation (SP)
|
100% |
115933
135.3 IPS |
|
Pose Estimation (HP)
|
100% |
326156
380.6 IPS |
|
Pose Estimation (Q)
|
96% |
108046
126.6 IPS |
|
Object Detection (SP)
|
100% |
8044
638.1 IPS |
|
Object Detection (HP)
|
100% |
11806
936.4 IPS |
|
Object Detection (Q)
|
83% |
7183
580.4 IPS |
|
Face Detection (SP)
|
100% |
19693
234.0 IPS |
|
Face Detection (HP)
|
100% |
26817
318.6 IPS |
|
Face Detection (Q)
|
97% |
17965
214.2 IPS |
|
Depth Estimation (SP)
|
100% |
49070
378.1 IPS |
|
Depth Estimation (HP)
|
99% |
87330
672.8 IPS |
|
Depth Estimation (Q)
|
78% |
39178
312.7 IPS |
|
Style Transfer (SP)
|
100% |
160490
206.3 IPS |
|
Style Transfer (HP)
|
100% |
474740
610.3 IPS |
|
Style Transfer (Q)
|
98% |
140326
180.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
26763
988.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
46618
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
21738
804.9 IPS |
|
Text Classification (SP)
|
100% |
2397
3.20 KIPS |
|
Text Classification (HP)
|
100% |
2972
3.97 KIPS |
|
Text Classification (Q)
|
97% |
1584
2.12 KIPS |
|
Machine Translation (SP)
|
100% |
3111
53.6 IPS |
|
Machine Translation (HP)
|
100% |
3192
55.0 IPS |
|
Machine Translation (Q)
|
70% |
1584
29.7 IPS |