Upload Date | June 21 2025 06:29 AM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 4060 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% |
5369
998.5 IPS |
|
Image Classification (HP)
|
99% |
7339
1.37 KIPS |
|
Image Classification (Q)
|
99% |
4843
903.4 IPS |
|
Image Segmentation (SP)
|
100% |
7404
120.0 IPS |
|
Image Segmentation (HP)
|
100% |
8497
137.7 IPS |
|
Image Segmentation (Q)
|
98% |
7176
116.7 IPS |
|
Pose Estimation (SP)
|
100% |
104420
121.8 IPS |
|
Pose Estimation (HP)
|
100% |
263186
307.1 IPS |
|
Pose Estimation (Q)
|
96% |
91827
107.6 IPS |
|
Object Detection (SP)
|
100% |
6430
510.0 IPS |
|
Object Detection (HP)
|
100% |
8430
668.7 IPS |
|
Object Detection (Q)
|
85% |
5918
476.4 IPS |
|
Face Detection (SP)
|
100% |
14662
174.2 IPS |
|
Face Detection (HP)
|
100% |
17994
213.8 IPS |
|
Face Detection (Q)
|
97% |
13571
161.8 IPS |
|
Depth Estimation (SP)
|
100% |
43779
337.3 IPS |
|
Depth Estimation (HP)
|
99% |
68575
528.3 IPS |
|
Depth Estimation (Q)
|
77% |
35594
285.0 IPS |
|
Style Transfer (SP)
|
100% |
172013
221.1 IPS |
|
Style Transfer (HP)
|
100% |
339677
436.7 IPS |
|
Style Transfer (Q)
|
98% |
156865
202.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
25007
923.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
35524
1.31 KIPS |
|
Image Super-Resolution (Q)
|
99% |
20437
756.7 IPS |
|
Text Classification (SP)
|
100% |
2126
2.84 KIPS |
|
Text Classification (HP)
|
99% |
2882
3.85 KIPS |
|
Text Classification (Q)
|
97% |
1631
2.18 KIPS |
|
Machine Translation (SP)
|
100% |
2075
35.7 IPS |
|
Machine Translation (HP)
|
100% |
2137
36.8 IPS |
|
Machine Translation (Q)
|
70% |
1309
24.5 IPS |