Upload Date | June 21 2025 06:04 AM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce GTX 1070 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | INTEL X99E |
Motherboard | INTEL X99E |
Power Plan | Atlas Power Scheme |
CPU Information | |
---|---|
Name | Intel Xeon E5-2680 v4 |
Topology | 1 Processor, 14 Cores, 28 Threads |
Identifier | GenuineIntel Family 6 Model 79 Stepping 1 |
Base Frequency | 2.40 GHz |
Cluster 1 | 14 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1997
371.4 IPS |
|
Image Classification (HP)
|
100% |
3144
584.6 IPS |
|
Image Classification (Q)
|
99% |
1796
335.1 IPS |
|
Image Segmentation (SP)
|
100% |
5402
87.6 IPS |
|
Image Segmentation (HP)
|
100% |
5099
82.7 IPS |
|
Image Segmentation (Q)
|
98% |
4426
72.0 IPS |
|
Pose Estimation (SP)
|
100% |
59244
69.1 IPS |
|
Pose Estimation (HP)
|
100% |
32403
37.8 IPS |
|
Pose Estimation (Q)
|
96% |
47467
55.6 IPS |
|
Object Detection (SP)
|
100% |
2688
213.2 IPS |
|
Object Detection (HP)
|
100% |
4103
325.4 IPS |
|
Object Detection (Q)
|
84% |
2378
191.8 IPS |
|
Face Detection (SP)
|
100% |
5517
65.6 IPS |
|
Face Detection (HP)
|
100% |
8264
98.2 IPS |
|
Face Detection (Q)
|
97% |
4886
58.3 IPS |
|
Depth Estimation (SP)
|
100% |
17998
138.7 IPS |
|
Depth Estimation (HP)
|
99% |
17047
131.7 IPS |
|
Depth Estimation (Q)
|
78% |
13941
111.3 IPS |
|
Style Transfer (SP)
|
100% |
95523
122.8 IPS |
|
Style Transfer (HP)
|
100% |
55647
71.5 IPS |
|
Style Transfer (Q)
|
98% |
73384
94.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
15223
562.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
12319
454.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
9752
361.1 IPS |
|
Text Classification (SP)
|
100% |
1253
1.67 KIPS |
|
Text Classification (HP)
|
100% |
1542
2.06 KIPS |
|
Text Classification (Q)
|
97% |
831
1.11 KIPS |
|
Machine Translation (SP)
|
100% |
2862
49.3 IPS |
|
Machine Translation (HP)
|
96% |
2811
48.6 IPS |
|
Machine Translation (Q)
|
70% |
1413
26.5 IPS |