User | krofa |
Upload Date | February 05 2025 09:17 AM |
Views | 6 |
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% |
7400
1.38 KIPS |
|
Image Classification (HP)
|
100% |
8835
1.64 KIPS |
|
Image Classification (Q)
|
100% |
5227
972.1 IPS |
|
Image Segmentation (SP)
|
100% |
7900
128.1 IPS |
|
Image Segmentation (HP)
|
100% |
9232
149.7 IPS |
|
Image Segmentation (Q)
|
98% |
6989
113.7 IPS |
|
Pose Estimation (SP)
|
100% |
163878
191.2 IPS |
|
Pose Estimation (HP)
|
100% |
290975
339.5 IPS |
|
Pose Estimation (Q)
|
96% |
122977
144.1 IPS |
|
Object Detection (SP)
|
100% |
9472
751.3 IPS |
|
Object Detection (HP)
|
100% |
11908
944.5 IPS |
|
Object Detection (Q)
|
85% |
6753
543.2 IPS |
|
Face Detection (SP)
|
100% |
20280
241.0 IPS |
|
Face Detection (HP)
|
100% |
24411
290.1 IPS |
|
Face Detection (Q)
|
97% |
15447
184.2 IPS |
|
Depth Estimation (SP)
|
100% |
58047
447.2 IPS |
|
Depth Estimation (HP)
|
99% |
86705
669.9 IPS |
|
Depth Estimation (Q)
|
77% |
35163
281.4 IPS |
|
Style Transfer (SP)
|
100% |
253808
326.3 IPS |
|
Style Transfer (HP)
|
100% |
521674
670.6 IPS |
|
Style Transfer (Q)
|
98% |
184469
237.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
33404
1.23 KIPS |
|
Image Super-Resolution (HP)
|
100% |
42605
1.57 KIPS |
|
Image Super-Resolution (Q)
|
99% |
20292
751.4 IPS |
|
Text Classification (SP)
|
100% |
2314
3.09 KIPS |
|
Text Classification (HP)
|
100% |
2699
3.60 KIPS |
|
Text Classification (Q)
|
97% |
1256
1.68 KIPS |
|
Machine Translation (SP)
|
100% |
2230
38.4 IPS |
|
Machine Translation (HP)
|
96% |
2184
37.8 IPS |
|
Machine Translation (Q)
|
70% |
1120
21.0 IPS |