User | krofa |
Upload Date | February 25 2025 09:50 AM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 3090 Ti |
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% |
6884
1.28 KIPS |
|
Image Classification (HP)
|
99% |
8442
1.57 KIPS |
|
Image Classification (Q)
|
100% |
5119
952.0 IPS |
|
Image Segmentation (SP)
|
100% |
7343
119.0 IPS |
|
Image Segmentation (HP)
|
100% |
8330
135.0 IPS |
|
Image Segmentation (Q)
|
98% |
6215
101.1 IPS |
|
Pose Estimation (SP)
|
100% |
170581
199.0 IPS |
|
Pose Estimation (HP)
|
100% |
279461
326.1 IPS |
|
Pose Estimation (Q)
|
96% |
128075
150.1 IPS |
|
Object Detection (SP)
|
100% |
8646
685.8 IPS |
|
Object Detection (HP)
|
100% |
10714
849.8 IPS |
|
Object Detection (Q)
|
85% |
6544
526.4 IPS |
|
Face Detection (SP)
|
100% |
18255
216.9 IPS |
|
Face Detection (HP)
|
100% |
21352
253.7 IPS |
|
Face Detection (Q)
|
97% |
14255
170.0 IPS |
|
Depth Estimation (SP)
|
100% |
57665
444.3 IPS |
|
Depth Estimation (HP)
|
99% |
84530
651.3 IPS |
|
Depth Estimation (Q)
|
77% |
35955
287.7 IPS |
|
Style Transfer (SP)
|
100% |
254364
327.0 IPS |
|
Style Transfer (HP)
|
100% |
495948
637.5 IPS |
|
Style Transfer (Q)
|
98% |
184780
238.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
32308
1.19 KIPS |
|
Image Super-Resolution (HP)
|
100% |
41513
1.53 KIPS |
|
Image Super-Resolution (Q)
|
99% |
19921
737.7 IPS |
|
Text Classification (SP)
|
100% |
2193
2.93 KIPS |
|
Text Classification (HP)
|
99% |
2691
3.59 KIPS |
|
Text Classification (Q)
|
97% |
1231
1.65 KIPS |
|
Machine Translation (SP)
|
100% |
1945
33.5 IPS |
|
Machine Translation (HP)
|
100% |
1949
33.6 IPS |
|
Machine Translation (Q)
|
70% |
1053
19.7 IPS |