User | mvodya |
Upload Date | February 03 2025 08:01 AM |
Views | 8 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 4090 |
System Information | |
---|---|
Operating System | Windows 11 Pro (64-bit) |
Model | Generic |
Motherboard | ASRock Z390 Taichi |
CPU Information | |
---|---|
Name | Intel Core i9-9900K |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | GenuineIntel Family 6 Model 158 Stepping 13 |
Base Frequency | 3.60 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
10434
1.94 KIPS |
|
Image Classification (HP)
|
99% |
14372
2.68 KIPS |
|
Image Classification (Q)
|
100% |
8533
1.59 KIPS |
|
Image Segmentation (SP)
|
100% |
12613
204.5 IPS |
|
Image Segmentation (HP)
|
100% |
14411
233.6 IPS |
|
Image Segmentation (Q)
|
98% |
11995
195.1 IPS |
|
Pose Estimation (SP)
|
100% |
270692
315.9 IPS |
|
Pose Estimation (HP)
|
100% |
430938
502.8 IPS |
|
Pose Estimation (Q)
|
96% |
239822
281.0 IPS |
|
Object Detection (SP)
|
100% |
13207
1.05 KIPS |
|
Object Detection (HP)
|
100% |
16773
1.33 KIPS |
|
Object Detection (Q)
|
86% |
11235
902.6 IPS |
|
Face Detection (SP)
|
100% |
33711
400.6 IPS |
|
Face Detection (HP)
|
100% |
38583
458.5 IPS |
|
Face Detection (Q)
|
97% |
28925
344.9 IPS |
|
Depth Estimation (SP)
|
100% |
80440
619.7 IPS |
|
Depth Estimation (HP)
|
99% |
125770
969.0 IPS |
|
Depth Estimation (Q)
|
77% |
60664
485.2 IPS |
|
Style Transfer (SP)
|
100% |
465652
598.6 IPS |
|
Style Transfer (HP)
|
100% |
799666
1.03 KIPS |
|
Style Transfer (Q)
|
98% |
407791
525.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
46518
1.72 KIPS |
|
Image Super-Resolution (HP)
|
100% |
62144
2.29 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35127
1.30 KIPS |
|
Text Classification (SP)
|
100% |
3110
4.15 KIPS |
|
Text Classification (HP)
|
99% |
3720
4.97 KIPS |
|
Text Classification (Q)
|
97% |
1802
2.41 KIPS |
|
Machine Translation (SP)
|
100% |
3006
51.8 IPS |
|
Machine Translation (HP)
|
100% |
2924
50.4 IPS |
|
Machine Translation (Q)
|
70% |
1803
33.8 IPS |