Upload Date | December 23 2024 11:08 PM |
Views | 1 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 4090 Laptop GPU |
System Information | |
---|---|
Operating System | Microsoft Windows 11 (64-bit) |
Model | GIGABYTE AORUS 17X AZF |
Motherboard | GIGABYTE AORUS 17X AZF |
CPU Information | |
---|---|
Name | Intel Core i9-13980HX |
Topology | 1 Processor, 24 Cores, 32 Threads |
Identifier | GenuineIntel Family 6 Model 183 Stepping 1 |
Base Frequency | 2.20 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 16 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
9831
1.83 KIPS |
|
Image Classification (HP)
|
99% |
14870
2.77 KIPS |
|
Image Classification (Q)
|
100% |
8864
1.65 KIPS |
|
Image Segmentation (SP)
|
100% |
14817
240.2 IPS |
|
Image Segmentation (HP)
|
100% |
19111
309.8 IPS |
|
Image Segmentation (Q)
|
98% |
14381
233.9 IPS |
|
Pose Estimation (SP)
|
100% |
189944
221.6 IPS |
|
Pose Estimation (HP)
|
100% |
391673
457.0 IPS |
|
Pose Estimation (Q)
|
96% |
167771
196.6 IPS |
|
Object Detection (SP)
|
100% |
13191
1.05 KIPS |
|
Object Detection (HP)
|
100% |
18834
1.49 KIPS |
|
Object Detection (Q)
|
85% |
11396
916.8 IPS |
|
Face Detection (SP)
|
100% |
34153
405.8 IPS |
|
Face Detection (HP)
|
100% |
45897
545.4 IPS |
|
Face Detection (Q)
|
97% |
29596
352.9 IPS |
|
Depth Estimation (SP)
|
100% |
61880
476.7 IPS |
|
Depth Estimation (HP)
|
99% |
114291
880.5 IPS |
|
Depth Estimation (Q)
|
77% |
43365
347.6 IPS |
|
Style Transfer (SP)
|
100% |
309373
397.7 IPS |
|
Style Transfer (HP)
|
100% |
733493
942.9 IPS |
|
Style Transfer (Q)
|
98% |
268892
346.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
43732
1.61 KIPS |
|
Image Super-Resolution (HP)
|
100% |
59277
2.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
33304
1.23 KIPS |
|
Text Classification (SP)
|
100% |
3194
4.26 KIPS |
|
Text Classification (HP)
|
99% |
3973
5.30 KIPS |
|
Text Classification (Q)
|
97% |
1645
2.20 KIPS |
|
Machine Translation (SP)
|
100% |
3960
68.2 IPS |
|
Machine Translation (HP)
|
100% |
3886
66.9 IPS |
|
Machine Translation (Q)
|
70% |
1971
37.0 IPS |