Upload Date | December 30 2024 04:34 PM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA RTX 5000 Ada Generation Laptop GPU |
System Information | |
---|---|
Operating System | Microsoft Windows 11 (64-bit) |
Model | Dell Inc. Precision 7780 |
Motherboard | Dell Inc. |
CPU Information | |
---|---|
Name | Intel Core i9-13950HX |
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 | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7250
1.35 KIPS |
|
Image Classification (HP)
|
99% |
12773
2.38 KIPS |
|
Image Classification (Q)
|
100% |
6535
1.22 KIPS |
|
Image Segmentation (SP)
|
100% |
11488
186.2 IPS |
|
Image Segmentation (HP)
|
100% |
12707
206.0 IPS |
|
Image Segmentation (Q)
|
98% |
10296
167.4 IPS |
|
Pose Estimation (SP)
|
100% |
134809
157.3 IPS |
|
Pose Estimation (HP)
|
100% |
305838
356.9 IPS |
|
Pose Estimation (Q)
|
96% |
107409
125.8 IPS |
|
Object Detection (SP)
|
100% |
10379
823.2 IPS |
|
Object Detection (HP)
|
100% |
13443
1.07 KIPS |
|
Object Detection (Q)
|
85% |
9259
744.8 IPS |
|
Face Detection (SP)
|
100% |
18420
218.9 IPS |
|
Face Detection (HP)
|
100% |
38195
453.8 IPS |
|
Face Detection (Q)
|
97% |
16574
197.6 IPS |
|
Depth Estimation (SP)
|
100% |
41497
319.7 IPS |
|
Depth Estimation (HP)
|
99% |
91648
708.1 IPS |
|
Depth Estimation (Q)
|
77% |
34212
274.2 IPS |
|
Style Transfer (SP)
|
100% |
256463
329.7 IPS |
|
Style Transfer (HP)
|
100% |
562570
723.2 IPS |
|
Style Transfer (Q)
|
98% |
209771
270.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
33038
1.22 KIPS |
|
Image Super-Resolution (HP)
|
100% |
46555
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
26923
996.9 IPS |
|
Text Classification (SP)
|
100% |
2131
2.84 KIPS |
|
Text Classification (HP)
|
100% |
1724
2.30 KIPS |
|
Text Classification (Q)
|
97% |
1200
1.61 KIPS |
|
Machine Translation (SP)
|
100% |
2687
46.3 IPS |
|
Machine Translation (HP)
|
100% |
2675
46.1 IPS |
|
Machine Translation (Q)
|
70% |
1562
29.3 IPS |