Upload Date | November 09 2024 07:54 PM |
Views | 1 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce GTX 1650 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | LENOVO 82K2 |
Motherboard | LENOVO LNVNB161216 |
Power Plan | Nihai Performans |
CPU Information | |
---|---|
Name | AMD Ryzen 5 5600H |
Topology | 1 Processor, 6 Cores, 12 Threads |
Identifier | AuthenticAMD Family 25 Model 80 Stepping 0 |
Base Frequency | 3.30 GHz |
Cluster 1 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2586
480.9 IPS |
|
Image Classification (HP)
|
100% |
2371
440.9 IPS |
|
Image Classification (Q)
|
100% |
2109
392.3 IPS |
|
Image Segmentation (SP)
|
100% |
4172
67.6 IPS |
|
Image Segmentation (HP)
|
100% |
3370
54.6 IPS |
|
Image Segmentation (Q)
|
98% |
3563
57.9 IPS |
|
Pose Estimation (SP)
|
100% |
25456
29.7 IPS |
|
Pose Estimation (HP)
|
100% |
16297
19.0 IPS |
|
Pose Estimation (Q)
|
97% |
22394
26.2 IPS |
|
Object Detection (SP)
|
100% |
2912
231.0 IPS |
|
Object Detection (HP)
|
100% |
2762
219.1 IPS |
|
Object Detection (Q)
|
89% |
2275
182.2 IPS |
|
Face Detection (SP)
|
100% |
6319
75.1 IPS |
|
Face Detection (HP)
|
100% |
5406
64.2 IPS |
|
Face Detection (Q)
|
97% |
5209
62.1 IPS |
|
Depth Estimation (SP)
|
100% |
14112
108.7 IPS |
|
Depth Estimation (HP)
|
99% |
10985
84.6 IPS |
|
Depth Estimation (Q)
|
76% |
10639
85.7 IPS |
|
Style Transfer (SP)
|
100% |
45806
58.9 IPS |
|
Style Transfer (HP)
|
100% |
30796
39.6 IPS |
|
Style Transfer (Q)
|
98% |
38993
50.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
9282
342.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
7257
268.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
6386
236.5 IPS |
|
Text Classification (SP)
|
100% |
1552
2.07 KIPS |
|
Text Classification (HP)
|
100% |
933
1.25 KIPS |
|
Text Classification (Q)
|
97% |
891
1.19 KIPS |
|
Machine Translation (SP)
|
100% |
2003
34.5 IPS |
|
Machine Translation (HP)
|
98% |
2041
35.3 IPS |
|
Machine Translation (Q)
|
60% |
822
18.3 IPS |