User | lionmini |
Upload Date | February 20 2025 05:03 AM |
Views | 5 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD Ryzen 5 6600U |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | LENOVO 21D1 |
Motherboard | LENOVO LNVNB161216 |
CPU Information | |
---|---|
Name | AMD Ryzen 5 6600U |
Topology | 1 Processor, 6 Cores, 12 Threads |
Identifier | AuthenticAMD Family 25 Model 68 Stepping 1 |
Base Frequency | 2.90 GHz |
Cluster 1 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1680
312.5 IPS |
|
Image Classification (HP)
|
100% |
444
82.5 IPS |
|
Image Classification (Q)
|
96% |
3254
607.6 IPS |
|
Image Segmentation (SP)
|
100% |
594
9.63 IPS |
|
Image Segmentation (HP)
|
100% |
383
6.21 IPS |
|
Image Segmentation (Q)
|
97% |
1876
30.5 IPS |
|
Pose Estimation (SP)
|
100% |
3106
3.62 IPS |
|
Pose Estimation (HP)
|
100% |
2684
3.13 IPS |
|
Pose Estimation (Q)
|
86% |
7201
8.51 IPS |
|
Object Detection (SP)
|
100% |
1457
115.6 IPS |
|
Object Detection (HP)
|
100% |
532
42.2 IPS |
|
Object Detection (Q)
|
58% |
2248
245.6 IPS |
|
Face Detection (SP)
|
100% |
3256
38.7 IPS |
|
Face Detection (HP)
|
100% |
1109
13.2 IPS |
|
Face Detection (Q)
|
96% |
5967
71.2 IPS |
|
Depth Estimation (SP)
|
100% |
4298
33.1 IPS |
|
Depth Estimation (HP)
|
99% |
1606
12.4 IPS |
|
Depth Estimation (Q)
|
78% |
7069
56.4 IPS |
|
Style Transfer (SP)
|
100% |
7872
10.1 IPS |
|
Style Transfer (HP)
|
100% |
6617
8.51 IPS |
|
Style Transfer (Q)
|
87% |
11846
15.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
1397
51.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
1286
47.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1947
72.2 IPS |
|
Text Classification (SP)
|
100% |
1213
1.62 KIPS |
|
Text Classification (HP)
|
100% |
646
862.0 IPS |
|
Text Classification (Q)
|
97% |
1122
1.50 KIPS |
|
Machine Translation (SP)
|
100% |
1389
23.9 IPS |
|
Machine Translation (HP)
|
100% |
537
9.25 IPS |
|
Machine Translation (Q)
|
68% |
1733
33.5 IPS |