Upload Date | June 14 2025 10:02 AM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD Ryzen 7 7840HS |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Home Insider Preview (64-bit) |
Model | LENOVO 82Y9 |
Motherboard | LENOVO LNVNB161216 |
CPU Information | |
---|---|
Name | AMD Ryzen 7 7840HS |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 25 Model 116 Stepping 1 |
Base Frequency | 3.80 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1611
299.6 IPS |
|
Image Classification (HP)
|
100% |
355
66.0 IPS |
|
Image Classification (Q)
|
99% |
5027
937.7 IPS |
|
Image Segmentation (SP)
|
100% |
1002
16.2 IPS |
|
Image Segmentation (HP)
|
100% |
465
7.53 IPS |
|
Image Segmentation (Q)
|
98% |
2227
36.2 IPS |
|
Pose Estimation (SP)
|
100% |
3154
3.68 IPS |
|
Pose Estimation (HP)
|
100% |
2762
3.22 IPS |
|
Pose Estimation (Q)
|
94% |
14557
17.1 IPS |
|
Object Detection (SP)
|
100% |
1595
126.5 IPS |
|
Object Detection (HP)
|
100% |
431
34.2 IPS |
|
Object Detection (Q)
|
86% |
4524
363.6 IPS |
|
Face Detection (SP)
|
100% |
3555
42.2 IPS |
|
Face Detection (HP)
|
100% |
1014
12.1 IPS |
|
Face Detection (Q)
|
97% |
6358
75.8 IPS |
|
Depth Estimation (SP)
|
100% |
3917
30.2 IPS |
|
Depth Estimation (HP)
|
99% |
1476
11.4 IPS |
|
Depth Estimation (Q)
|
78% |
5433
43.4 IPS |
|
Style Transfer (SP)
|
100% |
7725
9.93 IPS |
|
Style Transfer (HP)
|
100% |
7144
9.18 IPS |
|
Style Transfer (Q)
|
98% |
17709
22.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
1371
50.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
1282
47.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
2360
87.4 IPS |
|
Text Classification (SP)
|
100% |
938
1.25 KIPS |
|
Text Classification (HP)
|
100% |
438
584.7 IPS |
|
Text Classification (Q)
|
97% |
1167
1.56 KIPS |
|
Machine Translation (SP)
|
100% |
1576
27.2 IPS |
|
Machine Translation (HP)
|
100% |
526
9.06 IPS |
|
Machine Translation (Q)
|
65% |
2496
50.2 IPS |