Upload Date | June 22 2025 09:58 AM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD Ryzen 9 PRO 7940HS |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Ningyu N7 |
Motherboard | Ningyu N7 |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | AMD Ryzen 9 PRO 7940HS |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 25 Model 116 Stepping 1 |
Base Frequency | 4.00 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2464
458.3 IPS |
|
Image Classification (HP)
|
100% |
503
93.6 IPS |
|
Image Classification (Q)
|
99% |
7279
1.36 KIPS |
|
Image Segmentation (SP)
|
100% |
960
15.6 IPS |
|
Image Segmentation (HP)
|
100% |
664
10.8 IPS |
|
Image Segmentation (Q)
|
98% |
3138
51.0 IPS |
|
Pose Estimation (SP)
|
100% |
4979
5.81 IPS |
|
Pose Estimation (HP)
|
100% |
3979
4.64 IPS |
|
Pose Estimation (Q)
|
94% |
15118
17.7 IPS |
|
Object Detection (SP)
|
100% |
2098
166.4 IPS |
|
Object Detection (HP)
|
100% |
567
45.0 IPS |
|
Object Detection (Q)
|
86% |
5185
416.7 IPS |
|
Face Detection (SP)
|
100% |
4942
58.7 IPS |
|
Face Detection (HP)
|
100% |
1409
16.7 IPS |
|
Face Detection (Q)
|
97% |
8347
99.5 IPS |
|
Depth Estimation (SP)
|
100% |
6796
52.4 IPS |
|
Depth Estimation (HP)
|
99% |
2202
17.0 IPS |
|
Depth Estimation (Q)
|
78% |
6837
54.6 IPS |
|
Style Transfer (SP)
|
100% |
12194
15.7 IPS |
|
Style Transfer (HP)
|
100% |
10616
13.6 IPS |
|
Style Transfer (Q)
|
98% |
21694
28.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
1516
56.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
1517
56.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
1888
69.9 IPS |
|
Text Classification (SP)
|
100% |
1337
1.79 KIPS |
|
Text Classification (HP)
|
100% |
606
809.4 IPS |
|
Text Classification (Q)
|
97% |
1537
2.06 KIPS |
|
Machine Translation (SP)
|
100% |
1441
24.8 IPS |
|
Machine Translation (HP)
|
100% |
511
8.80 IPS |
|
Machine Translation (Q)
|
65% |
2030
40.8 IPS |