User | ggood003 |
Upload Date | August 23 2024 03:18 AM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD Ryzen 9 7900X3D |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | ASRock X670E Taichi |
Motherboard | ASRock X670E Taichi |
Power Plan | High performance |
CPU Information | |
---|---|
Name | AMD Ryzen 9 7900X3D |
Topology | 1 Processor, 12 Cores, 24 Threads |
Identifier | AuthenticAMD Family 25 Model 97 Stepping 2 |
Base Frequency | 4.40 GHz |
Cluster 1 | 12 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1746
324.8 IPS |
|
Image Classification (HP)
|
100% |
183
34.0 IPS |
|
Image Classification (Q)
|
99% |
4433
826.8 IPS |
|
Image Segmentation (SP)
|
100% |
2386
38.7 IPS |
|
Image Segmentation (HP)
|
100% |
276
4.48 IPS |
|
Image Segmentation (Q)
|
98% |
3138
51.0 IPS |
|
Pose Estimation (SP)
|
100% |
12113
14.1 IPS |
|
Pose Estimation (HP)
|
100% |
7772
9.07 IPS |
|
Pose Estimation (Q)
|
95% |
36112
42.3 IPS |
|
Object Detection (SP)
|
100% |
2305
182.8 IPS |
|
Object Detection (HP)
|
100% |
258
20.5 IPS |
|
Object Detection (Q)
|
88% |
2300
184.3 IPS |
|
Face Detection (SP)
|
100% |
4288
51.0 IPS |
|
Face Detection (HP)
|
100% |
361
4.29 IPS |
|
Face Detection (Q)
|
97% |
5771
68.8 IPS |
|
Depth Estimation (SP)
|
100% |
9352
72.1 IPS |
|
Depth Estimation (HP)
|
99% |
1244
9.58 IPS |
|
Depth Estimation (Q)
|
76% |
13820
111.3 IPS |
|
Style Transfer (SP)
|
100% |
24654
31.7 IPS |
|
Style Transfer (HP)
|
100% |
20181
25.9 IPS |
|
Style Transfer (Q)
|
98% |
41571
53.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2593
95.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
2338
86.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
3768
139.5 IPS |
|
Text Classification (SP)
|
100% |
1474
1.97 KIPS |
|
Text Classification (HP)
|
100% |
670
894.6 IPS |
|
Text Classification (Q)
|
97% |
450
602.7 IPS |
|
Machine Translation (SP)
|
100% |
2984
51.4 IPS |
|
Machine Translation (HP)
|
100% |
766
13.2 IPS |
|
Machine Translation (Q)
|
60% |
2850
63.6 IPS |