User | gbmk |
Upload Date | May 27 2025 09:11 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | AMD Ryzen 9 9900X 12-Core Processor |
System Information | |
---|---|
Operating System | Ubuntu 25.04 |
Model | ASRock X870E Nova WiFi |
Motherboard | ASRock X870E Nova WiFi |
CPU Information | |
---|---|
Name | AMD Ryzen 9 9900X 12-Core Processor |
Topology | 1 Processor, 12 Cores, 24 Threads |
Identifier | AuthenticAMD Family 26 Model 68 Stepping 0 |
Base Frequency | 5.66 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 60.41 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2137
397.4 IPS |
|
Image Classification (HP)
|
100% |
2029
377.3 IPS |
|
Image Classification (Q)
|
99% |
1885
351.7 IPS |
|
Image Segmentation (SP)
|
100% |
3303
53.5 IPS |
|
Image Segmentation (HP)
|
100% |
3425
55.5 IPS |
|
Image Segmentation (Q)
|
98% |
1707
27.8 IPS |
|
Pose Estimation (SP)
|
100% |
4210
4.91 IPS |
|
Pose Estimation (HP)
|
100% |
4189
4.89 IPS |
|
Pose Estimation (Q)
|
96% |
5735
6.72 IPS |
|
Object Detection (SP)
|
100% |
2167
171.9 IPS |
|
Object Detection (HP)
|
100% |
2189
173.7 IPS |
|
Object Detection (Q)
|
85% |
2073
166.9 IPS |
|
Face Detection (SP)
|
100% |
4008
47.6 IPS |
|
Face Detection (HP)
|
100% |
4015
47.7 IPS |
|
Face Detection (Q)
|
97% |
3985
47.5 IPS |
|
Depth Estimation (SP)
|
100% |
3467
26.7 IPS |
|
Depth Estimation (HP)
|
99% |
3520
27.1 IPS |
|
Depth Estimation (Q)
|
63% |
3141
29.5 IPS |
|
Style Transfer (SP)
|
100% |
4676
6.01 IPS |
|
Style Transfer (HP)
|
100% |
4708
6.05 IPS |
|
Style Transfer (Q)
|
98% |
9375
12.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
2317
85.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
2322
85.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
2694
99.8 IPS |
|
Text Classification (SP)
|
100% |
1875
2.50 KIPS |
|
Text Classification (HP)
|
100% |
1676
2.24 KIPS |
|
Text Classification (Q)
|
92% |
1047
1.41 KIPS |
|
Machine Translation (SP)
|
100% |
4314
74.3 IPS |
|
Machine Translation (HP)
|
100% |
4316
74.3 IPS |
|
Machine Translation (Q)
|
58% |
949
22.3 IPS |