User | gbmk |
Upload Date | May 27 2025 06:48 PM |
Views | 2 |
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% |
2133
396.6 IPS |
|
Image Classification (HP)
|
100% |
2103
391.1 IPS |
|
Image Classification (Q)
|
99% |
1899
354.1 IPS |
|
Image Segmentation (SP)
|
100% |
3261
52.9 IPS |
|
Image Segmentation (HP)
|
100% |
3298
53.5 IPS |
|
Image Segmentation (Q)
|
98% |
1684
27.4 IPS |
|
Pose Estimation (SP)
|
100% |
4219
4.92 IPS |
|
Pose Estimation (HP)
|
100% |
4205
4.91 IPS |
|
Pose Estimation (Q)
|
96% |
5678
6.65 IPS |
|
Object Detection (SP)
|
100% |
2166
171.8 IPS |
|
Object Detection (HP)
|
100% |
2221
176.2 IPS |
|
Object Detection (Q)
|
85% |
2043
164.4 IPS |
|
Face Detection (SP)
|
100% |
3989
47.4 IPS |
|
Face Detection (HP)
|
100% |
4039
48.0 IPS |
|
Face Detection (Q)
|
97% |
3988
47.6 IPS |
|
Depth Estimation (SP)
|
100% |
3448
26.6 IPS |
|
Depth Estimation (HP)
|
99% |
3471
26.7 IPS |
|
Depth Estimation (Q)
|
63% |
3152
29.6 IPS |
|
Style Transfer (SP)
|
100% |
4740
6.09 IPS |
|
Style Transfer (HP)
|
100% |
4738
6.09 IPS |
|
Style Transfer (Q)
|
98% |
9339
12.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
2317
85.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
2304
85.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
2685
99.5 IPS |
|
Text Classification (SP)
|
100% |
1809
2.41 KIPS |
|
Text Classification (HP)
|
100% |
1715
2.29 KIPS |
|
Text Classification (Q)
|
92% |
1044
1.40 KIPS |
|
Machine Translation (SP)
|
100% |
4044
69.7 IPS |
|
Machine Translation (HP)
|
100% |
4152
71.5 IPS |
|
Machine Translation (Q)
|
58% |
949
22.3 IPS |