User | gorg_graggel |
Upload Date | August 21 2025 05:33 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | AMD Ryzen 9 8945HS |
System Information | |
---|---|
Operating System | CachyOS |
Model | GMKtec NucBox K11 |
Motherboard | GMKtec NucBox K11 |
CPU Information | |
---|---|
Name | AMD Ryzen 9 8945HS |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 25 Model 117 Stepping 2 |
Base Frequency | 5.26 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 58.67 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1612
299.8 IPS |
|
Image Classification (HP)
|
100% |
1807
336.0 IPS |
|
Image Classification (Q)
|
99% |
1395
260.2 IPS |
|
Image Segmentation (SP)
|
100% |
2609
42.3 IPS |
|
Image Segmentation (HP)
|
100% |
2660
43.1 IPS |
|
Image Segmentation (Q)
|
98% |
1184
19.2 IPS |
|
Pose Estimation (SP)
|
100% |
2993
3.49 IPS |
|
Pose Estimation (HP)
|
100% |
2993
3.49 IPS |
|
Pose Estimation (Q)
|
96% |
3463
4.06 IPS |
|
Object Detection (SP)
|
100% |
1448
114.8 IPS |
|
Object Detection (HP)
|
100% |
2045
162.2 IPS |
|
Object Detection (Q)
|
85% |
1146
92.2 IPS |
|
Face Detection (SP)
|
100% |
3121
37.1 IPS |
|
Face Detection (HP)
|
100% |
3080
36.6 IPS |
|
Face Detection (Q)
|
97% |
2654
31.6 IPS |
|
Depth Estimation (SP)
|
100% |
3137
24.2 IPS |
|
Depth Estimation (HP)
|
99% |
2993
23.1 IPS |
|
Depth Estimation (Q)
|
63% |
2213
20.7 IPS |
|
Style Transfer (SP)
|
100% |
3875
4.98 IPS |
|
Style Transfer (HP)
|
100% |
3845
4.94 IPS |
|
Style Transfer (Q)
|
98% |
6236
8.04 IPS |
|
Image Super-Resolution (SP)
|
100% |
1930
71.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
1830
67.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1495
55.4 IPS |
|
Text Classification (SP)
|
100% |
1574
2.10 KIPS |
|
Text Classification (HP)
|
100% |
2169
2.89 KIPS |
|
Text Classification (Q)
|
92% |
779
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
2904
50.0 IPS |
|
Machine Translation (HP)
|
100% |
2927
50.4 IPS |
|
Machine Translation (Q)
|
58% |
699
16.4 IPS |