User | gorg_graggel |
Upload Date | August 31 2025 09:04 AM |
Views | 4 |
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% |
1373
255.4 IPS |
|
Image Classification (HP)
|
100% |
1328
247.0 IPS |
|
Image Classification (Q)
|
99% |
1215
226.6 IPS |
|
Image Segmentation (SP)
|
100% |
2770
44.9 IPS |
|
Image Segmentation (HP)
|
100% |
2783
45.1 IPS |
|
Image Segmentation (Q)
|
98% |
1218
19.8 IPS |
|
Pose Estimation (SP)
|
100% |
3164
3.69 IPS |
|
Pose Estimation (HP)
|
100% |
3164
3.69 IPS |
|
Pose Estimation (Q)
|
96% |
3580
4.19 IPS |
|
Object Detection (SP)
|
100% |
1996
158.3 IPS |
|
Object Detection (HP)
|
100% |
1502
119.2 IPS |
|
Object Detection (Q)
|
85% |
935
75.3 IPS |
|
Face Detection (SP)
|
100% |
3225
38.3 IPS |
|
Face Detection (HP)
|
100% |
3257
38.7 IPS |
|
Face Detection (Q)
|
97% |
2667
31.8 IPS |
|
Depth Estimation (SP)
|
100% |
3233
24.9 IPS |
|
Depth Estimation (HP)
|
99% |
3229
24.9 IPS |
|
Depth Estimation (Q)
|
63% |
2183
20.5 IPS |
|
Style Transfer (SP)
|
100% |
3971
5.10 IPS |
|
Style Transfer (HP)
|
100% |
3963
5.09 IPS |
|
Style Transfer (Q)
|
98% |
6500
8.38 IPS |
|
Image Super-Resolution (SP)
|
100% |
1929
71.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
1787
66.0 IPS |
|
Image Super-Resolution (Q)
|
97% |
1555
57.6 IPS |
|
Text Classification (SP)
|
100% |
2162
2.89 KIPS |
|
Text Classification (HP)
|
100% |
1567
2.09 KIPS |
|
Text Classification (Q)
|
92% |
785
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
2840
48.9 IPS |
|
Machine Translation (HP)
|
100% |
2923
50.3 IPS |
|
Machine Translation (Q)
|
58% |
732
17.2 IPS |