Upload Date | October 21 2025 08:37 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | AMD Ryzen AI Max+ 395 |
System Information | |
---|---|
Operating System | Ubuntu 24.04.3 LTS |
Model | GMKtec NucBox_EVO-X2 |
Motherboard | GMKtec GMKtec |
CPU Information | |
---|---|
Name | AMD Ryzen AI Max+ 395 |
Topology | 1 Processor, 16 Cores, 32 Threads |
Identifier | AuthenticAMD Family 26 Model 112 Stepping 0 |
Base Frequency | 5.18 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 62.43 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2066
384.1 IPS |
|
Image Classification (HP)
|
100% |
2049
381.1 IPS |
|
Image Classification (Q)
|
99% |
1855
346.0 IPS |
|
Image Segmentation (SP)
|
100% |
3171
51.4 IPS |
|
Image Segmentation (HP)
|
100% |
3258
52.8 IPS |
|
Image Segmentation (Q)
|
98% |
1709
27.8 IPS |
|
Pose Estimation (SP)
|
100% |
4849
5.66 IPS |
|
Pose Estimation (HP)
|
100% |
4809
5.61 IPS |
|
Pose Estimation (Q)
|
96% |
6262
7.34 IPS |
|
Object Detection (SP)
|
100% |
2532
200.9 IPS |
|
Object Detection (HP)
|
100% |
2462
195.3 IPS |
|
Object Detection (Q)
|
85% |
2113
170.1 IPS |
|
Face Detection (SP)
|
100% |
3877
46.1 IPS |
|
Face Detection (HP)
|
100% |
3916
46.5 IPS |
|
Face Detection (Q)
|
97% |
3618
43.1 IPS |
|
Depth Estimation (SP)
|
100% |
3269
25.2 IPS |
|
Depth Estimation (HP)
|
99% |
3369
26.0 IPS |
|
Depth Estimation (Q)
|
63% |
3141
29.4 IPS |
|
Style Transfer (SP)
|
100% |
5604
7.20 IPS |
|
Style Transfer (HP)
|
100% |
5731
7.37 IPS |
|
Style Transfer (Q)
|
98% |
9875
12.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1956
72.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
1988
73.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
2622
97.2 IPS |
|
Text Classification (SP)
|
100% |
1665
2.22 KIPS |
|
Text Classification (HP)
|
100% |
1605
2.14 KIPS |
|
Text Classification (Q)
|
92% |
941
1.26 KIPS |
|
Machine Translation (SP)
|
100% |
5640
97.2 IPS |
|
Machine Translation (HP)
|
100% |
3908
67.3 IPS |
|
Machine Translation (Q)
|
58% |
801
18.8 IPS |