| User | Oleksandr |
| Upload Date | April 03 2025 06:13 PM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Intel(R) N150 |
| System Information | |
|---|---|
| Operating System | Ubuntu 24.10 |
| Model | GMKtec NucBoxG9 |
| Motherboard | GMKtec GMKtec |
| CPU Information | |
|---|---|
| Name | Intel(R) N150 |
| Topology | 1 Processor, 4 Cores |
| Identifier | GenuineIntel Family 6 Model 190 Stepping 0 |
| Base Frequency | 3.60 GHz |
| Cluster 1 | 0 Cores |
| Memory Information | |
|---|---|
| Size | 10.92 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
419
78.0 IPS |
|
|
Image Classification (HP)
|
100% |
282
52.4 IPS |
|
|
Image Classification (Q)
|
99% |
191
35.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
388
6.29 IPS |
|
|
Image Segmentation (HP)
|
100% |
384
6.23 IPS |
|
|
Image Segmentation (Q)
|
98% |
252
4.09 IPS |
|
|
Pose Estimation (SP)
|
100% |
463
0.54 IPS |
|
|
Pose Estimation (HP)
|
100% |
466
0.54 IPS |
|
|
Pose Estimation (Q)
|
96% |
410
0.48 IPS |
|
|
Object Detection (SP)
|
100% |
264
20.9 IPS |
|
|
Object Detection (HP)
|
100% |
265
21.0 IPS |
|
|
Object Detection (Q)
|
85% |
198
16.0 IPS |
|
|
Face Detection (SP)
|
100% |
605
7.19 IPS |
|
|
Face Detection (HP)
|
100% |
608
7.23 IPS |
|
|
Face Detection (Q)
|
97% |
489
5.83 IPS |
|
|
Depth Estimation (SP)
|
100% |
538
4.14 IPS |
|
|
Depth Estimation (HP)
|
99% |
536
4.13 IPS |
|
|
Depth Estimation (Q)
|
63% |
381
3.57 IPS |
|
|
Style Transfer (SP)
|
100% |
914
1.18 IPS |
|
|
Style Transfer (HP)
|
100% |
919
1.18 IPS |
|
|
Style Transfer (Q)
|
98% |
999
1.29 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
280
10.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
283
10.5 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
246
9.13 IPS |
|
|
Text Classification (SP)
|
100% |
613
818.9 IPS |
|
|
Text Classification (HP)
|
100% |
603
805.2 IPS |
|
|
Text Classification (Q)
|
92% |
235
315.4 IPS |
|
|
Machine Translation (SP)
|
100% |
581
10.0 IPS |
|
|
Machine Translation (HP)
|
100% |
587
10.1 IPS |
|
|
Machine Translation (Q)
|
58% |
186
4.36 IPS |