Upload Date | December 26 2024 03:42 AM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | Intel(R) Arc(TM) 130V GPU (8GB) |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | GETAC F120 |
Motherboard | GETAC F120 |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel(R) Core(TM) Ultra 5 226V |
Topology | 1 Processor, 8 Cores |
Identifier | GenuineIntel Family 6 Model 189 Stepping 1 |
Base Frequency | 2.10 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1161
215.9 IPS |
|
Image Classification (HP)
|
100% |
2051
381.3 IPS |
|
Image Classification (Q)
|
100% |
1201
223.3 IPS |
|
Image Segmentation (SP)
|
100% |
2270
36.8 IPS |
|
Image Segmentation (HP)
|
100% |
3992
64.7 IPS |
|
Image Segmentation (Q)
|
98% |
1812
29.5 IPS |
|
Pose Estimation (SP)
|
100% |
7268
8.48 IPS |
|
Pose Estimation (HP)
|
100% |
40646
47.4 IPS |
|
Pose Estimation (Q)
|
96% |
7152
8.38 IPS |
|
Object Detection (SP)
|
100% |
2075
164.6 IPS |
|
Object Detection (HP)
|
100% |
3227
255.9 IPS |
|
Object Detection (Q)
|
88% |
1605
128.7 IPS |
|
Face Detection (SP)
|
100% |
3908
46.4 IPS |
|
Face Detection (HP)
|
100% |
7168
85.2 IPS |
|
Face Detection (Q)
|
97% |
2845
33.9 IPS |
|
Depth Estimation (SP)
|
100% |
7228
55.7 IPS |
|
Depth Estimation (HP)
|
99% |
15201
117.1 IPS |
|
Depth Estimation (Q)
|
77% |
5091
40.7 IPS |
|
Style Transfer (SP)
|
100% |
21557
27.7 IPS |
|
Style Transfer (HP)
|
100% |
67109
86.3 IPS |
|
Style Transfer (Q)
|
98% |
15420
19.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3429
126.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
7242
267.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
1869
69.2 IPS |
|
Text Classification (SP)
|
100% |
637
850.4 IPS |
|
Text Classification (HP)
|
100% |
625
833.6 IPS |
|
Text Classification (Q)
|
97% |
318
426.2 IPS |
|
Machine Translation (SP)
|
100% |
1089
18.8 IPS |
|
Machine Translation (HP)
|
100% |
1074
18.5 IPS |
|
Machine Translation (Q)
|
70% |
518
9.72 IPS |