Upload Date | January 07 2025 04:45 AM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | Intel(R) Arc(TM) Graphics |
System Information | |
---|---|
Operating System | Microsoft Windows 11 IoT Enterprise LTSC (64-bit) |
Model | Unknown |
Motherboard |
CPU Information | |
---|---|
Name | Intel(R) Core(TM) Ultra 7 155HL |
Topology | 1 Processor, 16 Cores, 22 Threads |
Identifier | GenuineIntel Family 6 Model 170 Stepping 4 |
Base Frequency | 2.50 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 10 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1567
291.4 IPS |
|
Image Classification (HP)
|
100% |
5321
989.6 IPS |
|
Image Classification (Q)
|
100% |
1406
261.4 IPS |
|
Image Segmentation (SP)
|
100% |
1608
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
7337
118.9 IPS |
|
Image Segmentation (Q)
|
98% |
1372
22.3 IPS |
|
Pose Estimation (SP)
|
100% |
14118
16.5 IPS |
|
Pose Estimation (HP)
|
100% |
20659
24.1 IPS |
|
Pose Estimation (Q)
|
95% |
12085
14.2 IPS |
|
Object Detection (SP)
|
100% |
1502
119.2 IPS |
|
Object Detection (HP)
|
99% |
5202
413.8 IPS |
|
Object Detection (Q)
|
86% |
1351
108.6 IPS |
|
Face Detection (SP)
|
100% |
1170
13.9 IPS |
|
Face Detection (HP)
|
100% |
9201
109.3 IPS |
|
Face Detection (Q)
|
97% |
1083
12.9 IPS |
|
Depth Estimation (SP)
|
100% |
8164
62.9 IPS |
|
Depth Estimation (HP)
|
98% |
22167
171.4 IPS |
|
Depth Estimation (Q)
|
76% |
6712
53.9 IPS |
|
Style Transfer (SP)
|
100% |
44176
56.8 IPS |
|
Style Transfer (HP)
|
100% |
74267
95.5 IPS |
|
Style Transfer (Q)
|
98% |
32100
41.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
8091
298.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
12539
463.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
5276
195.4 IPS |
|
Text Classification (SP)
|
86% |
735
994.6 IPS |
|
Text Classification (HP)
|
99% |
658
877.8 IPS |
|
Text Classification (Q)
|
84% |
494
670.9 IPS |
|
Machine Translation (SP)
|
100% |
2221
38.3 IPS |
|
Machine Translation (HP)
|
100% |
2086
35.9 IPS |
|
Machine Translation (Q)
|
70% |
965
18.1 IPS |