User | kiodiekin |
Upload Date | August 24 2024 04:41 AM |
Views | 3 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | Intel N100 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Default string Default string |
Motherboard | Default string Default string |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel N100 |
Topology | 1 Processor, 4 Cores |
Identifier | GenuineIntel Family 6 Model 190 Stepping 0 |
Base Frequency | 800 MHz |
Cluster 1 | 4 Cores |
Memory Information | |
---|---|
Size | 4.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
386
71.8 IPS |
|
Image Classification (HP)
|
100% |
67
12.5 IPS |
|
Image Classification (Q)
|
99% |
584
108.9 IPS |
|
Image Segmentation (SP)
|
100% |
343
5.56 IPS |
|
Image Segmentation (HP)
|
100% |
83
1.34 IPS |
|
Image Segmentation (Q)
|
98% |
631
10.3 IPS |
|
Pose Estimation (SP)
|
100% |
670
0.78 IPS |
|
Pose Estimation (HP)
|
100% |
513
0.60 IPS |
|
Pose Estimation (Q)
|
95% |
1699
1.99 IPS |
|
Object Detection (SP)
|
100% |
330
26.2 IPS |
|
Object Detection (HP)
|
100% |
69
5.47 IPS |
|
Object Detection (Q)
|
88% |
395
31.7 IPS |
|
Face Detection (SP)
|
100% |
571
6.78 IPS |
|
Face Detection (HP)
|
100% |
106
1.27 IPS |
|
Face Detection (Q)
|
97% |
998
11.9 IPS |
|
Depth Estimation (SP)
|
100% |
906
6.98 IPS |
|
Depth Estimation (HP)
|
99% |
270
2.08 IPS |
|
Depth Estimation (Q)
|
76% |
1335
10.8 IPS |
|
Style Transfer (SP)
|
100% |
1773
2.28 IPS |
|
Style Transfer (HP)
|
100% |
1292
1.66 IPS |
|
Style Transfer (Q)
|
98% |
2827
3.65 IPS |
|
Image Super-Resolution (SP)
|
100% |
408
15.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
299
11.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
809
30.0 IPS |
|
Text Classification (SP)
|
100% |
496
662.1 IPS |
|
Text Classification (HP)
|
100% |
251
335.5 IPS |
|
Text Classification (Q)
|
97% |
194
259.5 IPS |
|
Machine Translation (SP)
|
100% |
538
9.27 IPS |
|
Machine Translation (HP)
|
100% |
205
3.54 IPS |
|
Machine Translation (Q)
|
60% |
549
12.3 IPS |