Upload Date | January 06 2025 08:33 PM |
Views | 1 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | Intel Core i9-12900H |
System Information | |
---|---|
Operating System | Windows 11 (64-bit) |
Model | LENOVO 82RF |
Motherboard | LENOVO LNVNB161216 |
CPU Information | |
---|---|
Name | Intel Core i9-12900H |
Topology | 1 Processor, 14 Cores, 20 Threads |
Identifier | GenuineIntel Family 6 Model 154 Stepping 3 |
Base Frequency | 2.50 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2382
442.9 IPS |
|
Image Classification (HP)
|
100% |
467
86.9 IPS |
|
Image Classification (Q)
|
99% |
4240
790.8 IPS |
|
Image Segmentation (SP)
|
100% |
1165
18.9 IPS |
|
Image Segmentation (HP)
|
100% |
763
12.4 IPS |
|
Image Segmentation (Q)
|
98% |
2125
34.5 IPS |
|
Pose Estimation (SP)
|
100% |
5577
6.51 IPS |
|
Pose Estimation (HP)
|
100% |
3616
4.22 IPS |
|
Pose Estimation (Q)
|
94% |
17355
20.3 IPS |
|
Object Detection (SP)
|
100% |
2314
183.5 IPS |
|
Object Detection (HP)
|
100% |
568
45.0 IPS |
|
Object Detection (Q)
|
86% |
4164
334.6 IPS |
|
Face Detection (SP)
|
100% |
5679
67.5 IPS |
|
Face Detection (HP)
|
100% |
1370
16.3 IPS |
|
Face Detection (Q)
|
97% |
7256
86.5 IPS |
|
Depth Estimation (SP)
|
100% |
6942
53.5 IPS |
|
Depth Estimation (HP)
|
99% |
1775
13.7 IPS |
|
Depth Estimation (Q)
|
78% |
11994
95.7 IPS |
|
Style Transfer (SP)
|
100% |
12834
16.5 IPS |
|
Style Transfer (HP)
|
100% |
8859
11.4 IPS |
|
Style Transfer (Q)
|
98% |
20648
26.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2172
80.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
1720
63.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
3348
124.0 IPS |
|
Text Classification (SP)
|
100% |
1431
1.91 KIPS |
|
Text Classification (HP)
|
100% |
640
854.9 IPS |
|
Text Classification (Q)
|
97% |
436
584.1 IPS |
|
Machine Translation (SP)
|
100% |
1472
25.4 IPS |
|
Machine Translation (HP)
|
100% |
593
10.2 IPS |
|
Machine Translation (Q)
|
65% |
1808
36.3 IPS |