Upload Date | January 06 2025 08:41 PM |
Views | 2 |
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% |
2623
487.7 IPS |
|
Image Classification (HP)
|
100% |
471
87.6 IPS |
|
Image Classification (Q)
|
99% |
4481
835.8 IPS |
|
Image Segmentation (SP)
|
100% |
1446
23.4 IPS |
|
Image Segmentation (HP)
|
100% |
831
13.5 IPS |
|
Image Segmentation (Q)
|
98% |
2357
38.3 IPS |
|
Pose Estimation (SP)
|
100% |
5511
6.43 IPS |
|
Pose Estimation (HP)
|
100% |
3618
4.22 IPS |
|
Pose Estimation (Q)
|
94% |
17509
20.5 IPS |
|
Object Detection (SP)
|
100% |
2372
188.1 IPS |
|
Object Detection (HP)
|
100% |
591
46.9 IPS |
|
Object Detection (Q)
|
86% |
4261
342.5 IPS |
|
Face Detection (SP)
|
100% |
6276
74.6 IPS |
|
Face Detection (HP)
|
100% |
1450
17.2 IPS |
|
Face Detection (Q)
|
97% |
7473
89.1 IPS |
|
Depth Estimation (SP)
|
100% |
6995
53.9 IPS |
|
Depth Estimation (HP)
|
99% |
1826
14.1 IPS |
|
Depth Estimation (Q)
|
78% |
12071
96.3 IPS |
|
Style Transfer (SP)
|
100% |
13144
16.9 IPS |
|
Style Transfer (HP)
|
100% |
8841
11.4 IPS |
|
Style Transfer (Q)
|
98% |
20279
26.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
2317
85.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
1764
65.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
3489
129.2 IPS |
|
Text Classification (SP)
|
100% |
1368
1.83 KIPS |
|
Text Classification (HP)
|
100% |
640
854.8 IPS |
|
Text Classification (Q)
|
97% |
433
580.0 IPS |
|
Machine Translation (SP)
|
100% |
1552
26.7 IPS |
|
Machine Translation (HP)
|
100% |
611
10.5 IPS |
|
Machine Translation (Q)
|
65% |
2048
41.1 IPS |