Upload Date | September 16 2025 06:56 PM |
Views | 2 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce GTX 1660 SUPER |
System Information | |
---|---|
Operating System | Microsoft Windows 10 Pro (64-bit) |
Model | ASUS All Series |
Motherboard | ASUSTeK COMPUTER INC. H81M-CS |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Core i5-4460 |
Topology | 1 Processor, 4 Cores |
Identifier | GenuineIntel Family 6 Model 60 Stepping 3 |
Base Frequency | 3.20 GHz |
Cluster 1 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3792
705.3 IPS |
|
Image Classification (HP)
|
100% |
3573
664.5 IPS |
|
Image Classification (Q)
|
99% |
3141
585.8 IPS |
|
Image Segmentation (SP)
|
100% |
5931
96.2 IPS |
|
Image Segmentation (HP)
|
100% |
4957
80.4 IPS |
|
Image Segmentation (Q)
|
98% |
4737
77.0 IPS |
|
Pose Estimation (SP)
|
100% |
39817
46.5 IPS |
|
Pose Estimation (HP)
|
100% |
23999
28.0 IPS |
|
Pose Estimation (Q)
|
96% |
35518
41.6 IPS |
|
Object Detection (SP)
|
100% |
4609
365.6 IPS |
|
Object Detection (HP)
|
100% |
4293
340.5 IPS |
|
Object Detection (Q)
|
83% |
3724
300.9 IPS |
|
Face Detection (SP)
|
100% |
10496
124.7 IPS |
|
Face Detection (HP)
|
100% |
7928
94.2 IPS |
|
Face Detection (Q)
|
97% |
8954
106.8 IPS |
|
Depth Estimation (SP)
|
100% |
22599
174.1 IPS |
|
Depth Estimation (HP)
|
99% |
16608
128.0 IPS |
|
Depth Estimation (Q)
|
78% |
16600
132.5 IPS |
|
Style Transfer (SP)
|
100% |
69174
88.9 IPS |
|
Style Transfer (HP)
|
100% |
47527
61.1 IPS |
|
Style Transfer (Q)
|
98% |
59295
76.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
13658
504.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
9921
366.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
8810
326.2 IPS |
|
Text Classification (SP)
|
100% |
1533
2.05 KIPS |
|
Text Classification (HP)
|
100% |
1253
1.67 KIPS |
|
Text Classification (Q)
|
97% |
881
1.18 KIPS |
|
Machine Translation (SP)
|
100% |
2380
41.0 IPS |
|
Machine Translation (HP)
|
98% |
2380
41.1 IPS |
|
Machine Translation (Q)
|
70% |
1117
21.0 IPS |