User | tester_one |
Upload Date | August 11 2025 11:28 PM |
Views | 12 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA T400 4GB |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Advantech Default string |
Motherboard | Advantech AIMB-788E |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Core i5-12500 |
Topology | 1 Processor, 6 Cores, 12 Threads |
Identifier | GenuineIntel Family 6 Model 151 Stepping 5 |
Base Frequency | 3.00 GHz |
Cluster 1 | 6 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1403
261.0 IPS |
|
Image Classification (HP)
|
100% |
1179
219.2 IPS |
|
Image Classification (Q)
|
99% |
1294
241.4 IPS |
|
Image Segmentation (SP)
|
100% |
2195
35.6 IPS |
|
Image Segmentation (HP)
|
100% |
1630
26.4 IPS |
|
Image Segmentation (Q)
|
98% |
1888
30.7 IPS |
|
Pose Estimation (SP)
|
100% |
10110
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
6065
7.08 IPS |
|
Pose Estimation (Q)
|
96% |
9066
10.6 IPS |
|
Object Detection (SP)
|
100% |
1611
127.8 IPS |
|
Object Detection (HP)
|
100% |
1374
109.0 IPS |
|
Object Detection (Q)
|
83% |
1428
115.3 IPS |
|
Face Detection (SP)
|
100% |
3430
40.8 IPS |
|
Face Detection (HP)
|
100% |
2548
30.3 IPS |
|
Face Detection (Q)
|
97% |
3086
36.8 IPS |
|
Depth Estimation (SP)
|
100% |
6968
53.7 IPS |
|
Depth Estimation (HP)
|
99% |
4658
35.9 IPS |
|
Depth Estimation (Q)
|
78% |
5718
45.6 IPS |
|
Style Transfer (SP)
|
100% |
17509
22.5 IPS |
|
Style Transfer (HP)
|
100% |
11560
14.9 IPS |
|
Style Transfer (Q)
|
98% |
15392
19.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4047
149.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
3214
118.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
2996
110.9 IPS |
|
Text Classification (SP)
|
100% |
1359
1.81 KIPS |
|
Text Classification (HP)
|
100% |
613
817.7 IPS |
|
Text Classification (Q)
|
97% |
670
897.2 IPS |
|
Machine Translation (SP)
|
100% |
1826
31.4 IPS |
|
Machine Translation (HP)
|
98% |
1806
31.2 IPS |
|
Machine Translation (Q)
|
70% |
735
13.8 IPS |