User | nimblebits |
Upload Date | September 22 2024 11:17 AM |
Views | 6 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | Intel(R) UHD Graphics 620 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Dell Inc. Inspiron 3576 |
Motherboard | Dell Inc. 0K83NX |
Power Plan | High performance |
CPU Information | |
---|---|
Name | Intel Core i5-8250U |
Topology | 1 Processor, 4 Cores, 8 Threads |
Identifier | GenuineIntel Family 6 Model 142 Stepping 10 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
384
71.5 IPS |
|
Image Classification (HP)
|
100% |
434
80.8 IPS |
|
Image Classification (Q)
|
99% |
347
64.7 IPS |
|
Image Segmentation (SP)
|
100% |
573
9.30 IPS |
|
Image Segmentation (HP)
|
100% |
670
10.9 IPS |
|
Image Segmentation (Q)
|
98% |
489
7.94 IPS |
|
Pose Estimation (SP)
|
100% |
2289
2.67 IPS |
|
Pose Estimation (HP)
|
100% |
3633
4.24 IPS |
|
Pose Estimation (Q)
|
97% |
2083
2.44 IPS |
|
Object Detection (SP)
|
100% |
449
35.6 IPS |
|
Object Detection (HP)
|
98% |
449
35.7 IPS |
|
Object Detection (Q)
|
89% |
367
29.4 IPS |
|
Face Detection (SP)
|
100% |
793
9.43 IPS |
|
Face Detection (HP)
|
100% |
914
10.9 IPS |
|
Face Detection (Q)
|
97% |
653
7.79 IPS |
|
Depth Estimation (SP)
|
100% |
1646
12.7 IPS |
|
Depth Estimation (HP)
|
98% |
2017
15.6 IPS |
|
Depth Estimation (Q)
|
75% |
1373
11.1 IPS |
|
Style Transfer (SP)
|
100% |
5864
7.54 IPS |
|
Style Transfer (HP)
|
100% |
8828
11.3 IPS |
|
Style Transfer (Q)
|
98% |
5035
6.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
1155
42.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
1559
57.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
771
28.6 IPS |
|
Text Classification (SP)
|
100% |
322
429.3 IPS |
|
Text Classification (HP)
|
100% |
204
271.7 IPS |
|
Text Classification (Q)
|
97% |
218
292.4 IPS |
|
Machine Translation (SP)
|
100% |
365
6.29 IPS |
|
Machine Translation (HP)
|
100% |
362
6.24 IPS |
|
Machine Translation (Q)
|
60% |
184
4.10 IPS |