User | aeonsim |
Upload Date | August 17 2024 06:25 AM |
Views | 5 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce GTX 1050 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Microsoft Corporation Surface Book 2 |
Motherboard | Microsoft Corporation Surface Book 2 |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | Intel Core i7-8650U |
Topology | 1 Processor, 4 Cores, 8 Threads |
Identifier | GenuineIntel Family 6 Model 142 Stepping 10 |
Base Frequency | 2.11 GHz |
Cluster 1 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
56
10.4 IPS |
|
Image Classification (HP)
|
100% |
124
23.0 IPS |
|
Image Classification (Q)
|
100% |
57
10.6 IPS |
|
Image Segmentation (SP)
|
100% |
271
4.40 IPS |
|
Image Segmentation (HP)
|
100% |
196
3.17 IPS |
|
Image Segmentation (Q)
|
98% |
204
3.32 IPS |
|
Pose Estimation (SP)
|
100% |
1803
2.10 IPS |
|
Pose Estimation (HP)
|
100% |
807
0.94 IPS |
|
Pose Estimation (Q)
|
97% |
1430
1.67 IPS |
|
Object Detection (SP)
|
100% |
88
6.99 IPS |
|
Object Detection (HP)
|
100% |
155
12.3 IPS |
|
Object Detection (Q)
|
89% |
76
6.08 IPS |
|
Face Detection (SP)
|
100% |
178
2.12 IPS |
|
Face Detection (HP)
|
100% |
259
3.08 IPS |
|
Face Detection (Q)
|
97% |
142
1.70 IPS |
|
Depth Estimation (SP)
|
100% |
652
5.02 IPS |
|
Depth Estimation (HP)
|
99% |
541
4.17 IPS |
|
Depth Estimation (Q)
|
73% |
487
3.99 IPS |
|
Style Transfer (SP)
|
100% |
2919
3.75 IPS |
|
Style Transfer (HP)
|
100% |
1609
2.07 IPS |
|
Style Transfer (Q)
|
98% |
2445
3.15 IPS |
|
Image Super-Resolution (SP)
|
100% |
781
28.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
494
18.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
498
18.5 IPS |
|
Text Classification (SP)
|
100% |
199
265.2 IPS |
|
Text Classification (HP)
|
100% |
181
242.0 IPS |
|
Text Classification (Q)
|
97% |
105
140.0 IPS |
|
Machine Translation (SP)
|
100% |
322
5.55 IPS |
|
Machine Translation (HP)
|
96% |
302
5.22 IPS |
|
Machine Translation (Q)
|
60% |
89
1.98 IPS |