User | Zuluman |
Upload Date | August 17 2024 06:36 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Home (64-bit) |
Model | Microsoft Corporation Surface Pro X |
Motherboard | Microsoft Corporation Surface Pro X |
Power Plan | Ausbalanciert |
CPU Information | |
---|---|
Name | Microsoft SQ1 @ 3.0 GHz |
Topology | 1 Processor, 8 Cores |
Identifier | ARMv8 (64-bit) Family 8 Model 805 Revision D0E |
Base Frequency | 3.00 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Inference Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | Qualcomm(R) Adreno(TM) 680 GPU |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
406
76.1 IPS |
|
Image Classification (F16)
|
100% |
424
79.3 IPS |
|
Image Classification (I8)
|
100% |
230
43.1 IPS |
|
Image Segmentation (F32)
|
100% |
452
7.55 IPS |
|
Image Segmentation (F16)
|
100% |
457
7.63 IPS |
|
Image Segmentation (I8)
|
98% |
267
4.47 IPS |
|
Pose Estimation (F32)
|
100% |
2512
3.04 IPS |
|
Pose Estimation (F16)
|
100% |
2504
3.03 IPS |
|
Pose Estimation (I8)
|
100% |
1790
2.17 IPS |
|
Object Detection (F32)
|
100% |
327
24.4 IPS |
|
Object Detection (F16)
|
100% |
330
24.6 IPS |
|
Object Detection (I8)
|
71% |
226
16.9 IPS |
|
Face Detection (F32)
|
100% |
823
9.78 IPS |
|
Face Detection (F16)
|
100% |
826
9.83 IPS |
|
Face Detection (I8)
|
93% |
390
4.63 IPS |
|
Depth Estimation (F32)
|
100% |
1709
13.3 IPS |
|
Depth Estimation (F16)
|
100% |
1716
13.3 IPS |
|
Depth Estimation (I8)
|
94% |
974
7.56 IPS |
|
Style Transfer (F32)
|
100% |
3558
4.68 IPS |
|
Style Transfer (F16)
|
100% |
3636
4.78 IPS |
|
Style Transfer (I8)
|
98% |
2575
3.39 IPS |
|
Image Super-Resolution (F32)
|
100% |
1345
48.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
1333
47.6 IPS |
|
Image Super-Resolution (I8)
|
99% |
574
20.5 IPS |
|
Text Classification (F32)
|
100% |
158
226.8 IPS |
|
Text Classification (F16)
|
100% |
160
229.6 IPS |
|
Text Classification (I8)
|
98% |
86
123.8 IPS |
|
Machine Translation (F32)
|
100% |
378
6.96 IPS |
|
Machine Translation (F16)
|
100% |
377
6.94 IPS |
|
Machine Translation (I8)
|
65% |
157
2.90 IPS |