User | dd88 |
Upload Date | December 07 2024 04:31 PM |
Views | 9 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | Intel(R) Iris(R) Xe Graphics |
System Information | |
---|---|
Operating System | Microsoft Windows 11 IoT LTSC (64-bit) |
Model | TIMI Xiaomi Book Pro 14 2022 |
Motherboard | TIMI TM2117 |
CPU Information | |
---|---|
Name | Intel Core i5-1240P |
Topology | 1 Processor, 12 Cores, 16 Threads |
Identifier | GenuineIntel Family 6 Model 154 Stepping 3 |
Base Frequency | 1.70 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 8 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1020
189.7 IPS |
|
Image Classification (HP)
|
100% |
978
181.9 IPS |
|
Image Classification (Q)
|
100% |
855
159.1 IPS |
|
Image Segmentation (SP)
|
100% |
1495
24.2 IPS |
|
Image Segmentation (HP)
|
100% |
1715
27.8 IPS |
|
Image Segmentation (Q)
|
98% |
1085
17.6 IPS |
|
Pose Estimation (SP)
|
100% |
8828
10.3 IPS |
|
Pose Estimation (HP)
|
100% |
9777
11.4 IPS |
|
Pose Estimation (Q)
|
96% |
4838
5.67 IPS |
|
Object Detection (SP)
|
100% |
1145
90.8 IPS |
|
Object Detection (HP)
|
98% |
980
78.0 IPS |
|
Object Detection (Q)
|
86% |
956
76.8 IPS |
|
Face Detection (SP)
|
100% |
2319
27.6 IPS |
|
Face Detection (HP)
|
100% |
2648
31.5 IPS |
|
Face Detection (Q)
|
97% |
1682
20.1 IPS |
|
Depth Estimation (SP)
|
100% |
4641
35.8 IPS |
|
Depth Estimation (HP)
|
98% |
5135
39.7 IPS |
|
Depth Estimation (Q)
|
77% |
3264
26.1 IPS |
|
Style Transfer (SP)
|
100% |
19280
24.8 IPS |
|
Style Transfer (HP)
|
100% |
24424
31.4 IPS |
|
Style Transfer (Q)
|
98% |
12703
16.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2642
97.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
3475
128.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
1213
44.9 IPS |
|
Text Classification (SP)
|
100% |
834
1.11 KIPS |
|
Text Classification (HP)
|
100% |
346
461.9 IPS |
|
Text Classification (Q)
|
97% |
413
553.4 IPS |
|
Machine Translation (SP)
|
100% |
907
15.6 IPS |
|
Machine Translation (HP)
|
100% |
831
14.3 IPS |
|
Machine Translation (Q)
|
70% |
406
7.62 IPS |