Upload Date | April 17 2025 03:31 PM |
Views | 1 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | AMD Radeon 780M Graphics |
System Information | |
---|---|
Operating System | Windows 11 Pro (64-bit) |
Model | AZW SER8 |
Motherboard | AZW SER8 |
CPU Information | |
---|---|
Name | AMD Ryzen 7 8845HS |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 25 Model 117 Stepping 2 |
Base Frequency | 3.80 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3150
585.9 IPS |
|
Image Classification (HP)
|
100% |
4436
824.9 IPS |
|
Image Classification (Q)
|
100% |
2834
527.0 IPS |
|
Image Segmentation (SP)
|
100% |
3870
62.7 IPS |
|
Image Segmentation (HP)
|
100% |
4660
75.5 IPS |
|
Image Segmentation (Q)
|
98% |
3094
50.3 IPS |
|
Pose Estimation (SP)
|
100% |
42634
49.7 IPS |
|
Pose Estimation (HP)
|
100% |
71262
83.2 IPS |
|
Pose Estimation (Q)
|
96% |
30131
35.3 IPS |
|
Object Detection (SP)
|
100% |
2845
225.7 IPS |
|
Object Detection (HP)
|
100% |
3872
307.2 IPS |
|
Object Detection (Q)
|
87% |
2619
210.4 IPS |
|
Face Detection (SP)
|
100% |
6031
71.7 IPS |
|
Face Detection (HP)
|
100% |
11485
136.5 IPS |
|
Face Detection (Q)
|
97% |
5154
61.4 IPS |
|
Depth Estimation (SP)
|
100% |
18136
139.7 IPS |
|
Depth Estimation (HP)
|
99% |
28509
219.6 IPS |
|
Depth Estimation (Q)
|
77% |
14153
113.5 IPS |
|
Style Transfer (SP)
|
100% |
67054
86.2 IPS |
|
Style Transfer (HP)
|
100% |
111742
143.6 IPS |
|
Style Transfer (Q)
|
98% |
44552
57.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
13134
485.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
21630
798.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
8517
315.4 IPS |
|
Text Classification (SP)
|
100% |
2335
3.12 KIPS |
|
Text Classification (HP)
|
100% |
3419
4.56 KIPS |
|
Text Classification (Q)
|
97% |
1699
2.28 KIPS |
|
Machine Translation (SP)
|
100% |
3136
54.0 IPS |
|
Machine Translation (HP)
|
100% |
3251
56.0 IPS |
|
Machine Translation (Q)
|
70% |
1641
30.8 IPS |