Upload Date | August 26 2025 08:44 AM |
Views | 6 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | AMD Radeon 780M Graphics |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | GEEKOM A8 |
Motherboard | Default string A8 |
Power Plan | Balanced |
CPU Information | |
---|---|
Name | AMD Ryzen 9 8945HS |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 25 Model 117 Stepping 2 |
Base Frequency | 4.00 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2500
464.9 IPS |
|
Image Classification (HP)
|
100% |
4993
928.6 IPS |
|
Image Classification (Q)
|
100% |
2299
427.6 IPS |
|
Image Segmentation (SP)
|
100% |
4065
65.9 IPS |
|
Image Segmentation (HP)
|
100% |
4985
80.8 IPS |
|
Image Segmentation (Q)
|
98% |
3312
53.9 IPS |
|
Pose Estimation (SP)
|
100% |
42284
49.3 IPS |
|
Pose Estimation (HP)
|
100% |
74137
86.5 IPS |
|
Pose Estimation (Q)
|
96% |
30396
35.6 IPS |
|
Object Detection (SP)
|
100% |
2568
203.7 IPS |
|
Object Detection (HP)
|
100% |
3516
278.9 IPS |
|
Object Detection (Q)
|
87% |
2402
192.9 IPS |
|
Face Detection (SP)
|
100% |
6099
72.5 IPS |
|
Face Detection (HP)
|
100% |
10850
128.9 IPS |
|
Face Detection (Q)
|
97% |
4996
59.6 IPS |
|
Depth Estimation (SP)
|
100% |
17188
132.4 IPS |
|
Depth Estimation (HP)
|
99% |
26672
205.5 IPS |
|
Depth Estimation (Q)
|
77% |
13314
106.8 IPS |
|
Style Transfer (SP)
|
100% |
72336
93.0 IPS |
|
Style Transfer (HP)
|
100% |
114982
147.8 IPS |
|
Style Transfer (Q)
|
98% |
47333
61.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
12009
443.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
21493
793.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
8102
300.0 IPS |
|
Text Classification (SP)
|
100% |
2598
3.47 KIPS |
|
Text Classification (HP)
|
100% |
2878
3.84 KIPS |
|
Text Classification (Q)
|
97% |
1814
2.43 KIPS |
|
Machine Translation (SP)
|
100% |
3066
52.8 IPS |
|
Machine Translation (HP)
|
100% |
3139
54.1 IPS |
|
Machine Translation (Q)
|
70% |
1647
30.9 IPS |