Upload Date | April 13 2025 08:00 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | AMD Ryzen AI 9 HX 370 w/ Radeon 890M |
System Information | |
---|---|
Operating System | EndeavourOS |
Model | AZW SER9 |
Motherboard | AZW SER9 |
CPU Information | |
---|---|
Name | AMD Ryzen AI 9 HX 370 w/ Radeon 890M |
Topology | 1 Processor, 12 Cores, 24 Threads |
Identifier | AuthenticAMD Family 26 Model 36 Stepping 0 |
Base Frequency | 5.16 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 23.06 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1163
216.3 IPS |
|
Image Classification (HP)
|
100% |
1207
224.6 IPS |
|
Image Classification (Q)
|
99% |
1220
227.5 IPS |
|
Image Segmentation (SP)
|
100% |
2112
34.2 IPS |
|
Image Segmentation (HP)
|
100% |
2126
34.5 IPS |
|
Image Segmentation (Q)
|
98% |
1121
18.2 IPS |
|
Pose Estimation (SP)
|
100% |
3000
3.50 IPS |
|
Pose Estimation (HP)
|
100% |
3001
3.50 IPS |
|
Pose Estimation (Q)
|
96% |
3749
4.39 IPS |
|
Object Detection (SP)
|
100% |
1284
101.9 IPS |
|
Object Detection (HP)
|
100% |
1272
100.9 IPS |
|
Object Detection (Q)
|
85% |
1334
107.4 IPS |
|
Face Detection (SP)
|
100% |
2785
33.1 IPS |
|
Face Detection (HP)
|
100% |
2740
32.6 IPS |
|
Face Detection (Q)
|
97% |
2716
32.4 IPS |
|
Depth Estimation (SP)
|
100% |
2520
19.4 IPS |
|
Depth Estimation (HP)
|
99% |
2538
19.6 IPS |
|
Depth Estimation (Q)
|
63% |
2322
21.8 IPS |
|
Style Transfer (SP)
|
100% |
3828
4.92 IPS |
|
Style Transfer (HP)
|
100% |
3865
4.97 IPS |
|
Style Transfer (Q)
|
98% |
6988
9.01 IPS |
|
Image Super-Resolution (SP)
|
100% |
1402
51.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
1405
51.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
1877
69.5 IPS |
|
Text Classification (SP)
|
100% |
1421
1.90 KIPS |
|
Text Classification (HP)
|
100% |
1457
1.94 KIPS |
|
Text Classification (Q)
|
92% |
664
892.1 IPS |
|
Machine Translation (SP)
|
100% |
2884
49.7 IPS |
|
Machine Translation (HP)
|
100% |
2830
48.7 IPS |
|
Machine Translation (Q)
|
58% |
697
16.4 IPS |