User | Shanness |
Upload Date | September 26 2025 02:25 PM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | AMD Ryzen AI 7 350 |
System Information | |
---|---|
Operating System | Ubuntu 25.04 |
Model | LENOVO 83JY |
Motherboard | LENOVO LNVNB161216 |
CPU Information | |
---|---|
Name | AMD Ryzen AI 7 350 |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 26 Model 96 Stepping 0 |
Base Frequency | 5.09 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 30.14 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2050
381.2 IPS |
|
Image Classification (HP)
|
100% |
2054
382.0 IPS |
|
Image Classification (Q)
|
99% |
1362
253.9 IPS |
|
Image Segmentation (SP)
|
100% |
2608
42.3 IPS |
|
Image Segmentation (HP)
|
100% |
2636
42.7 IPS |
|
Image Segmentation (Q)
|
98% |
1249
20.3 IPS |
|
Pose Estimation (SP)
|
100% |
2961
3.46 IPS |
|
Pose Estimation (HP)
|
100% |
3021
3.52 IPS |
|
Pose Estimation (Q)
|
96% |
3642
4.27 IPS |
|
Object Detection (SP)
|
100% |
1611
127.8 IPS |
|
Object Detection (HP)
|
100% |
1596
126.6 IPS |
|
Object Detection (Q)
|
85% |
1101
88.6 IPS |
|
Face Detection (SP)
|
100% |
3472
41.3 IPS |
|
Face Detection (HP)
|
100% |
3515
41.8 IPS |
|
Face Detection (Q)
|
97% |
3049
36.4 IPS |
|
Depth Estimation (SP)
|
100% |
3308
25.5 IPS |
|
Depth Estimation (HP)
|
99% |
3292
25.4 IPS |
|
Depth Estimation (Q)
|
63% |
2454
23.0 IPS |
|
Style Transfer (SP)
|
100% |
3990
5.13 IPS |
|
Style Transfer (HP)
|
100% |
4004
5.15 IPS |
|
Style Transfer (Q)
|
98% |
6712
8.65 IPS |
|
Image Super-Resolution (SP)
|
100% |
2355
86.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
2343
86.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
1952
72.3 IPS |
|
Text Classification (SP)
|
100% |
2652
3.54 KIPS |
|
Text Classification (HP)
|
100% |
2657
3.55 KIPS |
|
Text Classification (Q)
|
92% |
1002
1.35 KIPS |
|
Machine Translation (SP)
|
100% |
3426
59.0 IPS |
|
Machine Translation (HP)
|
100% |
3515
60.6 IPS |
|
Machine Translation (Q)
|
58% |
793
18.6 IPS |