Upload Date | April 13 2025 07:14 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | AMD Ryzen 9 3950X |
System Information | |
---|---|
Operating System | Pop!_OS 22.04 LTS |
Model | To Be Filled By O.E.M. To Be Filled By O.E.M. |
Motherboard | ASRock X470 Taichi |
CPU Information | |
---|---|
Name | AMD Ryzen 9 3950X |
Topology | 1 Processor, 16 Cores |
Identifier | AuthenticAMD Family 23 Model 113 Stepping 0 |
Base Frequency | 4.76 GHz |
Cluster 1 | 0 Cores |
Memory Information | |
---|---|
Size | 125.72 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
919
171.0 IPS |
|
Image Classification (HP)
|
100% |
925
172.0 IPS |
|
Image Classification (Q)
|
99% |
743
138.6 IPS |
|
Image Segmentation (SP)
|
100% |
1464
23.7 IPS |
|
Image Segmentation (HP)
|
100% |
1349
21.9 IPS |
|
Image Segmentation (Q)
|
98% |
966
15.7 IPS |
|
Pose Estimation (SP)
|
100% |
2239
2.61 IPS |
|
Pose Estimation (HP)
|
100% |
2228
2.60 IPS |
|
Pose Estimation (Q)
|
96% |
3273
3.83 IPS |
|
Object Detection (SP)
|
100% |
944
74.9 IPS |
|
Object Detection (HP)
|
100% |
931
73.9 IPS |
|
Object Detection (Q)
|
85% |
772
62.1 IPS |
|
Face Detection (SP)
|
100% |
1499
17.8 IPS |
|
Face Detection (HP)
|
100% |
1536
18.3 IPS |
|
Face Detection (Q)
|
97% |
1436
17.1 IPS |
|
Depth Estimation (SP)
|
100% |
1498
11.5 IPS |
|
Depth Estimation (HP)
|
99% |
1475
11.4 IPS |
|
Depth Estimation (Q)
|
63% |
1476
13.8 IPS |
|
Style Transfer (SP)
|
100% |
2471
3.18 IPS |
|
Style Transfer (HP)
|
100% |
2446
3.14 IPS |
|
Style Transfer (Q)
|
98% |
4861
6.27 IPS |
|
Image Super-Resolution (SP)
|
100% |
948
35.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
913
33.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1226
45.4 IPS |
|
Text Classification (SP)
|
100% |
821
1.10 KIPS |
|
Text Classification (HP)
|
100% |
821
1.10 KIPS |
|
Text Classification (Q)
|
92% |
497
667.0 IPS |
|
Machine Translation (SP)
|
100% |
1499
25.8 IPS |
|
Machine Translation (HP)
|
100% |
1429
24.6 IPS |
|
Machine Translation (Q)
|
58% |
453
10.6 IPS |