User | Dee_Ment |
Upload Date | January 22 2025 01:35 PM |
Views | 1 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 2080 Ti |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Home (64-bit) |
Model | AB350 Pro4 |
Motherboard | ASRock AB350 Pro4 |
Power Plan | AMD Ryzen High Performance |
CPU Information | |
---|---|
Name | AMD Ryzen 9 3950X |
Topology | 1 Processor, 16 Cores, 32 Threads |
Identifier | AuthenticAMD Family 23 Model 113 Stepping 0 |
Base Frequency | 3.50 GHz |
Cluster 1 | 16 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7272
1.35 KIPS |
|
Image Classification (HP)
|
100% |
10057
1.87 KIPS |
|
Image Classification (Q)
|
99% |
5116
954.3 IPS |
|
Image Segmentation (SP)
|
100% |
10362
168.0 IPS |
|
Image Segmentation (HP)
|
100% |
13259
214.9 IPS |
|
Image Segmentation (Q)
|
98% |
8093
131.6 IPS |
|
Pose Estimation (SP)
|
100% |
95367
111.3 IPS |
|
Pose Estimation (HP)
|
100% |
277368
323.6 IPS |
|
Pose Estimation (Q)
|
96% |
77051
90.3 IPS |
|
Object Detection (SP)
|
100% |
8719
691.6 IPS |
|
Object Detection (HP)
|
100% |
12164
964.9 IPS |
|
Object Detection (Q)
|
85% |
6365
512.4 IPS |
|
Face Detection (SP)
|
100% |
20812
247.3 IPS |
|
Face Detection (HP)
|
100% |
29311
348.3 IPS |
|
Face Detection (Q)
|
97% |
15760
187.9 IPS |
|
Depth Estimation (SP)
|
100% |
46372
357.3 IPS |
|
Depth Estimation (HP)
|
99% |
72670
559.9 IPS |
|
Depth Estimation (Q)
|
77% |
29257
234.4 IPS |
|
Style Transfer (SP)
|
100% |
186456
239.7 IPS |
|
Style Transfer (HP)
|
100% |
393484
505.8 IPS |
|
Style Transfer (Q)
|
98% |
139244
179.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
28555
1.05 KIPS |
|
Image Super-Resolution (HP)
|
100% |
36633
1.35 KIPS |
|
Image Super-Resolution (Q)
|
99% |
16248
601.6 IPS |
|
Text Classification (SP)
|
100% |
1912
2.55 KIPS |
|
Text Classification (HP)
|
99% |
3022
4.03 KIPS |
|
Text Classification (Q)
|
97% |
1130
1.51 KIPS |
|
Machine Translation (SP)
|
100% |
3086
53.2 IPS |
|
Machine Translation (HP)
|
100% |
3039
52.3 IPS |
|
Machine Translation (Q)
|
70% |
1310
24.6 IPS |