User | PB7591 |
Upload Date | September 03 2025 03:28 AM |
Views | 5 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | Radeon (TM) Pro WX 9100 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Generic |
Motherboard | ASRock TRX40 Creator |
Power Plan | High performance |
CPU Information | |
---|---|
Name | AMD Ryzen Threadripper 3970X |
Topology | 1 Processor, 32 Cores, 64 Threads |
Identifier | AuthenticAMD Family 23 Model 49 Stepping 0 |
Base Frequency | 3.70 GHz |
Cluster 1 | 32 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4778
888.6 IPS |
|
Image Classification (HP)
|
100% |
5601
1.04 KIPS |
|
Image Classification (Q)
|
100% |
3914
727.8 IPS |
|
Image Segmentation (SP)
|
100% |
6429
104.2 IPS |
|
Image Segmentation (HP)
|
100% |
7490
121.4 IPS |
|
Image Segmentation (Q)
|
98% |
5560
90.4 IPS |
|
Pose Estimation (SP)
|
100% |
64701
75.5 IPS |
|
Pose Estimation (HP)
|
100% |
99966
116.6 IPS |
|
Pose Estimation (Q)
|
96% |
55950
65.5 IPS |
|
Object Detection (SP)
|
100% |
5613
445.2 IPS |
|
Object Detection (HP)
|
100% |
5623
446.0 IPS |
|
Object Detection (Q)
|
88% |
4574
366.7 IPS |
|
Face Detection (SP)
|
100% |
14652
174.1 IPS |
|
Face Detection (HP)
|
100% |
17127
203.5 IPS |
|
Face Detection (Q)
|
97% |
11928
142.2 IPS |
|
Depth Estimation (SP)
|
100% |
27845
214.5 IPS |
|
Depth Estimation (HP)
|
99% |
32511
250.5 IPS |
|
Depth Estimation (Q)
|
77% |
20840
166.9 IPS |
|
Style Transfer (SP)
|
100% |
129970
167.1 IPS |
|
Style Transfer (HP)
|
100% |
194978
250.6 IPS |
|
Style Transfer (Q)
|
98% |
106109
136.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
16455
607.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
19686
726.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
11588
429.1 IPS |
|
Text Classification (SP)
|
100% |
1506
2.01 KIPS |
|
Text Classification (HP)
|
100% |
1545
2.06 KIPS |
|
Text Classification (Q)
|
97% |
859
1.15 KIPS |
|
Machine Translation (SP)
|
100% |
2735
47.1 IPS |
|
Machine Translation (HP)
|
100% |
2845
49.0 IPS |
|
Machine Translation (Q)
|
70% |
1117
20.9 IPS |