Upload Date | January 11 2024 04:43 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | ASUS System Product Name |
Motherboard | ASUSTeK COMPUTER INC. ROG CROSSHAIR VI HERO (WI-FI AC) |
Power Plan | 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 |
L1 Instruction Cache | 32.0 KB x 16 |
L1 Data Cache | 32.0 KB x 16 |
L2 Cache | 512 KB x 16 |
L3 Cache | 16.0 MB x 4 |
Memory Information | |
---|---|
Size | 32.00 GB |
Inference Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 3090 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
8028
1.50 KIPS |
|
Image Classification (F16)
|
100% |
8189
1.53 KIPS |
|
Image Classification (I8)
|
100% |
5518
1.03 KIPS |
|
Image Segmentation (F32)
|
100% |
10951
182.9 IPS |
|
Image Segmentation (F16)
|
100% |
10816
180.6 IPS |
|
Image Segmentation (I8)
|
98% |
8554
142.9 IPS |
|
Pose Estimation (F32)
|
100% |
158901
192.4 IPS |
|
Pose Estimation (F16)
|
100% |
160688
194.6 IPS |
|
Pose Estimation (I8)
|
100% |
117758
142.6 IPS |
|
Object Detection (F32)
|
100% |
4487
335.0 IPS |
|
Object Detection (F16)
|
100% |
4486
334.9 IPS |
|
Object Detection (I8)
|
56% |
3741
279.3 IPS |
|
Face Detection (F32)
|
100% |
23480
279.2 IPS |
|
Face Detection (F16)
|
100% |
24322
289.2 IPS |
|
Face Detection (I8)
|
89% |
16904
201.0 IPS |
|
Depth Estimation (F32)
|
100% |
54045
419.1 IPS |
|
Depth Estimation (F16)
|
100% |
50042
388.1 IPS |
|
Depth Estimation (I8)
|
95% |
32529
252.3 IPS |
|
Style Transfer (F32)
|
100% |
247038
325.0 IPS |
|
Style Transfer (F16)
|
100% |
232298
305.6 IPS |
|
Style Transfer (I8)
|
98% |
165627
217.9 IPS |
|
Image Super-Resolution (F32)
|
100% |
31682
1.13 KIPS |
|
Image Super-Resolution (F16)
|
100% |
31695
1.13 KIPS |
|
Image Super-Resolution (I8)
|
99% |
19068
681.0 IPS |
|
Text Classification (F32)
|
100% |
2215
3.18 KIPS |
|
Text Classification (F16)
|
100% |
2263
3.25 KIPS |
|
Text Classification (I8)
|
98% |
1221
1.75 KIPS |
|
Machine Translation (F32)
|
100% |
3109
57.2 IPS |
|
Machine Translation (F16)
|
100% |
3071
56.5 IPS |
|
Machine Translation (I8)
|
70% |
1507
27.7 IPS |