Upload Date | August 23 2024 12:23 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Microsoft Windows 10 Home (64-bit) |
Model | System manufacturer System Product Name |
Motherboard | ASUSTeK COMPUTER INC. ROG STRIX B450-F GAMING |
Power Plan | AMD Ryzen High Performance |
CPU Information | |
---|---|
Name | AMD Ryzen 5 3600X |
Topology | 1 Processor, 6 Cores, 12 Threads |
Identifier | AuthenticAMD Family 23 Model 113 Stepping 0 |
Base Frequency | 3.80 GHz |
Cluster 1 | 6 Cores |
L1 Instruction Cache | 32.0 KB x 6 |
L1 Data Cache | 32.0 KB x 6 |
L2 Cache | 512 KB x 6 |
L3 Cache | 16.0 MB x 2 |
Memory Information | |
---|---|
Size | 16.00 GB |
Inference Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | Intel(R) Arc(TM) A770 Graphics |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4535
848.6 IPS |
|
Image Classification (F16)
|
100% |
4564
854.1 IPS |
|
Image Classification (I8)
|
99% |
3911
731.8 IPS |
|
Image Segmentation (F32)
|
100% |
6263
104.6 IPS |
|
Image Segmentation (F16)
|
100% |
6260
104.5 IPS |
|
Image Segmentation (I8)
|
98% |
5694
95.1 IPS |
|
Pose Estimation (F32)
|
100% |
83925
101.6 IPS |
|
Pose Estimation (F16)
|
100% |
83705
101.4 IPS |
|
Pose Estimation (I8)
|
100% |
67246
81.4 IPS |
|
Object Detection (F32)
|
100% |
3363
251.1 IPS |
|
Object Detection (F16)
|
100% |
3336
249.1 IPS |
|
Object Detection (I8)
|
60% |
3123
233.2 IPS |
|
Face Detection (F32)
|
100% |
14315
170.2 IPS |
|
Face Detection (F16)
|
100% |
14328
170.4 IPS |
|
Face Detection (I8)
|
88% |
11074
131.7 IPS |
|
Depth Estimation (F32)
|
100% |
28901
224.1 IPS |
|
Depth Estimation (F16)
|
100% |
28880
224.0 IPS |
|
Depth Estimation (I8)
|
95% |
24366
189.0 IPS |
|
Style Transfer (F32)
|
100% |
167284
220.0 IPS |
|
Style Transfer (F16)
|
100% |
166619
219.2 IPS |
|
Style Transfer (I8)
|
98% |
129944
170.9 IPS |
|
Image Super-Resolution (F32)
|
100% |
16500
589.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
16508
589.6 IPS |
|
Image Super-Resolution (I8)
|
99% |
12416
443.4 IPS |
|
Text Classification (F32)
|
90% |
749
1.08 KIPS |
|
Text Classification (F16)
|
90% |
755
1.09 KIPS |
|
Text Classification (I8)
|
90% |
593
852.3 IPS |
|
Machine Translation (F32)
|
100% |
1461
26.9 IPS |
|
Machine Translation (F16)
|
100% |
1465
27.0 IPS |
|
Machine Translation (I8)
|
70% |
1040
19.1 IPS |