Upload Date | August 13 2024 04:23 AM |
Views | 6 |
AI Information | |
---|---|
Framework | ONNX |
Backend | CPU |
Device | AMD Ryzen 7 2700X |
System Information | |
---|---|
Operating System | Microsoft Windows 10 Pro (64-bit) |
Model | Dell Inc. Inspiron 5676 |
Motherboard | Dell Inc. 0VYXHD |
Power Plan | Dell |
CPU Information | |
---|---|
Name | AMD Ryzen 7 2700X |
Topology | 1 Processor, 8 Cores, 16 Threads |
Identifier | AuthenticAMD Family 23 Model 8 Stepping 2 |
Base Frequency | 3.70 GHz |
Cluster 1 | 8 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
892
165.8 IPS |
|
Image Classification (HP)
|
100% |
98
18.2 IPS |
|
Image Classification (Q)
|
97% |
1082
202.0 IPS |
|
Image Segmentation (SP)
|
100% |
778
12.6 IPS |
|
Image Segmentation (HP)
|
100% |
155
2.52 IPS |
|
Image Segmentation (Q)
|
97% |
1045
17.0 IPS |
|
Pose Estimation (SP)
|
100% |
3172
3.70 IPS |
|
Pose Estimation (HP)
|
100% |
2631
3.07 IPS |
|
Pose Estimation (Q)
|
87% |
3045
3.60 IPS |
|
Object Detection (SP)
|
100% |
1002
79.5 IPS |
|
Object Detection (HP)
|
100% |
131
10.4 IPS |
|
Object Detection (Q)
|
86% |
761
61.2 IPS |
|
Face Detection (SP)
|
100% |
1369
16.3 IPS |
|
Face Detection (HP)
|
100% |
206
2.45 IPS |
|
Face Detection (Q)
|
96% |
1949
23.2 IPS |
|
Depth Estimation (SP)
|
100% |
3337
25.7 IPS |
|
Depth Estimation (HP)
|
99% |
612
4.71 IPS |
|
Depth Estimation (Q)
|
76% |
2628
21.2 IPS |
|
Style Transfer (SP)
|
100% |
7836
10.1 IPS |
|
Style Transfer (HP)
|
100% |
6796
8.74 IPS |
|
Style Transfer (Q)
|
87% |
6540
8.51 IPS |
|
Image Super-Resolution (SP)
|
100% |
1203
44.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
1155
42.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1105
40.9 IPS |
|
Text Classification (SP)
|
100% |
659
879.9 IPS |
|
Text Classification (HP)
|
100% |
358
478.4 IPS |
|
Text Classification (Q)
|
97% |
297
398.0 IPS |
|
Machine Translation (SP)
|
100% |
1049
18.1 IPS |
|
Machine Translation (HP)
|
100% |
390
6.72 IPS |
|
Machine Translation (Q)
|
60% |
949
21.2 IPS |