User | Zztony |
Upload Date | February 08 2025 06:39 PM |
Views | 4 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA Quadro M1200 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Dell Inc. Precision 5520 |
Motherboard | Dell Inc. 0R6JFH |
Power Plan | Balansert |
CPU Information | |
---|---|
Name | Intel Core i7-7820HQ |
Topology | 1 Processor, 4 Cores, 8 Threads |
Identifier | GenuineIntel Family 6 Model 158 Stepping 9 |
Base Frequency | 2.90 GHz |
Cluster 1 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
796
148.0 IPS |
|
Image Classification (HP)
|
100% |
776
144.3 IPS |
|
Image Classification (Q)
|
100% |
649
120.7 IPS |
|
Image Segmentation (SP)
|
100% |
1186
19.2 IPS |
|
Image Segmentation (HP)
|
100% |
1191
19.3 IPS |
|
Image Segmentation (Q)
|
98% |
968
15.7 IPS |
|
Pose Estimation (SP)
|
100% |
6282
7.33 IPS |
|
Pose Estimation (HP)
|
100% |
6123
7.14 IPS |
|
Pose Estimation (Q)
|
97% |
5698
6.67 IPS |
|
Object Detection (SP)
|
100% |
1017
80.6 IPS |
|
Object Detection (HP)
|
100% |
1007
79.9 IPS |
|
Object Detection (Q)
|
89% |
791
63.4 IPS |
|
Face Detection (SP)
|
100% |
1715
20.4 IPS |
|
Face Detection (HP)
|
100% |
1749
20.8 IPS |
|
Face Detection (Q)
|
97% |
1340
16.0 IPS |
|
Depth Estimation (SP)
|
100% |
3827
29.5 IPS |
|
Depth Estimation (HP)
|
99% |
3748
29.0 IPS |
|
Depth Estimation (Q)
|
75% |
3029
24.4 IPS |
|
Style Transfer (SP)
|
100% |
10874
14.0 IPS |
|
Style Transfer (HP)
|
100% |
10880
14.0 IPS |
|
Style Transfer (Q)
|
98% |
9749
12.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3204
118.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
3050
112.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
2311
85.6 IPS |
|
Text Classification (SP)
|
100% |
823
1.10 KIPS |
|
Text Classification (HP)
|
100% |
849
1.13 KIPS |
|
Text Classification (Q)
|
97% |
423
566.3 IPS |
|
Machine Translation (SP)
|
100% |
1472
25.4 IPS |
|
Machine Translation (HP)
|
96% |
1408
24.3 IPS |
|
Machine Translation (Q)
|
60% |
551
12.3 IPS |