| Upload Date | February 03 2025 02:14 AM |
| Views | 18 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Intel Xeon E5-2630 v2 |
| System Information | |
|---|---|
| Operating System | Ubuntu 24.04.1 LTS |
| Model | Dell Inc. Precision T5610 |
| Motherboard | Dell Inc. 0WN7Y6 |
| CPU Information | |
|---|---|
| Name | Intel Xeon E5-2630 v2 |
| Topology | 2 Processors, 12 Cores, 24 Threads |
| Identifier | GenuineIntel Family 6 Model 62 Stepping 4 |
| Base Frequency | 3.10 GHz |
| Cluster 1 | 0 Cores |
| Memory Information | |
|---|---|
| Size | 125.83 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
7
1.37 IPS |
|
|
Image Classification (HP)
|
100% |
7
1.29 IPS |
|
|
Image Classification (Q)
|
97% |
5
1.03 IPS |
|
|
Image Segmentation (SP)
|
100% |
12
0.20 IPS |
|
|
Image Segmentation (HP)
|
100% |
12
0.20 IPS |
|
|
Image Segmentation (Q)
|
98% |
10
0.16 IPS |
|
|
Pose Estimation (SP)
|
100% |
20
0.02 IPS |
|
|
Pose Estimation (HP)
|
100% |
19
0.02 IPS |
|
|
Pose Estimation (Q)
|
96% |
21
0.02 IPS |
|
|
Object Detection (SP)
|
100% |
10
0.81 IPS |
|
|
Object Detection (HP)
|
100% |
10
0.82 IPS |
|
|
Object Detection (Q)
|
87% |
9
0.69 IPS |
|
|
Face Detection (SP)
|
100% |
38
0.45 IPS |
|
|
Face Detection (HP)
|
100% |
33
0.39 IPS |
|
|
Face Detection (Q)
|
97% |
26
0.31 IPS |
|
|
Depth Estimation (SP)
|
100% |
23
0.18 IPS |
|
|
Depth Estimation (HP)
|
99% |
23
0.18 IPS |
|
|
Depth Estimation (Q)
|
64% |
16
0.15 IPS |
|
|
Style Transfer (SP)
|
100% |
68
0.09 IPS |
|
|
Style Transfer (HP)
|
100% |
76
0.10 IPS |
|
|
Style Transfer (Q)
|
98% |
73
0.09 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
19
0.69 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
19
0.69 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
15
0.55 IPS |
|
|
Text Classification (SP)
|
100% |
18
24.0 IPS |
|
|
Text Classification (HP)
|
100% |
19
25.5 IPS |
|
|
Text Classification (Q)
|
91% |
12
16.6 IPS |
|
|
Machine Translation (SP)
|
100% |
34
0.59 IPS |
|
|
Machine Translation (HP)
|
100% |
76
1.31 IPS |
|
|
Machine Translation (Q)
|
58% |
36
0.87 IPS |