| User | Imro74 |
| Upload Date | December 17 2024 05:24 PM |
| Views | 17 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Intel Core i3-3240 |
| System Information | |
|---|---|
| Operating System | Debian GNU/Linux 12 (bookworm) |
| Model | N/A |
| Motherboard | Intel Corporation DH67BL |
| CPU Information | |
|---|---|
| Name | Intel Core i3-3240 |
| Topology | 1 Processor, 2 Cores, 4 Threads |
| Identifier | GenuineIntel Family 6 Model 58 Stepping 9 |
| Base Frequency | 3.40 GHz |
| Cluster 1 | 0 Cores |
| Memory Information | |
|---|---|
| Size | 15.53 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
7
1.36 IPS |
|
|
Image Classification (HP)
|
100% |
7
1.36 IPS |
|
|
Image Classification (Q)
|
97% |
6
1.06 IPS |
|
|
Image Segmentation (SP)
|
100% |
10
0.16 IPS |
|
|
Image Segmentation (HP)
|
100% |
10
0.16 IPS |
|
|
Image Segmentation (Q)
|
98% |
8
0.12 IPS |
|
|
Pose Estimation (SP)
|
100% |
12
0.01 IPS |
|
|
Pose Estimation (HP)
|
100% |
12
0.01 IPS |
|
|
Pose Estimation (Q)
|
96% |
9
0.01 IPS |
|
|
Object Detection (SP)
|
100% |
7
0.56 IPS |
|
|
Object Detection (HP)
|
100% |
7
0.56 IPS |
|
|
Object Detection (Q)
|
87% |
5
0.44 IPS |
|
|
Face Detection (SP)
|
100% |
24
0.28 IPS |
|
|
Face Detection (HP)
|
100% |
24
0.28 IPS |
|
|
Face Detection (Q)
|
97% |
18
0.22 IPS |
|
|
Depth Estimation (SP)
|
100% |
17
0.13 IPS |
|
|
Depth Estimation (HP)
|
99% |
17
0.13 IPS |
|
|
Depth Estimation (Q)
|
64% |
11
0.10 IPS |
|
|
Style Transfer (SP)
|
100% |
36
0.05 IPS |
|
|
Style Transfer (HP)
|
100% |
36
0.05 IPS |
|
|
Style Transfer (Q)
|
98% |
28
0.04 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
8
0.28 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
8
0.28 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
6
0.22 IPS |
|
|
Text Classification (SP)
|
100% |
10
12.9 IPS |
|
|
Text Classification (HP)
|
100% |
10
12.9 IPS |
|
|
Text Classification (Q)
|
91% |
7
9.75 IPS |
|
|
Machine Translation (SP)
|
100% |
19
0.32 IPS |
|
|
Machine Translation (HP)
|
100% |
19
0.32 IPS |
|
|
Machine Translation (Q)
|
58% |
10
0.24 IPS |