| User | Imro74 |
| Upload Date | December 21 2024 03:02 PM |
| Views | 21 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Intel Core i7-720QM |
| System Information | |
|---|---|
| Operating System | Debian GNU/Linux 12 (bookworm) |
| Model | ASUSTeK Computer Inc. G73Jh |
| Motherboard | ASUSTeK Computer Inc. G73Jh |
| CPU Information | |
|---|---|
| Name | Intel Core i7-720QM |
| Topology | 1 Processor, 4 Cores, 8 Threads |
| Identifier | GenuineIntel Family 6 Model 30 Stepping 5 |
| Base Frequency | 1.60 GHz |
| Cluster 1 | 0 Cores |
| Memory Information | |
|---|---|
| Size | 11.60 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
6
1.06 IPS |
|
|
Image Classification (HP)
|
100% |
6
1.06 IPS |
|
|
Image Classification (Q)
|
97% |
5
0.90 IPS |
|
|
Image Segmentation (SP)
|
100% |
8
0.13 IPS |
|
|
Image Segmentation (HP)
|
100% |
8
0.13 IPS |
|
|
Image Segmentation (Q)
|
98% |
7
0.11 IPS |
|
|
Pose Estimation (SP)
|
100% |
9
0.01 IPS |
|
|
Pose Estimation (HP)
|
100% |
9
0.01 IPS |
|
|
Pose Estimation (Q)
|
96% |
8
0.01 IPS |
|
|
Object Detection (SP)
|
100% |
6
0.44 IPS |
|
|
Object Detection (HP)
|
100% |
6
0.44 IPS |
|
|
Object Detection (Q)
|
87% |
5
0.37 IPS |
|
|
Face Detection (SP)
|
100% |
18
0.22 IPS |
|
|
Face Detection (HP)
|
100% |
18
0.22 IPS |
|
|
Face Detection (Q)
|
97% |
15
0.18 IPS |
|
|
Depth Estimation (SP)
|
100% |
13
0.10 IPS |
|
|
Depth Estimation (HP)
|
99% |
13
0.10 IPS |
|
|
Depth Estimation (Q)
|
64% |
9
0.09 IPS |
|
|
Style Transfer (SP)
|
100% |
28
0.04 IPS |
|
|
Style Transfer (HP)
|
100% |
28
0.04 IPS |
|
|
Style Transfer (Q)
|
98% |
24
0.03 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6
0.22 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6
0.22 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
5
0.19 IPS |
|
|
Text Classification (SP)
|
100% |
8
10.0 IPS |
|
|
Text Classification (HP)
|
100% |
8
10.0 IPS |
|
|
Text Classification (Q)
|
91% |
6
8.05 IPS |
|
|
Machine Translation (SP)
|
100% |
14
0.25 IPS |
|
|
Machine Translation (HP)
|
100% |
14
0.25 IPS |
|
|
Machine Translation (Q)
|
58% |
8
0.20 IPS |