README.md 1.9 KB
Newer Older
sunxx1's avatar
sunxx1 committed
1
2
# SeResnet50

sunxx1's avatar
sunxx1 committed
3
4
5
6
7
8
## 论文

Squeeze-and-Excitation Networks

- https://arxiv.org/pdf/1709.01507.pdf

sunxx1's avatar
sunxx1 committed
9
10
11
12
## 模型介绍

SE-ResNet50是一种基于残差网络(ResNet)和注意力机制(SE)的深度卷积神经网络模型,是由微软亚洲研究院提出的,是一种高效、快速、准确的图像分类模型,具有广泛的应用前景。

sunxx1's avatar
sunxx1 committed
13
![20231124110818](./images/20231124110818.png)
sunxx1's avatar
sunxx1 committed
14

sunxx1's avatar
sunxx1 committed
15
## 模型结构
sunxx1's avatar
sunxx1 committed
16

sunxx1's avatar
sunxx1 committed
17
Seresnet50的整体结构包括基础网络部分和Squeeze-and-Excitation(SE)模块。
sunxx1's avatar
sunxx1 committed
18

sunxx1's avatar
sunxx1 committed
19
![20231124111112](./images/20231124111112.png)
sunxx1's avatar
sunxx1 committed
20

sunxx1's avatar
sunxx1 committed
21
## 环境配置
sunxx1's avatar
sunxx1 committed
22

sunxx1's avatar
sunxx1 committed
23
### Docker
sunxx1's avatar
sunxx1 committed
24

sunxx1's avatar
sunxx1 committed
25
26
27
28
29
```python
git clone --recursive http://developer.hpccube.com/codes/modelzoo/seresnet50_mmcv.git
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:1.10.0-centos7.6-dtk-22.10.1-py37-latest
# <your IMAGE ID>用以上拉取的docker的镜像ID替换
docker run --shm-size 10g --network=host --name=nit-pytorch --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $PWD/Seresnet50_mmcv :/home/Seresnet50_mmcv -it <your IMAGE ID> bash
sunxx1's avatar
sunxx1 committed
30

sunxx1's avatar
sunxx1 committed
31
32
33
cd Seresnet50_mmcv/mmclassification-mmcv
pip install -r requirements.txt
```
sunxx1's avatar
sunxx1 committed
34
35
36
37
38

## 数据集

在本测试中可以使用ImageNet数据集。

sunxx1's avatar
sunxx1 committed
39
40
41
42
43
```
├── meta
├── train
├── val
```
sunxx1's avatar
sunxx1 committed
44
45
46
47
48

### 训练

将训练数据解压到data目录下。

sunxx1's avatar
sunxx1 committed
49
### 单机8卡
sunxx1's avatar
sunxx1 committed
50
51
52

    ./seresnet50.sh

sunxx1's avatar
sunxx1 committed
53
## 精度
sunxx1's avatar
sunxx1 committed
54
55
56

测试数据使用的是ImageNet数据集,使用的加速卡是DCU Z100L。

sunxx1's avatar
sunxx1 committed
57
58
59
60
| 卡数 |          精度           |
| :--: | :---------------------: |
|  8   | top1:0.7754;top5:0.9373 |

sunxx1's avatar
sunxx1 committed
61
62
63
64
65
66
67
68
69
70
71
72
73
74
## result

![img](https://developer.hpccube.com/codes/modelzoo/vit_pytorch/-/raw/master/image/README/1695381570003.png)

## 应用场景

### 算法类别

图像分类

### 热点行业

制造,能源,交通,网安

sunxx1's avatar
sunxx1 committed
75
### 源码仓库及问题反馈
sunxx1's avatar
sunxx1 committed
76

sunxx1's avatar
sunxx1 committed
77
https://developer.hpccube.com/codes/modelzoo/seresnet50_mmcv
sunxx1's avatar
sunxx1 committed
78
79
80
81

### 参考

https://github.com/open-mmlab/mmpretrain