# MMAL-Net
This is a PyTorch implementation of the paper ["Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization (MMAL-Net)"](https://arxiv.org/abs/2003.09150) (Fan Zhang, Meng Li, Guisheng Zhai, Yizhao Liu), and the paper has been accepted by the 27th International Conference on Multimedia Modeling (MMM2021). Welcome to discuss with us in issues!
![avatar](./network.png)
### Table of Contents
- <a href='#requirements'>Requirements</a>
- <a href='#datasets'>Datasets</a>
- <a href='#training L-Net'>Training MMAL-Net</a>
- <a href='#evaluation'>Evaluation</a>
- <a href='#model'>Model</a>
- <a href='#reference'>Reference</a>
## Requirements
- python 3.7
- pytorch 1.3.1
- numpy 1.17.3
- scikit-image 0.16.2
- Tensorboard 1.15.0
- TensorboardX 2.0
- tqdm 4.41.1
- imageio 2.6.1
- pillow 6.1.0
## Datasets
Download the [CUB-200-2011](http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz) datasets and copy the contents of the extracted **images** folder into **datasets/CUB 200-2011/images**.
Download the [FGVC-Aircraft](http://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/archives/fgvc-aircraft-2013b.tar.gz) datasets and copy the contents of the extracted **data/images** folder into **datasets/FGVC_Aircraft/data/images**)
You can also try other fine-grained datasets.
## Training TBMSL-Net
If you want to train the MMAL-Net, please download the pretrained model of [ResNet-50](https://drive.google.com/open?id=1raU0m3zA52dh5ayQc3kB-7Ddusa0lOT-) and move it to **models/pretrained** before run ``python train.py``. You may need to change the configurations in ``config.py`` if your GPU memory is not enough. The parameter ``N_list`` is ``N1, N2, N3`` in the original paper and you can adjust them according to GPU memory. During training, the log file and checkpoint file will be saved in ``model_path`` directory.
## Evaluation
If you want to test the MMAL-Net, just run ``python test.py``. You need to specify the ``model_path`` in ``test.py`` to choose the checkpoint model for testing.
## Model
We also provide the checkpoint model trained by ourselves, you can download if from [Google Drive](https://drive.google.com/open?id=13ANynWz7O3QK0RdL4KqASW8X_vMb6V4B) for **CUB-200-2011** or download from [here](https://drive.google.com/file/d/1-LD1Jz6Dh-P6Ibtl17scfrTFQTrW4Zy3/view?usp=sharing) for **FGVC-Aircraft**. If you test on our provided model, you will get 89.6% and 94.7% test accuracy, respectively.
## Reference
If you are interested in our work and want to cite it, please acknowledge the following paper:
```
@misc{zhang2020threebranch,
title={Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization},
author={Fan Zhang and Meng Li and Guisheng Zhai and Yizhao Liu},
year={2020},
eprint={2003.09150},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
没有合适的资源?快使用搜索试试~ 我知道了~
MMAL-Net:这是论文“用于细粒度视觉分类的多分支和多尺度注意力学习(MMAL-Net)”的PyTorch实施(张凡,李萌,...
共40个文件
py:15个
txt:13个
gitkeep:6个
需积分: 50 4 下载量 171 浏览量
2021-04-23
02:32:29
上传
评论 1
收藏 7.35MB ZIP 举报
温馨提示
MMAL网 这是论文用于细粒度的PyTorch实施(张帆,李萌,翟桂生,刘亦钊)由第27届国际多媒体建模国际会议(MMM2021)提供。 欢迎与我们讨论问题! 目录 要求 的Python 3.7 pytorch 1.3.1 numpy的1.17.3 scikit图像0.16.2 Tensorboard 1.15.0 TensorboardX 2.0 tqdm 4.41.1 图像2.6.1 枕头6.1.0 数据集 下载数据集,并将提取的图像文件夹的内容复制到datasets / CUB 200-2011 / images中。 下载数据集并将提取的data / images文件夹的内容复制到datasets / FGVC_Aircraft / data / images ) 您也可以尝试其他细粒度的数据集。 培训TBMSL-Net 如果要训练MMAL-Net,请在运行py
资源推荐
资源详情
资源评论
收起资源包目录
MMAL-Net-master.zip (40个子文件)
MMAL-Net-master
network.png 741KB
.gitignore 113B
envconfig
env_list.yml 2KB
torch.yml 2KB
datasets
Stanford_Cars
test.txt 106KB
cars_test
.gitkeep 72B
cars_train
.gitkeep 72B
train.txt 107KB
FGVC-aircraft
data
images
.gitkeep 72B
test.txt 49KB
train.txt 97KB
dataset.py 9KB
CUB_200_2011
parts
part_click_locs.txt 20.14MB
parts.txt 150B
part_locs.txt 3.46MB
image_class_labels.txt 98KB
images
.gitkeep 72B
classes.txt 5KB
images.txt 666KB
train_test_split.txt 81KB
bounding_boxes.txt 320KB
attributes.txt 9KB
README 6KB
networks
resnet.py 13KB
model.py 6KB
models
.gitkeep 72B
pretrained
.gitkeep 72B
utils
train_model.py 4KB
compute_window_nums.py 252B
indices2coordinates.py 975B
vis.py 2KB
eval_model.py 5KB
cal_iou.py 769B
AOLM.py 1KB
auto_laod_resume.py 1KB
read_dataset.py 2KB
README.md 3KB
config.py 2KB
test.py 2KB
train.py 2KB
共 40 条
- 1
资源评论
LinSha
- 粉丝: 13
- 资源: 4615
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- Picasso_v3.1 2.ipa
- chromedriver-mac-arm64.zip
- 蓝zapro.apk
- chromedriver-linux64.zip
- UCAS研一深度学习实验-MNIST手写数字识别python源码+详细注释(高分项目)
- 基于Python和PyTorch框架完成的一个手写数字识别实验源码(带MINIST手写数字数据集)+详细注释(高分项目)
- 基于Matlab在MNIST数据集上利用CNN完成手写体数字识别任务,并实现单层CNN反向传播算法+源代码+文档说明(高分项目)
- NVIDIA驱动、CUDA和Pytorch及其依赖
- 基于SVM多特征融合的微表情识别python源码+项目说明+详细注释(高分课程设计)
- html动态爱心代码一(附源码)
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功