ML_GCN
所属分类:数值算法/人工智能
开发工具:Python
文件大小:138KB
下载次数:3
上传日期:2020-03-20 12:45:22
上 传 者:
qqqzzzz
说明: 基于多标签的目标检测,与传统的木匾检测算法不同,最后实现分类
(The target detection based on multi label is different from the traditional algorithm of wooden plaque detection. Finally, the classification is realized)
文件列表:
.DS_Store (6148, 2019-08-28)
__init__.py (0, 2019-08-28)
checkpoint (0, 2019-10-13)
checkpoint\.DS_Store (6148, 2019-08-28)
checkpoint\coco (0, 2019-10-13)
checkpoint\coco\.DS_Store (6148, 2019-08-28)
checkpoint\voc (0, 2019-10-13)
checkpoint\voc\.DS_Store (6148, 2019-08-28)
coco.py (5133, 2019-08-28)
data (0, 2019-10-13)
data\.DS_Store (6148, 2019-08-28)
data\coco (0, 2019-10-13)
data\coco\coco_adj.pkl (52065, 2019-08-28)
data\coco\coco_glove_word2vec.pkl (96161, 2019-08-28)
data\voc (0, 2019-10-13)
data\voc\voc_adj.pkl (3582, 2019-08-28)
data\voc\voc_glove_word2vec.pkl (24161, 2019-08-28)
demo_coco_gcn.py (3622, 2019-08-28)
demo_voc2007_gcn.py (3479, 2019-08-28)
engine.py (18975, 2019-08-28)
models.py (3100, 2019-08-28)
util.py (11715, 2019-08-28)
voc.py (9007, 2019-08-28)
# ML_GCN.pytorch
PyTorch implementation of [Multi-Label Image Recognition with Graph Convolutional Networks](https://arxiv.org/abs/1904.03582), CVPR 2019.
### Requirements
Please, install the following packages
- numpy
- torch-0.3.1
- torchnet
- torchvision-0.2.0
- tqdm
### Download pretrain models
checkpoint/coco ([GoogleDrive](https://drive.google.com/open?id=1ivLi1Rc-dCUmN1ProcMk76zxF1DSvlIk))
checkpoint/voc ([GoogleDrive](https://drive.google.com/open?id=1lhbmW5g-Mo9KgI07nmc1kwSbEnb6t-YA))
or
[Baidu](https://pan.baidu.com/s/17j3lTjMRmXvWHT86zhaaVA)
### Options
- `lr`: learning rate
- `lrp`: factor for learning rate of pretrained layers. The learning rate of the pretrained layers is `lr * lrp`
- `batch-size`: number of images per batch
- `image-size`: size of the image
- `epochs`: number of training epochs
- `evaluate`: evaluate model on validation set
- `resume`: path to checkpoint
### Demo VOC 2007
```sh
python3 demo_voc2007_gcn.py data/voc --image-size 448 --batch-size 32 -e --resume checkpoint/voc/voc_checkpoint.pth.tar
```
### Demo COCO 2014
```sh
python3 demo_coco_gcn.py data/coco --image-size 448 --batch-size 32 -e --resume checkpoint/coco/coco_checkpoint.pth.tar
```
## Citing this repository
If you find this code useful in your research, please consider citing us:
```
@inproceedings{ML_GCN_CVPR_2019,
author = {Zhao-Min, Chen and Xiu-Shen, Wei and Peng, Wang and Yanwen, Guo},
title = {{Multi-Label Image Recognition with Graph Convolutional Networks}},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019}
}
```
## Reference
This project is based on https://github.com/durandtibo/wildcat.pytorch
## Tips
If you have any questions about our work, please do not hesitate to contact us by emails.
近期下载者:
相关文件:
收藏者: