Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
tjulitianyi 8c86c53dd3 | 2 years ago | |
---|---|---|
.idea | 3 years ago | |
checkpoint | 4 years ago | |
data | 3 years ago | |
.DS_Store | 4 years ago | |
README.md | 2 years ago | |
__init__.py | 4 years ago | |
coco.py | 4 years ago | |
demo_coco_gcn.py | 4 years ago | |
demo_voc2007_gcn.py | 2 years ago | |
engine.py | 2 years ago | |
models.py | 3 years ago | |
train_voc2007.sh | 2 years ago | |
util.py | 4 years ago | |
voc.py | 4 years ago |
PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.
Method | COCO | NUS-WIDE | VOC2007 |
---|---|---|---|
Res-101 GAP | 77.3 | 56.9 | 91.7 |
Res-101 GMP | 81.9 | 59.7 | 93.0 |
Ours | 83.0 | 62.5 | 94.0 |
Please, install the following packages
# 优先执行
pip3 install git+https://github.com/pytorch/tnt.git@master
# 如果GitHub无法访问,可执行如下命令
pip install torchnet
checkpoint/coco (GoogleDrive)
checkpoint/voc (GoogleDrive)
or
lr
: learning ratelrp
: factor for learning rate of pretrained layers. The learning rate of the pretrained layers is lr * lrp
batch-size
: number of images per batchimage-size
: size of the imageepochs
: number of training epochsevaluate
: evaluate model on validation setresume
: path to checkpointpython3 demo_voc2007_gcn.py data/voc --image-size 448 --batch-size 32 -e --resume checkpoint/voc/voc_checkpoint.pth.tar
python3 demo_coco_gcn.py data/coco --image-size 448 --batch-size 32 -e --resume checkpoint/coco/coco_checkpoint.pth.tar
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}
}
This project is based on https://github.com/durandtibo/wildcat.pytorch
If you have any questions about our work, please do not hesitate to contact us by emails.
Pickle Python SVG other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》