de-net's Introduction

DE-Net

Official Pytorch implementation for our AAAI 2023 paper DE-Net: Dynamic Text-guided Image Editing Adversarial Networks by Ming Tao, Bing-Kun Bao, Hao Tang, Fei Wu, Longhui Wei, Qi Tian.

Samples

Requirements

python 3.8
Pytorch 1.9
At least 1x12GB NVIDIA GPU

Installation

Clone this repo.

git clone https://github.com/tobran/DE-Net
pip install -r requirements.txt
cd DE-Net/code/

Preparation

Datasets

Download the preprocessed metadata for birds coco and extract them to data/
Download the birds image data. Extract them to data/birds/
Download coco2014 dataset and extract the images to data/coco/images/

Training

cd DE-Net/code/

Train the DE-Net model

For bird dataset: bash scripts/train.sh ./cfg/bird.yml
For coco dataset: bash scripts/train.sh ./cfg/coco.yml

Resume training process

If your training process is interrupted unexpectedly, set resume_epoch and resume_model_path in train.sh to resume training.

de-net's People

Contributors

Stargazers

Watchers

de-net's Issues

Missing file when reproducing code

Hi, Ming Tao

Thx for presenting us your amazing work on text-guided image editting.

I found that the lib package was missing files, such as moduels and perpare files, while reproducing the code. I hope you can improve this code.Thanks.

When will the code be released?

Hi, Ming Tao

Thx for presenting us your amazing work on text-guided image editting.

I am interested in reprodcing the results in your paper. When do you plan to release your code for this project? It will help me a lot.

Can not find the code file 'perpare' in folder 'lib'

I can't find the code file ‘perpare’ 、‘modules’ and ‘datasets_clip’ in folder 'lib'. when I run this code, it report errors such as:
ModuleNotFoundError: No module named 'lib.perpare'.

Recommend Projects