Awesome
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
<img src="results.jpg" width="877px" height="379px"/><img src="fram.jpeg" width="952px" height="380px"/>
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.