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

1. Download the preprocessed metadata for birds coco and extract them to data/
2. Download the birds image data. Extract them to data/birds/
3. 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.