This is the official PyTorch implementation of the paper Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks.
- Preparation
- Training VQVAE and VQGAN
- Training Txt2Img-MHN
- Image Generation
- Inception Score and FID Score
- CLIP Score
- Zero-Shot Classification
- Paper
- Acknowledgement
- License
- Install required packages:
pip install -r requirements.txt - Install Taming Transformers:
- Download the repo
- Run
pip install -e . - Copy the files in the folder
taming-transformers-masterfrom this repo to the downloadedtaming-transformers-masterfolder
- Download the remote sensing text-image dataset RSICD used in this repo
- Extract separate
.txtfiles for the text descriptions of each image in RSICD:python data_preparation.py - Data folder structure:
├── RSICD/
│ ├── airport_1.jpg
│ ├── airport_2.jpg
│ ├── ...
│ ├── viaduct_420.jpg
│ ├── airport_1.txt
│ ├── airport_2.txt
│ ├── ...
│ ├── viaduct_420.txt
- Train VQVAE:
$ cd Txt2Img-MHN-main
$ CUDA_VISIBLE_DEVICES=0 python train_vqvae.py --data_dir /Path/To/RSICD/
- Train VQGAN:
$ cd taming-transformers-master
$ CUDA_VISIBLE_DEVICES=0 python main.py --base configs/custom_vqgan.yaml -t True --gpus 0,
- Train Txt2Img-MHN with the pretrained VQVAE:
$ cd Txt2Img-MHN-main
$ CUDA_VISIBLE_DEVICES=0 python train_txt2img_mhn.py --vae_type 0 --data_dir /Path/To/RSICD/ --vqvae_path /Path/To/vae.pth --batch_size 8
- Train Txt2Img-MHN with the pretrained VQGAN:
$ cd Txt2Img-MHN-main
$ CUDA_VISIBLE_DEVICES=0 python train_txt2img_mhn.py --vae_type 1 --data_dir /Path/To/RSICD/ --vqgan_model_path /Path/To/last.ckpt --vqgan_config_path /Path/To/project.yaml --batch_size 8
Note: Training with multiple GPUs is supported. Simply specify the GPU ids with CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7,...
- Use tensorboard to monitor the training process:
$ cd Txt2Img-MHN-main
$ tensorboard --logdir ./ --samples_per_plugin images=100
- Txt2Img-MHN (VQVAE):
$ cd Txt2Img-MHN-main
$ CUDA_VISIBLE_DEVICES=0 python gen_im.py --vae_type 0 --data_dir /Path/To/RSICD/ --vqvae_path /Path/To/vae.pth --mhn_vqvae_path /Path/To/mhn_vqvae.pth --num_gen_per_image 10
- Txt2Img-MHN (VQGAN):
$ cd Txt2Img-MHN-main
$ CUDA_VISIBLE_DEVICES=0 python gen_im.py --vae_type 1 --data_dir /Path/To/RSICD/ --vqgan_model_path /Path/To/last.ckpt --vqgan_config_path /Path/To/project.yaml --mhn_vqgan_path /Path/To/mhn_vqgan.pth --num_gen_per_image 10
Alternatively, you can download our pretrained models for a quick look.
- Txt2Img-MHN (VQVAE): Google Drive Baidu NetDisk (Code: u14r)
- Txt2Img-MHN (VQGAN): Google Drive Baidu NetDisk (Code: pt68)
- Data preparation: Before training the Inception model, prepare a new data folder with the structure below:
├── RSICD_cls/
│ ├── airport/
| | ├── airport_1.jpg
| | ├── airport_2.jpg
| | ├── ...
│ ├── bareland/
| | ├── bareland_1.jpg
| | ├── bareland_2.jpg
| | ├── ...
│ ├── ...
│ ├── viaduct/
| | ├── viaduct_1.jpg
| | ├── viaduct_2.jpg
| | ├── ...
- Pretrain the Inception model:
$ cd Txt2Img-MHN-main/is_fid_score
$ CUDA_VISIBLE_DEVICES=0 python pretrain_inception.py --root_dir /Path/To/RSICD_cls/
- Calculate the Inception score and FID score:
$ cd Txt2Img-MHN-main/is_fid_score
$ CUDA_VISIBLE_DEVICES=0 python is_fid_score.py --gen_dir /Path/To/GenImgFolder/ --data_dir /Path/To/RSICD/
- Calculate the CLIP score with the CLIP model fine-tuned on the RSICD dataset:
$ cd Txt2Img-MHN-main
$ CUDA_VISIBLE_DEVICES=0 python clip_score.py --gen_dir /Path/To/GenImgFolder/ --data_dir /Path/To/RSICD/
$ cd Txt2Img-MHN-main/zero_shot_classification
$ CUDA_VISIBLE_DEVICES=0 python zero_shot_evaluation.py --gen_dir /Path/To/GenImgFolder/ --root_dir /Path/To/RSICD/
Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
Please cite the following paper if you find it useful for your research:
@article{txt2img_mhn,
title={Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks},
author={Xu, Yonghao and Yu, Weikang and Ghamisi, Pedram and Kopp, Michael and Hochreiter, Sepp},
journal={IEEE Trans. Image Process.},
doi={10.1109/TIP.2023.3323799},
year={2023}
}
This research has been conducted at the Institute of Advanced Research in Artificial Intelligence (IARAI).
This repo is distributed under MIT License. The code can be used for academic purposes only.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent