Byeonghyun Pak*, Byeongju Woo*, Sunghwan Kim*, Dae-hwan Kim, Hoseong Kim†\ Agency for Defense Development\ ECCV 2024
Project Page
] [Paper
]The requirements can be installed with:
conda create -n tqdm python=3.9 numpy=1.26.4
conda activate tqdm
conda install pytorch==2.0.1 torchvision==0.15.2 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install -r requirements.txt
pip install xformers==0.0.20
pip install mmcv-full==1.5.3
Please download the pre-trained CLIP and EVA02-CLIP and save them in ./pretrained
folder.
Model | Type | Link |
---|---|---|
CLIP | ViT-B-16.pt |
official repo |
EVA02-CLIP | EVA02_CLIP_L_336_psz14_s6B |
official repo |
You can download tqdm model checkpoints:
Model | Pretrained | Trained on | Config | Link |
---|---|---|---|---|
tqdm-clip-vit-b-gta |
CLIP | GTA5 | config | download link |
tqdm-eva02-clip-vit-l-gta |
EVA02-CLIP | GTA5 | config | download link |
tqdm-eva02-clip-vit-l-city |
EVA02-CLIP | Cityscapes | config | download link |
After downloading the datasets, edit the data folder root in the dataset config files following your environment.
src_dataset_dict = dict(..., data_root='[YOUR_DATA_FOLDER_ROOT]', ...)
tgt_dataset_dict = dict(..., data_root='[YOUR_DATA_FOLDER_ROOT]', ...)
bash dist_train.sh configs/[TRAIN_CONFIG] [NUM_GPUs]
[TRAIN_CONFIG]
: train configuration (e.g., tqdm/tqdm_eve_vit-l_1e-5_20k-g2c-512.py
)[NUM_GPUs]
: the number of the GPUs
bash dist_test.sh configs/[TEST_CONFIG] work_dirs/[MODEL] [NUM_GPUs] --eval mIoU
[TRAIN_CONFIG]
: test configuration (e.g., tqdm/tqdm_eve_vit-l_1e-5_20k-g2b-512.py
)[MODEL]
: model checkpoint (e.g., tqdm_eve_vit-l_1e-5_20k-g2c-512/epoch_last.pth
)[NUM_GPUs]
: the number of the GPUsIf you find our code helpful, please cite our paper:
@article{pak2024textual,
title = {Textual Query-Driven Mask Transformer for Domain Generalized Segmentation},
author = {Pak, Byeonghyun and Woo, Byeongju and Kim, Sunghwan and Kim, Dae-hwan and Kim, Hoseong},
journal = {arXiv preprint arXiv:2407.09033},
year = {2024}
}
This project is based on the following open-source projects. We thank the authors for sharing their codes.