Shuyang Sun*, Runjia Li*, Philip Torr, Xiuye Gu, Siyang Li
The code is fully released at Google Research.
The README doc is currently under development.
- Anaconda 3
- PyTorch ≥ 1.7 and torchvision that matches the PyTorch installation. Install them together at pytorch.org to make sure of this.
conda env create --name ENV_NAME --file=car_env.yml
We have set up an online demo. You can check it out at: TODO
If you want to test an image locally, you can simply run
python3 demo.py --cfg-path=YOUR_CFG_PATH --output_path=SAVE_PATH
- Data preparation: See Preparing Datasets for CaR
- Evaluate:
python3 evaluate.py --cfg-path=CFG_PATH
You can find configs for each dataset underconfigs
.
@inproceedings{clip_as_rnn,
title = {CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor},
author = {Sun, Shuyang and Li, Runjia and Torr, Philip and Gu, Xiuye and Li, Siyang},
year = {2024},
booktitle = {CVPR},
}