The repository is organized around runnable experiment entrypoints rather than a single training framework. Each module can be used independently, and run.py provides a unified launcher. conda create ...
Clone repo and create conda environment (recommended). Then install requirements.txt in a Python>=3.8.0 environment, including PyTorch>=1.8. git clone https://github ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results