Our blogpost can be found here.
Make virtual environment and install dependencies:
make setup_env
Source your virtual environment:
source .venv/bin/activate
Reproduce the training results from a given experiment:
python -m src.train experiment=wang2024/rgcnn_triple
cd ~/development/dl2
Let's say you want to run the experiment at configs/experiment/wang2022/equivariance_test/convnet.yaml
. You can make use of the shortcut slurmtrain
as follows:
make strain experiment=wang2022/equivariance_test/convnet
If you need to modify anything, the script is at scripts/slurm/train.sh
.
make slurmcat id=6246500
The logs are stored at scripts/slurm_logs/slurm_output_{id}.out
.
To maximize convenience, reproducibility and encourage usage of our modules (models, datasets, tools), we've package some of them separately.