Link to the Paper - arXiv
- Linux-64
- Python 3.9
- PyTorch 1.10.1
- CPU or NVIDIA GPU + CUDA10.2 CuDNN7.5
- Create a conda environment and install required packages:
conda create -n <env> python=3.9
conda activate <env>
pip install -r requirements.txt
Download the Mini-imagenet and notMNIST datasets from Google Drive. Other datasets will be automatically downloaded.
For training, run the following command.
python run.py -exp <experiment_id>
To manually input number of runs, epochs and learning rate, run the following command:
python run.py -exp <experiment_id> -r <n_runs> -e <n_epochs> -lr <learning_rate>
For test, run the following command.
python test.py -exp <experiment_id>