The code implementation of VSGMN mainly based on PyTorch. All of our experiments run and test in Python 3.8.8. To install all required dependencies:
$ pip install -r requirements.txt
We trained the model on three popular ZSL benchmarks: CUB, SUN and AWA2 following the data split of xlsa17. Please follow TransZero to prepare datasets and extract visual features.
$ python train_awa_vsgmn.py
$ python train_cub_vsgmn.py
$ python train_sun_vsgmn.py