Pytorch Implemetation for our NAACL2019 Paper "Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling" https://arxiv.org/abs/1904.02399
Thanks for your code. It seems that in model.py, there is no definition for: self.z2h(z) and self.lookup, and they are used in
def generate(self, z, max_length, sos_id).
Hi @kingofspace0wzz ,
Thanks for your code. It seems that in model.py, there is no definition for: self.z2h(z) and self.lookup, and they are used in def generate(self, z, max_length, sos_id).