avmodi

There is a minor code bug in attention_on_cat_and_numerical_feats combine method. if numerical_feats.shape[1] != 0: if self.numerical_feat_dim > self.text_out_dim: numerical_feats = self.num_mlp(numerical_feats) w_num = torch.mm(numerical_feats, self.weight_num) g_num = (torch.cat([w_text, **w_cat**], dim=-1)...

Can i solve the following problem using FISTA? minimise over x -> norm(**(y-Ax)./sqrt(Ax)**, 2) + lambda(norm(x,2))