A detail about your code

gaopengcuhk / Pretrained-Pix2Seq

Replication of Pix2Seq with Pretrained Model

60 stars 5 forks source link

A detail about your code #13

Closed sunmenmian closed 2 years ago

sunmenmian commented 2 years ago

Hi! Thank you for your great work. And I don't understand the detail about the vocal_embed: In your code, 'self.vocal_embed = nn.Embedding(self.num_vocal-2, d_model)', here why subtract 2? and what is the mean of 2? Thanks