Open limonan-tal opened 1 year ago
Based on the code at https://github.com/Gengzigang/PCT/blob/main/models/pct_tokenizer.py#L156, the codebook is updated during the tokenizer training stage.
I also have the same question,how the codebook initialized codebook?self.codebook.data.normal_()?
Hi, Could I know how you initialize a new codebook? Furthermore, in you paper, you demonstrated that the codebook is updated by using exponential moving average of previous tokens, I wonder this step is in Stage I (i.e. train encoder) or is an additional stage before training tokenizers?