pytorch/examples

A question about weight initialization of embedding layer.

Open

#595 aperta il 18 lug 2019

Vedi su GitHub
 (1 commento) (0 reazioni) (0 assegnatari)Python (9429 fork)batch import
good first issue

Metriche repository

Star
 (21.634 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

I have a question about the weight intialization of embedding layer.

In source code of PyTorch, the weight of embedding layer is initialized by N(0, 1). In this code, the weight of embedding layer is intialized by uniform.

I trained the model two times with different initialization method, and I found that the default initialization makes the model converges too slow.

So, why the embedding is initialized by N(0, 1), which seems not a good start point?

Guida contributor