pytorch/examples
A question about weight initialization of embedding layer.
Ouverte
#595 ouverte le 18 juil. 2019
good first issue
Métriques du dépôt
- Stars
- (21 634 étoiles)
- Métriques de merge PR
- (Métriques PR en attente)
Description
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?