Did the default weight initialization method change? (torch1.1 vs torch1.3)

1

I found some differences between the torch 1.1 and torch 1.3 initialization methods during deeplearning experiments.
Are there really different default weight initialization methods for torch1.1 and torch1.3?

2

The default weight initialization for batch norm layers was updated to 1s instead of sampling from a uniform distribution in this PR, which shipped with 1.2, if I’m not mistaken.
Besides that I’m unaware of any changes.

2 Likes
3

Thank you very much for your answer!

1 Like