Custom Weight Initialization
Opened this issue · 3 comments
glenn-jocher commented
I noticed you use code for custom weight initialization:
Lines 162 to 169 in 2c90e67
I've not seen this before. Is there a reason behind this specific strategy? Do you know the effect this has on the training, and have you compared this with the pytorch default weight initialization? Thank you!
iamhankai commented
kaiming_normal_
is a commonly used initialization strategy.
glenn-jocher commented
@iamhankai thank you! Do you know what the default pytorch weights init strategy is?
I suppose this makes for easier comparisons with the TF version of ghostnet to use the same strategy on both?
iamhankai commented
@glenn-jocher TF version of ghostnet also used Kaiming normal initialization.