Lazy Initialization

English Version pytorch
#1

https://d2l.ai/chapter_builders-guide/lazy-init.html

#2

AttributeError: module ‘d2l.torch’ has no attribute ‘add_to_class’

my d2l version is 0.17.5. I am using Google colab.

1 Like
#3

I’m very curious to learn more about problem #3… How do we use parameter tying to fix the issue of different - sized inputs?