Thomas Wolf thomwolf

🚂

training

Co-founder @ Hugging Face

thomwolf / bayes_by_backprop.py

Created November 30, 2017 13:27 — forked from vvanirudh/bayes_by_backprop.py

Bayes by Backprop in PyTorch (introduced in the paper "Weight uncertainty in Neural Networks", Blundell et. al. 2015)

	# Drawn from https://gist.github.com/rocknrollnerd/c5af642cf217971d93f499e8f70fcb72 (in Theano)
	# This is implemented in PyTorch
	# Author : Anirudh Vemula

	import torch
	import torch.nn as nn
	from torch.autograd import Variable
	import numpy as np

	from sklearn.datasets import fetch_mldata