Markus Dreyer markusdr

The Best of the Best Practices (BOBP) Guide for Python

A "Best of the Best Practices" (BOBP) guide to developing in Python.

	import torch
	import torch.nn as nn
	import torch.nn.functional as F

	# helpers

	def make_unit_length(x, epsilon=1e-6):
	norm = x.norm(p=2, dim=-1, keepdim=True)
	return x.div(norm + epsilon)

	""" Deep Auto-Encoder implementation

	An auto-encoder works as follows:

	Data of dimension k is reduced to a lower dimension j using a matrix multiplication:
	softmax(W*x + b) = x'

	where W is matrix from R^k --> R^j

	A reconstruction matrix W' maps back from R^j --> R^k

	# produces a patch between the files in the 2 dirs

	# -c : special context for output
	# -r : directory recursively
	# -B : ignore blanks

	diff -crB before_dir after_dir > foo.patch

	# if you want to patch before_dir now