Clay Fortune snowyday

snowyday / mnist_dist.py

Last active February 17, 2019 14:19

Distributed MNIST with Ignite

	from argparse import ArgumentParser

	import torch
	from torch import nn
	import torch.nn.functional as F
	from torch.optim import SGD
	import torch.utils.data

	# === ADDED FOR DISTRIBUTED >>>
	import torch.distributed

snowyday / loss_to_eve.py

Last active April 24, 2017 21:40

Usage of eve

	optimizer = optim.Eve(model.parameters())

	optimizer.step(lambda: loss)

snowyday / eve.py

Last active January 16, 2018 04:26

Eve: Improving Stochastic Gradient Descent with Feedback

	import math
	from torch.optim import Optimizer

	class Eve(Optimizer):
	"""Implements Eve (Adam with feedback) algorithm.

	It has been proposed in `Improving Stochastic Gradient Descent with Feedback, `_.

	Arguments:
	params (iterable): iterable of parameters to optimize or dicts defining