shagunsodhani

The Batch Normalization paper describes a method to address the various issues related to training of Deep Neural Networks. It makes normalization a part of the architecture itself and reports significant improvements in terms of the number of iterations required to train the network.

Issues With Training Deep Neural Networks

Internal Covariate shift

Covariate shift refers to the change in the input distribution to a learning system. In the case of deep networks, the input to each layer is affected by parameters in all the input layers. So even small changes to the network get amplified down the network. This leads to change in the input distribution to internal layers of the deep network and is known as internal covariate shift.

It is well established that networks converge faster if the inputs have been whitened (ie zero mean, unit variances) and are uncorrelated and internal covariate shift leads to just the opposite.

karpathy

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

floodsung

# -------------------------------
# DQN for CartPole in OpenAI Gym
# Author: Flood Sung
# Date: 2016.6.27
# All rights reserved
# -------------------------------

import gym
import tensorflow as tf 
import numpy as np 

awjuliani

kkweon

import tensorflow as tf
import numpy as np
import threading
import gym
import os
from scipy.misc import imresize


def copy_src_to_dst(from_scope, to_scope):
    """Creates a copy variable weights operation

jganzabal

This configuration worked for me, hope it helps

It is based on: https://becominghuman.ai/deep-learning-gaming-build-with-nvidia-titan-xp-and-macbook-pro-with-thunderbolt2-5ceee7167f8b

and on: https://stackoverflow.com/questions/44744737/tensorflow-mac-os-gpu-support

Hardware

mikelove

1) Download mosek from here:
https://www.mosek.com/downloads/
(I downloaded this to my ~/bin)

cd ~/bin
tar -xvf mosektoolslinux64x86.tar.bz2

2) Add this to your ~/.bashrc
export PATH=$PATH:/home/username/bin/mosek/8/tools/platform/linux64x86/bin