domluna

# Required downloads:
# NVIDIA-Linux-x86_64-367.27.run
# cuda_8.0.27_linux.run
# cudnn-8.0-linux-x64-v5.0-ga.tgz

sudo apt-get install build-essential
sudo apt-get install linux-image-extra-`uname -r`
sudo ./NVIDIA-Linux-x86_64-367.27.run
./cuda_8.0.27_linux.run --extract=`pwd`/extracts
sudo ./extracts/cuda-linux64-rel-8.0.27-20733550.run

domluna

import  tensorflow as tf
import numpy as np

w = np.arange(1, 10, dtype=np.float32).reshape((3,3,1,1))
f = tf.Variable(tf.constant(w))
input = tf.placeholder(tf.float32, (None, 28, 28, 1))
conv = tf.nn.conv2d(input, f, [1,2,2,1], 'SAME')

s = tf.Session()
x = np.zeros((28, 28), dtype=np.float32)

domluna

import  tensorflow as tf
import numpy as np

w = np.arange(1, 10, dtype=np.float32).reshape((3,3,1,1))
f = tf.Variable(tf.constant(w))
input = tf.placeholder(tf.float32, (None, 28, 28, 1))
conv = tf.nn.conv2d(input, f, [1,2,2,1], 'VALID')

s = tf.Session()
x = np.zeros((28, 28), dtype=np.float32)

domluna

# Simple pagerank implementation
# M - transition matrix
# r - initial rankings
# \beta - the taxation cost, (1-\beta) is the teleport prob
# iter - iterations to run for
function pagerank(M::Matrix{Float64}, r::Vector{Float64}, β::Float64, iter::Int64)
    c = (1-β)/length(r)
    v_prime = β*M*r + c
    for i = 1:iter
        v_prime = β*M*v_prime + c

domluna

"""
This script runs a policy gradient algorithm
"""

from gym.envs import make
from modular_rl import *
import argparse, sys, cPickle
from tabulate import tabulate
import shutil, os, logging
import gym

domluna

name: CarND-Term1
channels:
    - https://conda.anaconda.org/menpo
dependencies:
    - python==3.5.2
    - numpy
    - matplotlib
    - tensorflow
    - jupyter
    - opencv3

domluna

# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,

domluna

def conv2d(inputs, filter, strides, name='conv2d'):
        k = tf.get_variable('W', filter, initializer=xavier_initializer_conv2d())
        b = tf.get_variable('b', filter[-1], initializer=tf.constant_initializer(0.0))
        conv = tf.nn.conv2d(inputs, k, strides, 'SAME')
        bias_add = tf.nn.bias_add(conv, b)
        return tf.nn.relu(bias_add, name=name)


def vision_model(frames, n_frames):
    with tf.variable_scope('Conv1') as scope:

domluna

# derivs
# cross entropy -1/p deriv of -log(p)
# softmax 
# p * (1 - p) if i == j if this is the node we picked
# -p * p if i != j otherwise
#
# chain rule for both functions dsoftmax * dcross_entropy
# p * (1 - p) * (-1/p) = p - 1
# -p * p * (-1/p) = p

domluna

"""
This script runs a policy gradient algorithm
"""

from gym.envs import make
from modular_rl import *
import argparse, sys, cPickle
from tabulate import tabulate
import shutil, os, logging
import gym