MattChanTK

import gym
import numpy as np
import random
import math
from time import sleep

## Initialize the "Cart-Pole" environment
env = gym.make('CartPole-v0')

## Defining the environment related constants

MattChanTK

import gym
import numpy as np
import random
import math
from time import sleep

## Initialize the "Cart-Pole" environment
env = gym.make('CartPole-v0')

## Defining the environment related constants

MattChanTK

import gym
import numpy as np
import random
import math
from time import sleep


## Initialize the "Cart-Pole" environment
env = gym.make('CartPole-v0')

MattChanTK

import gzip
import os
import struct
import numpy as np

try:
    from urllib.request import urlretrieve
except ImportError:
    from urllib import urlretrieve

MattChanTK

'''
-----------------------------------------------------
Functions to load or download MNIST images and unpack
into training and testing sets.
-----------------------------------------------------
'''
# loading data from local path if possible. Otherwise download from online sources
def load_or_download_mnist_files(filename, num_samples, local_data_dir):

    if (local_data_dir):

MattChanTK

'''
--------------------------------------------------
Retrieve and process the training and testing data
--------------------------------------------------
'''
# Ensure we always get the same amount of randomness
np.random.seed(0)

# Define the data dimensions
image_shape = (1, 28, 28)

MattChanTK

'''
---------------------------------------------
Constructing the Convolutional Neural Network
---------------------------------------------
'''
def create_convolutional_neural_network(input_vars, out_dims, dropout_prob=0.0):

    convolutional_layer_1 = Convolution((5, 5), 32, strides=1, activation=cntk.ops.relu, pad=True)(input_vars)
    pooling_layer_1 = MaxPooling((2, 2), strides=(2, 2), pad=True)(convolutional_layer_1)

MattChanTK

'''
----------------------
Setting up the trainer
----------------------
'''
# Define the label as the other input parameter of the trainer
labels = cntk.ops.input_variable(output_dim, np.float32)

#Initialize the parameters for the trainer
train_minibatch_size = 50

MattChanTK

'''
-----------------------------------------
Training the Convolutional Neural Network
-----------------------------------------
'''
num_training_epoch = 1
training_progress_output_freq = 10

for epoch in range(num_training_epoch):

MattChanTK

'''
-------------------
Classification Test
--------------------
'''
test_minibatch_size = 1000

sample_count = 0
test_results = []