solaris33

# -*- coding: utf-8 -*-

# tf.train.Coordinator 예제

# original source:
# https://github.com/Hezi-Resheff/Oreilly-Learning-TensorFlow/blob/master/08__queues_threads/queue_basic.py

from __future__ import print_function

import tensorflow as tf

solaris33

# -*- coding: utf-8 -*-

# original source:
# https://github.com/Hezi-Resheff/Oreilly-Learning-TensorFlow/blob/master/08__queues_threads/queue_basic.py

from __future__ import print_function

import tensorflow as tf

import threading

solaris33

solaris33

# -*- coding: utf-8 -*-

# tf.get_variable & tf.variable_scope 예제 (변수가 공유된다.)

# MNIST 데이터를 다운로드 한다.
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

import tensorflow as tf

solaris33

# -*- coding: utf-8 -*-

#tf.Variable 예제 (변수 공유 안됨)

# MNIST 데이터를 다운로드 한다.
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

import tensorflow as tf

solaris33

# -*- coding: utf-8 -*-

"""
CIFAR-10 Convolutional Neural Networks(CNN) Example

next_batch function is copied from edo's answer

https://stackoverflow.com/questions/40994583/how-to-implement-tensorflows-next-batch-for-own-data

Author : solaris33

solaris33

import numpy as np
import matplotlib.pyplot as plt

mu, sigma = 0, 0.1 # mean and standard deviation
# np.random.nomral 함수를 이용해서 평균 0, 표준편차 0.1인 sample들을 1000개 추출한다.
s = np.random.normal(mu, sigma, 1000)

# sample들의 historgram을 출력한다.
count, bins, ignored = plt.hist(s, 30, normed=True)
# sample들을 이용해서 Gaussian Distribution의 shape을 재구축해서 line으로 그린다.

solaris33

solaris33

# -*- coding: utf-8 -*-

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


## Initialize the "Cart-Pole" environment

solaris33

# -*- coding: utf-8 -*-

import gym

env = gym.make('CartPole-v0')
for i_episode in range(20):
    # 새로운 에피소드(initial environment)를 불러온다(reset)
    observation = env.reset()
    for t in range(100):
        env.render()