2017年04月_理想主义文艺青年

原创 2017Google Codejam round1c Problem B. Parenting Partnering

ProblemCameron and Jamie are longtime life partners and have recently become parents! Being in charge of a baby, exciting as it is, is not without challenges. Given that both parents have a scient

2017-04-30 21:20:23 667

原创 2017Google Codejam round1c Problem A. Ample Syrup

ProblemThe kitchen at the Infinite House of Pancakes has just received an order for a stack of K pancakes! The chef currently has N pancakes available, where N ≥ K. Each pancake is a cylinder, a

2017-04-30 21:15:21 967

原创 2017Google Codejam round1b Problem C. Pony Express

ProblemIt's the year 1860, and the Pony Express is the fastest mail delivery system joining the East and West coasts of the United States. This system serves N different cities. In each city, th

2017-04-23 19:20:05 6843

原创 2017Google Codejam round1b Problem B. Stable Neigh-bors

ProblemYou are lucky enough to own N pet unicorns. Each of your unicorns has either one or two of the following kinds of hairs in its mane: red hairs, yellow hairs, and blue hairs. The color of

2017-04-23 16:48:49 914

原创 Generative Adversarial Nets(GAN) Tensorflow实现

import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataimport numpy as npimport matplotlib# from scipy.misc import imsave# from skimage.io import imsave# import scipy.m

2017-04-22 15:59:03 1015

原创 GAN相关工作介绍

GAN介绍GenerativeAdversarial Nets生成对抗网络的思想在2014年提出，在原始的paper中，作者用博弈论来阐释GAN框架背后的思想。每一个GAN框架，都包含一个生成模型G和一个判别模型D，判别模型的任务是判断给定图像是否看起来‘自然’，换句话说，是否像是机器生成的。而生成器的任务是，生成看起来‘自然’的图像，要求与原始数据分布尽可能一致。作者在文中有一个形象的比

2017-04-19 22:58:15 3625 2

原创 TensorFlow-MNSIT进阶篇代码

在入门篇之后进阶篇进行了拓展使用了卷积神经网络两个卷积层两个pooling层一个全连接层其中注意 padding='SAME'对图片大小的影响For the SAME padding, the output height and width are computed as:out_height = ceil(float(in_height) / f

2017-04-11 20:51:34 727

原创 TensorFlow-MNIST入门篇代码

看了下TensorFlow的官方文档里面关于MNIST的入门篇在这里把代码整理了input_data.py(urllib下面有红线没关系)# __author__ = 'youngkl'# -*- coding: utf-8 -*-from __future__ import absolute_importfrom __future__ import divisionfr

2017-04-11 15:39:19 993

原创 TensorFlow基本用法

# __author__ = 'youngkl'# -*- coding: utf-8 -*-import tensorflow as tf#1*2的矩阵mat1=tf.constant([[3.,3.]])#2*1的矩阵mat2=tf.constant([[2.],[3.]])ans=tf.matmul(mat1,mat2)#此时ans无法直接输出'''# 启动默认图

2017-04-10 20:53:25 492

原创 python学习小记

写机器学习算法经常用到python 这里记录一些常用的python小的点会很基础供个人使用贴出来一些自己学的过程中写的小的测试代码1.矩阵定义矩阵的转置矩阵的逆矩阵相乘 e的N次方import numpy as npa=np.mat('1 1 1 1;0.1353 0.3678 0.3678 1;1 0.3678 0.3678 0.1353')# c=np

2017-04-01 14:03:19 357

youngkl博客