wall72/install_TensorFlow_on_Windows_10_Bash.md

## install_TensorFlow_on_Windows_10_Bash.md

      
      Raw
    
  
              install_TensorFlow_on_Windows_10_Bash.md
            
          
    install TensorFlow on Windows 10 Bash (include graphiclib)
1. install packages
sudo apt-get update
sudo apt-get install -y --no-install-recommends \
        build-essential \
        libfreetype6-dev \
        libpng12-dev \
        libzmq3-dev \
        pkg-config \
        python3-dev \
        python3-numpy \
        python3-pip \
        python3-scipy \
        python3-matplotlib \
        python3-pandas \
        python3-tk \
        unzip
sudo apt-get clean
sudo rm -rf /var/lib/apt/lists/*

2. install packages with pip
sudo pip3 install seaborn
export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0rc2-cp34-cp34m-linux_x86_64.whl
sudo pip3 install --upgrade $TF_BINARY_URL


if install python3.5 and occur pip3 error

sudo pip3 install --upgrade pip
sudo pip3 install setuptools
sudo pip3 install seaborn
export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0rc2-cp35-cp35m-linux_x86_64.whl
sudo pip3 install --upgrade $TF_BINARY_URL

3. edit .bashrc

adding environment variable DISPLAY

export DISPLAY=:0

4. install X-Server on Host

(https://sourceforge.net/projects/xming/)

5. run test code

(http://jorditorres.org/first-contact-with-tensorflow/)

import numpy as np

num_puntos = 2000
conjunto_puntos = []
for i in range(num_puntos):
   if np.random.random() > 0.5:
     conjunto_puntos.append([np.random.normal(0.0, 0.9), np.random.normal(0.0, 0.9)])
   else:
     conjunto_puntos.append([np.random.normal(3.0, 0.5), np.random.normal(1.0, 0.5)])

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns

df = pd.DataFrame({"x": [v[0] for v in conjunto_puntos],
        "y": [v[1] for v in conjunto_puntos]})
sns.lmplot("x", "y", data=df, fit_reg=False, size=6)
plt.show()

import tensorflow as tf

vectors = tf.constant(conjunto_puntos)
k = 4
centroides = tf.Variable(tf.slice(tf.random_shuffle(vectors),[0,0],[k,-1]))

expanded_vectors = tf.expand_dims(vectors, 0)
expanded_centroides = tf.expand_dims(centroides, 1)

assignments = tf.argmin(tf.reduce_sum(tf.square(tf.sub(expanded_vectors, expanded_centroides)), 2), 0)

means = tf.concat(0, [tf.reduce_mean(tf.gather(vectors, tf.reshape(tf.where( tf.equal(assignments, c)),[1,-1])), reduction_indices=[1]) for c in range(k)])

update_centroides = tf.assign(centroides, means)

init_op = tf.initialize_all_variables()

sess = tf.Session()
sess.run(init_op)

for step in range(100):
   _, centroid_values, assignment_values = sess.run([update_centroides, centroides, assignments])

data = {"x": [], "y": [], "cluster": []}

for i in range(len(assignment_values)):
  data["x"].append(conjunto_puntos[i][0])
  data["y"].append(conjunto_puntos[i][1])
  data["cluster"].append(assignment_values[i])

df = pd.DataFrame(data)
sns.lmplot("x", "y", data=df, fit_reg=False, size=6, hue="cluster", legend=False)
plt.show()