Installation Anaconda Tensorflow PyTorch Jupyter Notebook Ubuntu 18.04 Server Xfce4 VM Virtualbox

installation_anaconda_pytorch_tensorflow.txt

#####################################################################
#
#  Installation Anaconda Tensorflow PyTorch Jupyter Notebook Ubuntu 18.04 Server Xfce4 VM Virtualbox
#  https://ftp-stud.hs-esslingen.de/pub/Mirrors/releases.ubuntu.com/18.04/
#  
#	Install
#	ubuntu-18.04.2-live-server-amd64.iso
#	sudo apt update && sudo apt upgrate && sudo apt install xfce4
#	20:21 - 20:36 = 15 min ~
#
#####################################################################


wget https://repo.anaconda.com/archive/Anaconda3-2018.12-Linux-x86_64.sh
chmod +x Anaconda3-2018.12-Linux-x86_64.sh
bash Anaconda3-2018.12-Linux-x86_64.sh

export PATH=~/anaconda3/bin:$PATH

python --version
conda --version
conda env list
conda list

# conda create -n tensorflow pip python=3.6
# activate tensorflow

sudo apt install python3-pip
pip --version
pip install tensorflow

conda install pytorch torchvision -c pytorch

# conda update conda
# conda install mkl=2018
# conda install jupyter
# conda list
jupyter notebook

# https://www.tensorflow.org/install/pip
# http://mirrors.nju.edu.cn/tensorflow/linux/cpu/


# pip install pytorch torchvision
# pip install --ignore-installed --upgrade tensorflow
# pip install https://files.pythonhosted.org/packages/d4/29/6b4f1e02417c3a1ccc85380f093556ffd0b35dc354078074c5195c8447f2/tensorflow-1.13.1-cp37-cp37m-manylinux1_x86_64.whl 
# pip install --upgrade pip
# pip freeze
# pip uninstall numpy
# pip uninstall scipy
# pip install numpy --upgrade
# pip install scipy --upgrade
# pip install tensorflow --upgrade
# pip install --no-cache numpy
# conda install -c conda-forge numpy
# conda install pytorch torchvision

------
#################################
######  test torch
#################################

from __future__ import print_function
import torch
import torch.nn as nn
m = nn.Linear(20, 30)
input = torch.randn(128, 20)
output = m(input)
print(output.size())

#################################
###### test tensorflow
#################################

import tensorflow as tf
data = tf.constant([1, 2, 3, 4, 5, 6, 7, 8, 9, 10], dtype=tf.float32)
data = tf.reshape(data, shape=[1, 2, 5, 1])
pool = tf.layers.max_pooling2d(data, pool_size=[2, 2], strides=2, padding='same')
sess = tf.Session()
print(sess.run(pool))


#################################
####### test keras
#################################

import tensorflow as tf
mnist = tf.keras.datasets.mnist

(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(512, activation=tf.nn.relu),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)