added all chapters

Author: goodrahstar

Chapter01/setupDeepLearning.sh

@@ -0,0 +1,83 @@
+#!/bin/bash
+
+# Save this script to /home/yourUserName, chmod +x setupDeepLearning.sh, run using ./setupDeepLearning.sh
+
+mkdir tensorflow
+cd tensorflow
+
+################################################################################
+# Install utils.
+################################################################################
+echo -e "\e[36m***Installing utilities*** \e[0m"
+sudo apt-get update
+sudo apt-get install unzip git-all pkg-config zip g++ zlib1g-dev
+
+################################################################################
+# Install Java deps.
+################################################################################
+echo -e "\e[36m***Installing Java8. Press ENTER when prompted*** \e[0m"
+echo -e "\e[36m***And accept licence*** \e[0m"
+sudo add-apt-repository ppa:webupd8team/java
+sudo apt-get update
+sudo apt-get install oracle-java8-installer
+
+################################################################################
+# Install Bazel dep.
+################################################################################
+echo -e "\e[36m***Installing Bazel*** \e[0m"
+wget https://github.com/bazelbuild/bazel/releases/download/0.11.1/bazel-0.11.1-without-jdk-installer-linux-x86_64.sh -O bazel-installer-linux-x86_64.sh
+chmod +x bazel-installer-linux-x86_64.sh
+sudo ./bazel-installer-linux-x86_64.sh
+rm bazel-installer-linux-x86_64.sh
+sudo chown $USER:$USER ~/.cache/bazel/
+
+################################################################################
+# Fetch Swig and Python deps.
+################################################################################
+echo -e "\e[36m***Installing python deps*** \e[0m"
+sudo apt-get install swig
+sudo apt-get install build-essential python-dev python-pip checkinstall
+sudo apt-get install libreadline-gplv2-dev libncursesw5-dev libssl-dev libsqlite3-dev tk-dev libgdbm-dev libc6-dev libbz2-dev
+
+################################################################################
+# Fetch and install Python.
+################################################################################
+echo -e "\e[36m***Installing Python*** \e[0m"
+wget https://www.python.org/ftp/python/2.7.14/Python-2.7.14.tgz
+tar -xvf Python-2.7.14.tgz
+cd Python-2.7.14
+./configure
+make
+sudo make install
+cd ../
+rm Python-2.7.14.tgz
+
+################################################################################
+# Grab TensorFlow CPU version from central repo
+################################################################################
+echo -e "\e[36m***Cloning TensorFlow from GitHub*** \e[0m"
+sudo pip install tensorflow
+
+################################################################################
+# Grab Keras from repo
+################################################################################
+echo -e "\e[36m***Installing Keras with Tensorflow backend*** \e[0m"
+sudo pip install keras
+
+################################################################################
+# Installing other python dependencies
+################################################################################
+echo -e "\e[36m***Installing Python Deps*** \e[0m"
+sudo apt-get install python-numpy
+sudo pip install numpy --upgrade
+sudo pip --no-cache-dir install Pillow pandas scipy sklearn
+sudo pip install web.py gunicorn
+
+echo -e "\e[36mReady to run TensorFlow! \e[0m"
+
+################################################################################
+# Checking the installations
+################################################################################
+echo -e "\e[36m***Listing modules*** \e[0m"
+
+pip list

Chapter02/.DS_Store

@@ -0,0 +1,20 @@
+#!/usr/bin/env python2
+
+# Hyperparameters and all other kind of params
+
+# Parameters
+learning_rate = 0.01
+num_steps = 100
+batch_size = 128
+display_step = 1
+
+
+# Network Parameters
+n_hidden_1 = 300 # 1st layer number of neurons
+n_hidden_2 = 300 # 2nd layer number of neurons
+num_input = 784 # MNIST data input (img shape: 28*28)
+num_classes = 10 # MNIST total classes (0-9 digits)
+
+#Training Parameters
+checkpoint_every = 100
+checkpoint_dir = './runs/'

Chapter02/hy_param.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+
+from __future__ import print_function
+
+
+import os
+import numpy as np
+import tensorflow as tf
+import matplotlib.pyplot as plt
+
+import hy_param
+
+from tensorflow.examples.tutorials.mnist import input_data
+mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
+
+# Pointing the model checkpoint
+checkpoint_file = tf.train.latest_checkpoint(os.path.join(hy_param.checkpoint_dir, 'checkpoints'))
+saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
+
+# Loading test data
+test_data = np.array([mnist.test.images[6]])
+
+# Loading input variable from the model
+input_x = tf.get_default_graph().get_operation_by_name("input_x").outputs[0]
+
+# Loading Prediction operation
+prediction = tf.get_default_graph().get_operation_by_name("prediction").outputs[0]
+
+
+with tf.Session() as sess:
+    # Restoring the model from the checkpoint
+    saver.restore(sess, checkpoint_file)
+    
+    # Executing the model to make predictions    
+    data = sess.run(prediction, feed_dict={input_x: test_data })
+    
+    print("Predicted digit: ", data.argmax() )
+
+
+# Display the feed image
+print ("Input image:")
+plt.gray()
+plt.imshow(test_data.reshape([28,28]))

Chapter02/inference.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+import tensorflow as tf
+import hy_param
+
+
+## Defining Placeholders which will be used as inputs for the model
+X = tf.placeholder("float", [None, hy_param.num_input],name="input_x")
+Y = tf.placeholder("float", [None, hy_param.num_classes],name="input_y")
+
+
+# Defining variables for weights & bias
+weights = {
+    'h1': tf.Variable(tf.random_normal([hy_param.num_input, hy_param.n_hidden_1])),
+    'h2': tf.Variable(tf.random_normal([hy_param.n_hidden_1, hy_param.n_hidden_2])),
+    'out': tf.Variable(tf.random_normal([hy_param.n_hidden_2, hy_param.num_classes]))
+}
+biases = {
+    'b1': tf.Variable(tf.random_normal([hy_param.n_hidden_1])),
+    'b2': tf.Variable(tf.random_normal([hy_param.n_hidden_2])),
+    'out': tf.Variable(tf.random_normal([hy_param.num_classes]))
+}
+
+
+# Hidden fully connected layer 1 with 300 neurons
+layer_1 = tf.add(tf.matmul(X, weights['h1']), biases['b1'])
+# Hidden fully connected layer 2 with 300 neurons
+layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
+# Output fully connected layer with a neuron for each class
+logits = tf.matmul(layer_2, weights['out']) + biases['out']
+
+# Performing softmax operation
+prediction = tf.nn.softmax(logits, name='prediction')
+
+# Define loss and optimizer
+loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
+    logits=logits, labels=Y))
+optimizer = tf.train.AdamOptimizer(learning_rate=hy_param.learning_rate)
+train_op = optimizer.minimize(loss_op)
+
+# Evaluate model
+correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y, 1))
+accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32) ,name='accuracy')

Chapter02/model.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+
+from __future__ import print_function
+
+# Import MNIST data
+import os
+from tensorflow.examples.tutorials.mnist import input_data
+mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
+
+import tensorflow as tf
+import model
+import hy_param
+
+
+## tf Graph input
+X = model.X
+Y = model.Y
+
+
+
+checkpoint_dir = os.path.abspath(os.path.join(hy_param.checkpoint_dir, "checkpoints"))
+checkpoint_prefix = os.path.join(checkpoint_dir, "model")
+if not os.path.exists(checkpoint_dir):
+    os.makedirs(checkpoint_dir)
+saver = tf.train.Saver(tf.global_variables(), max_to_keep=2)
+        
+#loss = tf.Variable(0.0)
+# Initialize the variables
+init = tf.global_variables_initializer()
+all_loss = []
+# Start training
+with tf.Session() as sess:
+    writer_1 = tf.summary.FileWriter("./runs/summary/",sess.graph)
+    
+    sum_var = tf.summary.scalar("loss", model.accuracy)
+    write_op = tf.summary.merge_all()
+
+    # Run the initializer
+    sess.run(init)
+
+    for step in range(1, hy_param.num_steps+1):
+        # Extracting 
+        batch_x, batch_y = mnist.train.next_batch(hy_param.batch_size)
+        # Run optimization op (backprop)
+        sess.run(model.train_op, feed_dict={X: batch_x, Y: batch_y})
+        if step % hy_param.display_step == 0 or step == 1:
+            # Calculate batch loss and accuracy
+            loss, acc, summary = sess.run([model.loss_op, model.accuracy, write_op], feed_dict={X: batch_x,
+                                                                 Y: batch_y})
+            all_loss.append(loss)
+            writer_1.add_summary(summary, step)
+            print("Step " + str(step) + ", Minibatch Loss= " + \
+                  "{:.4f}".format(loss) + ", Training Accuracy= " + \
+                  "{:.3f}".format(acc))
+        if step % hy_param.checkpoint_every == 0:
+            path = saver.save(
+                        sess, checkpoint_prefix, global_step=step)
+#            print("Saved model checkpoint to {}\n".format(path))
+
+    print("Optimization Finished!")
+
+    # Calculate accuracy for MNIST test images
+    print("Testing Accuracy:", \
+        sess.run(model.accuracy, feed_dict={X: mnist.test.images,
+                                      Y: mnist.test.labels}))
+    
+