tensor_stream 1.0.0 → 1.0.1

data/samples/linear_regression.rb

@@ -1,69 +0,0 @@
-# Linear Regression sample, using SGD and auto-differentiation
-require "bundler/setup"
-require 'tensor_stream'
-
-tf = TensorStream # use tf to make it look like TensorFlow
-
-learning_rate = 0.01
-momentum = 0.5
-training_epochs = 10000
-display_step = 50
-
-train_X = [3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
-7.042,10.791,5.313,7.997,5.654,9.27,3.1]
-train_Y = [1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
-2.827,3.465,1.65,2.904,2.42,2.94,1.3]
-
-n_samples = train_X.size
-
-X = Float.placeholder
-Y = Float.placeholder
-
-# Set model weights
-
-W = rand.t.var name: "weight"
-b = rand.t.var name: "bias"
-
-# Construct a linear model
-pred = X * W + b
-
-# Mean squared error
-cost = ((pred - Y) ** 2).reduce / ( 2 * n_samples)
-
-# Other possible Optimizers
-
-# optimizer = TensorStream::Train::MomentumOptimizer.new(learning_rate, momentum, use_nesterov: true).minimize(cost)
-# optimizer = TensorStream::Train::AdamOptimizer.new(learning_rate).minimize(cost)
-# optimizer = TensorStream::Train::AdadeltaOptimizer.new(1.0).minimize(cost)
-# optimizer = TensorStream::Train::AdagradOptimizer.new(0.01).minimize(cost)
-# optimizer = TensorStream::Train::RMSPropOptimizer.new(0.01, centered: true).minimize(cost)
-optimizer = TensorStream::Train::GradientDescentOptimizer.new(learning_rate).minimize(cost)
-
-
-# Initialize the variables (i.e. assign their default value)
-init = tf.global_variables_initializer()
-# Add ops to save and restore all the variables.
-saver = tf::Train::Saver.new
-
-tf.session do |sess|
-    start_time = Time.now
-    sess.run(init)
-    (0..training_epochs).each do |epoch|
-      train_X.zip(train_Y).each do |x,y|
-        sess.run(optimizer, feed_dict: {X => x, Y => y})
-      end
-
-      if (epoch+1) % display_step == 0
-        # Save the variables to disk.
-        save_path = saver.save(sess, "/tmp/lg_model")
-        c = sess.run(cost, feed_dict: {X => train_X, Y => train_Y})
-        puts("Epoch:", '%04d' % (epoch+1), "cost=",  c, \
-            "W=", sess.run(W), "b=", sess.run(b))
-      end
-    end
-
-    puts("Optimization Finished!")
-    training_cost = sess.run(cost, feed_dict: { X => train_X, Y => train_Y})
-    puts("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')
-    puts("time elapsed ", Time.now.to_i - start_time.to_i)
-end

data/samples/multigpu.rb

@@ -1,73 +0,0 @@
-require "bundler/setup"
-require 'tensor_stream'
-require 'tensor_stream/evaluator/opencl/opencl_evaluator'
-# require 'pry-byebug'
-
-ts = TensorStream
-
-n = 10
-DIMEN = 1024
-
-A = ts.random_uniform([DIMEN, DIMEN]).eval
-B = ts.random_uniform([DIMEN, DIMEN]).eval
-
-
-# Create a graph to store results
-c1 = []
-c2 = []
-a = nil
-b = nil
-
-def matpow(m, n)
-  return m if n < 1
-  TensorStream.matmul(m, matpow(m, n-1))
-end
-
-ts.device('/device:GPU:0') do
-  a = ts.placeholder(:float32, shape: [DIMEN, DIMEN])
-  b = ts.placeholder(:float32, shape: [DIMEN, DIMEN])
-  # Compute A^n and B^n and store results in c1
-  c1 << matpow(a, n)
-  c1 << matpow(b, n)
-end
-
-sum = ts.device('/device:GPU:0') do
-  ts.add_n(c1)
-end
-
-t1_1 = Time.now.to_i
-t2_1 = nil
-
-ts.session(log_device_placement: true) do |sess|
-  sess.run(sum, feed_dict: { a => A, b => B})
-  t2_1 = Time.now.to_i
-end
-
-# Multi GPU computing
-# GPU:0 computes A^n
-ts.device('/device:GPU:1') do
-  a = ts.placeholder(:float32, shape: [DIMEN, DIMEN])
-  c2 << matpow(a, n)
-end
-
-# GPU:1 computes B^n
-ts.device('/device:GPU:1') do
-  b = ts.placeholder(:float32, shape: [DIMEN, DIMEN])
-  c2 << matpow(b, n)
-end
-
-ts.device('/device:GPU:1') do
-  sum = ts.add_n(c2) #Addition of all elements in c2, i.e. A^n + B^n
-end
-
-t1_2 = Time.now.to_i
-t2_2 = nil
-ts.session(log_device_placement:true) do |sess|
-    # Run the op.
-    sess.run(sum, feed_dict: {a => A, b => B})
-    t2_2 = Time.now.to_i
-end
-
-
-print("Single GPU computation time: " + (t2_1-t1_1).to_s)
-print("Multi GPU computation time: " + (t2_2-t1_2).to_s)

data/samples/raw_neural_net_sample.rb

@@ -1,112 +0,0 @@
-""" Neural Network.
-
-A 2-Hidden Layers Fully Connected Neural Network (a.k.a Multilayer Perceptron)
-implementation with TensorFlow. This example is using the MNIST database
-of handwritten digits (http://yann.lecun.com/exdb/mnist/).
-
-Links:
-    [MNIST Dataset](http://yann.lecun.com/exdb/mnist/).
-
-Author: Aymeric Damien
-Project: https://github.com/aymericdamien/TensorFlow-Examples/
-
-The mnist-learn gem is required as well as an OpenCL compatible device with drivers correctly installed
-"""
-require "bundler/setup"
-require 'tensor_stream'
-require 'mnist-learn'
-
-tf = TensorStream
-# Import MNIST data
-puts "downloading minst data"
-mnist = Mnist.read_data_sets('/tmp/data', one_hot: true)
-puts "downloading finished"
-
-# Parameters
-learning_rate = 0.001
-momentum = 0.01
-num_steps = 100
-batch_size = 128
-display_step = 5
-
-# Network Parameters
-n_hidden_1 = 256 # 1st layer number of neurons
-n_hidden_2 = 256 # 2nd layer number of neurons
-num_input = 784 # MNIST data input (img shape: 28*28)
-num_classes = 10 # MNIST total classes (0-9 digits)
-
-# tf Graph input
-X = tf.placeholder(:float64, shape: [nil, num_input])
-Y = tf.placeholder(:float64, shape: [nil, num_classes])
-
-# Store layers weight & bias
-weights = {
-    'h1' => tf.variable(tf.random_normal([num_input, n_hidden_1]), dtype: :float64, name: 'h1'),
-    'h2' => tf.variable(tf.random_normal([n_hidden_1, n_hidden_2]), dtype: :float64, name: 'h2'),
-    'out' => tf.variable(tf.random_normal([n_hidden_2, num_classes]), dtype: :float64, name: 'out')
-}
-
-biases = {
-    'b1' => tf.variable(tf.random_normal([n_hidden_1]), dtype: :float64, name: 'b1'),
-    'b2' => tf.variable(tf.random_normal([n_hidden_2]), dtype: :float64, name: 'b2'),
-    'out' => tf.variable(tf.random_normal([num_classes]), dtype: :float64, name: 'out2')
-}
-
-
-# Create model
-def neural_net(x, weights, biases)
-    tf = TensorStream
-    # Hidden fully connected layer with 256 neurons
-    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
-    # Hidden fully connected layer with 256 neurons
-    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
-    # Output fully connected layer with a neuron for each class
-    tf.matmul(layer_2, weights['out']) + biases['out']
-end
-
-# Construct model
-logits = neural_net(X, weights, biases)
-prediction = tf.nn.softmax(logits)
-
-# Define loss and optimizer
-loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(
-    logits: logits, labels: Y))
-
-optimizer = TensorStream::Train::MomentumOptimizer.new(learning_rate, momentum, use_nesterov: true)
-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, :float32))
-
-# tf.add_check_numerics_ops
-
-# Initialize the variables (i.e. assign their default value)
-init = tf.global_variables_initializer
-
-# Start training
-tf.session do |sess|
-    # Run the initializer
-    sess.run(init)
-
-    print("Testing Accuracy:", \
-        sess.run(accuracy, feed_dict: { X => mnist.test.images,
-                                        Y => mnist.test.labels}))
-
-    (1..num_steps+1).each do |step|
-        batch_x, batch_y = mnist.train.next_batch(batch_size)
-        # Run optimization op (backprop)
-        sess.run(train_op, feed_dict: { X => batch_x, Y => batch_y })
-        if step % display_step == 0 || step == 1
-            # Calculate batch loss and accuracy
-            loss, acc = sess.run([loss_op, accuracy], feed_dict: { X => batch_x, Y => batch_y})
-            print("\nStep " + step.to_s + ", Minibatch Loss= " + \
-                    loss.to_s + ", Training Accuracy= " + \
-                    acc.to_s)
-        end
-    end
-    print("\nOptimization Finished!")
-    print("\nTesting Accuracy after optimization:", \
-        sess.run(accuracy, feed_dict: { X => mnist.test.images,
-                                        Y => mnist.test.labels}))
-end