tensor_stream 0.6.0 → 0.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6d647cef8f32fa7b3c10460365adfc55ccdd9872e71d453df090986349b615f5
-  data.tar.gz: baa7be71775bc5d39396343b6d4c32943cf3b79d5a2e591c885bd6fc9314883e
+  metadata.gz: f4f9e6d7a1640d4b24b92d7706bcab88ab5bb294551f38dc6ad403eb1b2a761b
+  data.tar.gz: 71c245e394be382e3976f4b2b9989c2b89538f22cc40984a5a84e07fb0bca597
 SHA512:
-  metadata.gz: d3207ef919464e696d03fe7bbd264ba606565bf09d66796d461b687f047e8b2b969259bcffaf7524677d6b22398ba32025ca8f94c33756cda3a3bb37f535a902
-  data.tar.gz: 735dbd55e54237619bb9c6653818dade6df257fb71a58cc4abd540a3053d51d318d734ba149c3889bd6403a5219166c291534a66528b83e481ba1240e2696e49
+  metadata.gz: a04ca2c61064dc4fb67f2653acbde962f8f8b5f56a5e5f27760f44f6032b81c61307e3b207bbb4ec42bd1713d06315ba760a710a712fb9f124efa6c7f06a7246
+  data.tar.gz: ae8e29f412c1b63b854604696df4858ce4d3fb078c982e53a0b85fd8ff6b546c2b9502ecb4d253cb6d0f9255aa1e16b1aaa445da769a0b06bb85ed55a0aebd55

data/lib/tensor_stream/evaluator/ruby_evaluator.rb

@@ -532,7 +532,6 @@ module TensorStream
         matrix_a, matrix_b = inputs
         rank_a = get_rank(matrix_a)
         rank_b = get_rank(matrix_b)
-
         raise "#{tensor.inputs[0].name} rank must be greater than 1" if rank_a < 2
         raise "#{tensor.inputs[1].name} rank must be greater than 1" if rank_b < 2
 

data/lib/tensor_stream/nn/nn_ops.rb

@@ -11,11 +11,11 @@ module TensorStream
     end
 
     def self.sigmoid(input, name: nil)
-      TensorStream.sigmoid(input, name)
+      TensorStream.sigmoid(input, name: name)
     end
 
     def self.softmax_cross_entropy_with_logits(labels: nil, logits: nil, name: nil)
-      softmax_cross_entropy_with_logits_v2(labels, logits, name)
+      softmax_cross_entropy_with_logits_v2(labels: labels, logits: logits, name: name)
     end
 
     def self.softmax_cross_entropy_with_logits_v2(labels: nil, logits: nil, name: nil)

data/lib/tensor_stream/version.rb

@@ -1,5 +1,5 @@
 module TensorStream
-  VERSION = '0.6.0'.freeze
+  VERSION = '0.6.1'.freeze
 
   def self.version
     VERSION

data/samples/iris.rb

@@ -1,5 +1,6 @@
 require "bundler/setup"
 require 'tensor_stream'
+require 'tensor_stream/evaluator/opencl/opencl_evaluator'
 
 # This neural network will predict the species of an iris based on sepal and petal size
 # Dataset: http://en.wikipedia.org/wiki/Iris_flower_data_set
@@ -47,65 +48,54 @@ x_test.each_with_index do |x, index|
   validation_cases << [x, y_test[index] ]
 end
 
-learning_rate = 0.1
-num_steps = 500
-batch_size = 128
-display_step = 100
 
-# Network Parameters
-n_hidden_1 = 4 # 1st layer number of neurons
-num_classes = 3 # MNIST total classes (0-9 digits)
-num_input = 4
-training_epochs = 100
 
-tf = TensorStream
-
-# tf Graph input
-x = tf.placeholder("float", shape: [nil, num_input], name: 'x')
-y = tf.placeholder("float", shape: [nil, num_classes], name: 'y')
-
-# Store layers weight & bias
-weights = {
-  h1: tf.variable(tf.random_normal([num_input, n_hidden_1]), name: 'h1'),
-  out: tf.variable(tf.random_normal([num_classes, num_classes]), name: 'out')
-}
-
-biases = {
-  b1: tf.variable(tf.random_normal([n_hidden_1]), name: 'b1'),
-  out: tf.variable(tf.random_normal([num_classes]), name: 'b_out')
-}
+def init_weights(shape)
+  # Weight initialization
+  weights = TensorStream.random_normal(shape, stddev: 0.1)
+  TensorStream.variable(weights)
+end
 
-# Create model
-def neural_net(x, weights, biases)
-    layer_1 = TensorStream.tanh(TensorStream.add(TensorStream.matmul(x, weights[:h1]), biases[:b1], name: 'layer1_add'))
-    # Output fully connected layer with a neuron for each class
-    TensorStream.sigmoid(TensorStream.matmul(layer_1, weights[:out]) + biases[:out])
+def forwardprop(x, w_1, w_2)
+  # Forward-propagation.
+  # IMPORTANT: yhat is not softmax since TensorFlow's softmax_cross_entropy_with_logits() does that internally.
+  h  = TensorStream.nn.sigmoid(TensorStream.matmul(x, w_1))  # The \sigma function
+  TensorStream.matmul(h, w_2)  # The \varphi function
 end
 
-# Construct model
-logits = neural_net(x, weights, biases)
-
-# Mean squared error
-cost = TensorStream.reduce_sum(TensorStream.pow(logits - y, 2)) / ( 2 * y_train.size)
-optimizer = TensorStream::Train::GradientDescentOptimizer.new(learning_rate).minimize(cost)
-
-# Initialize the variables (i.e. assign their default value)
-init = TensorStream.global_variables_initializer()
-
-TensorStream.session do |sess|
-  puts "init vars"
-  sess.run(init)
-  puts "Testing the untrained network..."
-  loss = sess.run(cost, feed_dict: { x => x_train, y => y_train })
-  puts loss
-  puts "loss before training"
-  (0..training_epochs).each do |epoch|
-    x_train.zip(y_train).each do |t_x, t_y|
-      sess.run(optimizer, feed_dict: { x => [t_x], y => [t_y] })
-      loss = sess.run(cost, feed_dict: { x => [t_x], y => [t_y] })
-    end
-    puts "loss #{loss}"
+x_size = x_train[0].size
+y_size = y_train[0].size
+h_size = 256
+X = tf.placeholder(:float, shape: [nil, x_size])
+y = tf.placeholder(:float, shape: [nil, y_size])
+
+# Weight initializations
+w_1 = init_weights([x_size, h_size])
+w_2 = init_weights([h_size, y_size])
+
+# Forward propagation
+yhat    = forwardprop(X, w_1, w_2)
+predict = tf.argmax(yhat, axis=1)
+
+# Backward propagation
+cost    = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels: y, logits: yhat))
+updates =  TensorStream::Train::GradientDescentOptimizer.new(0.01).minimize(cost)
+
+# Run SGD
+sess = tf.session
+init = tf.global_variables_initializer
+sess.run(init)
+
+loss = sess.run(cost, feed_dict: { X => x_train, y => y_train })
+puts "Testing the untrained network..."
+puts loss
+(0..100).each do |epoch|
+  x_train.size.times do |i|
+    sess.run(updates, feed_dict: {X => [x_train[i]], y => [y_train[i]]})
+    loss = sess.run(cost, feed_dict: { X => [x_train[i]], y => [y_train[i]] })
   end
-  loss = sess.run(cost, feed_dict: { x => x_train, y => y_train })
-  puts "loss after training #{loss}"
-end
+  puts "epoch: #{epoch}, loss #{loss}"
+end
+
+loss = sess.run(cost, feed_dict: { X => x_train, y => y_train })
+puts "loss after training #{loss}"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tensor_stream
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.6.1
 platform: ruby
 authors:
 - Joseph Emmanuel Dayo