Merge pull request aymericdamien#85 from normanheckscher/master

begin refactor for TF1.0

README.md

@@ -98,7 +98,7 @@ The following examples are coming from [TFLearn](https://github.com/tflearn/tfle
 
 ## Dependencies
 ```
-tensorflow
+tensorflow 1.0alpha
 numpy
 matplotlib
 cuda

examples/2_BasicModels/linear_regression.py

@@ -41,7 +41,7 @@
 optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/2_BasicModels/logistic_regression.py

@@ -38,7 +38,7 @@
 optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/2_BasicModels/nearest_neighbor.py

@@ -26,14 +26,14 @@
 
 # Nearest Neighbor calculation using L1 Distance
 # Calculate L1 Distance
-distance = tf.reduce_sum(tf.abs(tf.add(xtr, tf.neg(xte))), reduction_indices=1)
+distance = tf.reduce_sum(tf.abs(tf.add(xtr, tf.negative(xte))), reduction_indices=1)
 # Prediction: Get min distance index (Nearest neighbor)
 pred = tf.arg_min(distance, 0)
 
 accuracy = 0.
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/3_NeuralNetworks/autoencoder.py

@@ -17,7 +17,7 @@
 
 # Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
-mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
+mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
 
 # Parameters
 learning_rate = 0.01
@@ -83,7 +83,7 @@ def decoder(x):
 optimizer = tf.train.RMSPropOptimizer(learning_rate).minimize(cost)
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/3_NeuralNetworks/bidirectional_rnn.py

@@ -10,7 +10,7 @@
 from __future__ import print_function
 
 import tensorflow as tf
-from tensorflow.python.ops import rnn, rnn_cell
+from tensorflow.contrib import rnn
 import numpy as np
 
 # Import MNIST data
@@ -60,20 +60,20 @@ def BiRNN(x, weights, biases):
     # Reshape to (n_steps*batch_size, n_input)
     x = tf.reshape(x, [-1, n_input])
     # Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
-    x = tf.split(0, n_steps, x)
+    x = tf.split(x, n_steps, 0)
 
     # Define lstm cells with tensorflow
     # Forward direction cell
-    lstm_fw_cell = rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0)
+    lstm_fw_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
     # Backward direction cell
-    lstm_bw_cell = rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0)
+    lstm_bw_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
 
     # Get lstm cell output
     try:
-        outputs, _, _ = rnn.bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
+        outputs, _, _ = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
                                               dtype=tf.float32)
     except Exception: # Old TensorFlow version only returns outputs not states
-        outputs = rnn.bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
+        outputs = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
                                         dtype=tf.float32)
 
     # Linear activation, using rnn inner loop last output
@@ -82,15 +82,15 @@ def BiRNN(x, weights, biases):
 pred = BiRNN(x, weights, biases)
 
 # Define loss and optimizer
-cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
 
 # Evaluate model
 correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
 accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/3_NeuralNetworks/convolutional_network.py

@@ -96,15 +96,15 @@ def conv_net(x, weights, biases, dropout):
 pred = conv_net(x, weights, biases, keep_prob)
 
 # Define loss and optimizer
-cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
 
 # Evaluate model
 correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
 accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/3_NeuralNetworks/multilayer_perceptron.py

@@ -60,11 +60,11 @@ def multilayer_perceptron(x, weights, biases):
 pred = multilayer_perceptron(x, weights, biases)
 
 # Define loss and optimizer
-cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/3_NeuralNetworks/recurrent_network.py

@@ -10,7 +10,7 @@
 from __future__ import print_function
 
 import tensorflow as tf
-from tensorflow.python.ops import rnn, rnn_cell
+from tensorflow.contrib import rnn
 
 # Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
@@ -58,29 +58,29 @@ def RNN(x, weights, biases):
     # Reshaping to (n_steps*batch_size, n_input)
     x = tf.reshape(x, [-1, n_input])
     # Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
-    x = tf.split(0, n_steps, x)
+    x = tf.split(x, n_steps, 0)
 
     # Define a lstm cell with tensorflow
-    lstm_cell = rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0)
+    lstm_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
 
     # Get lstm cell output
-    outputs, states = rnn.rnn(lstm_cell, x, dtype=tf.float32)
+    outputs, states = rnn.static_rnn(lstm_cell, x, dtype=tf.float32)
 
     # Linear activation, using rnn inner loop last output
     return tf.matmul(outputs[-1], weights['out']) + biases['out']
 
 pred = RNN(x, weights, biases)
 
 # Define loss and optimizer
-cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
 
 # Evaluate model
 correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
 accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # Launch the graph
 with tf.Session() as sess:

examples/4_Utils/save_restore_model.py

@@ -11,7 +11,7 @@
 
 # Import MNIST data
 from tensorflow.examples.tutorials.mnist import input_data
-mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
+mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
 
 import tensorflow as tf
 
@@ -60,11 +60,11 @@ def multilayer_perceptron(x, weights, biases):
 pred = multilayer_perceptron(x, weights, biases)
 
 # Define loss and optimizer
-cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
 
 # Initializing the variables
-init = tf.initialize_all_variables()
+init = tf.global_variables_initializer()
 
 # 'Saver' op to save and restore all the variables
 saver = tf.train.Saver()

examples/4_Utils/tensorboard_advanced.py

@@ -41,12 +41,12 @@ def multilayer_perceptron(x, weights, biases):
     layer_1 = tf.add(tf.matmul(x, weights['w1']), biases['b1'])
     layer_1 = tf.nn.relu(layer_1)
     # Create a summary to visualize the first layer ReLU activation
-    tf.histogram_summary("relu1", layer_1)
+    tf.summary.histogram("relu1", layer_1)
     # Hidden layer with RELU activation
     layer_2 = tf.add(tf.matmul(layer_1, weights['w2']), biases['b2'])
     layer_2 = tf.nn.relu(layer_2)
     # Create another summary to visualize the second layer ReLU activation
-    tf.histogram_summary("relu2", layer_2)
+    tf.summary.histogram("relu2", layer_2)
     # Output layer
     out_layer = tf.add(tf.matmul(layer_2, weights['w3']), biases['b3'])
     return out_layer
@@ -91,24 +91,24 @@ def multilayer_perceptron(x, weights, biases):
 init = tf.initialize_all_variables()
 
 # Create a summary to monitor cost tensor
-tf.scalar_summary("loss", loss)
+tf.summary.scalar("loss", loss)
 # Create a summary to monitor accuracy tensor
-tf.scalar_summary("accuracy", acc)
+tf.summary.scalar("accuracy", acc)
 # Create summaries to visualize weights
 for var in tf.trainable_variables():
-    tf.histogram_summary(var.name, var)
+    tf.summary.histogram(var.name, var)
 # Summarize all gradients
 for grad, var in grads:
-    tf.histogram_summary(var.name + '/gradient', grad)
+    tf.summary.histogram(var.name + '/gradient', grad)
 # Merge all summaries into a single op
-merged_summary_op = tf.merge_all_summaries()
+merged_summary_op = tf.summary.merge_all()
 
 # Launch the graph
 with tf.Session() as sess:
     sess.run(init)
 
     # op to write logs to Tensorboard
-    summary_writer = tf.train.SummaryWriter(logs_path,
+    summary_writer = tf.summary.FileWriter(logs_path,
                                             graph=tf.get_default_graph())
 
     # Training cycle

examples/4_Utils/tensorboard_basic.py

@@ -52,18 +52,18 @@
 init = tf.initialize_all_variables()
 
 # Create a summary to monitor cost tensor
-tf.scalar_summary("loss", cost)
+tf.summary.scalar("loss", cost)
 # Create a summary to monitor accuracy tensor
-tf.scalar_summary("accuracy", acc)
+tf.summary.scalar("accuracy", acc)
 # Merge all summaries into a single op
-merged_summary_op = tf.merge_all_summaries()
+merged_summary_op = tf.summary.merge_all()
 
 # Launch the graph
 with tf.Session() as sess:
     sess.run(init)
 
     # op to write logs to Tensorboard
-    summary_writer = tf.train.SummaryWriter(logs_path, graph=tf.get_default_graph())
+    summary_writer = tf.summary.FileWriter(logs_path, graph=tf.get_default_graph())
 
     # Training cycle
     for epoch in range(training_epochs):