#%% # Copyright 2015 The TensorFlow Authors. All Rights Reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # ============================================================================== import tensorflow as tf import numpy as np # Import MINST data from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("/tmp/data/", one_hot=True) # Parameters learning_rate = 0.01 max_samples = 400000 batch_size = 128 display_step = 10 # Network Parameters n_input = 28 # MNIST data input (img shape: 28*28) n_steps = 28 # timesteps n_hidden = 256 # hidden layer num of features n_classes = 10 # MNIST total classes (0-9 digits) # tf Graph input x = tf.placeholder("float", [None, n_steps, n_input]) y = tf.placeholder("float", [None, n_classes]) # Define weights weights = { # Hidden layer weights => 2*n_hidden because of foward + backward cells 'out': tf.Variable(tf.random_normal([2*n_hidden, n_classes])) } biases = { 'out': tf.Variable(tf.random_normal([n_classes])) } def BiRNN(x, weights, biases): # Prepare data shape to match `bidirectional_rnn` function requirements # Current data input shape: (batch_size, n_steps, n_input) # Required shape: 'n_steps' tensors list of shape (batch_size, n_input) # Permuting batch_size and n_steps x = tf.transpose(x, [1, 0, 2]) # 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(x, n_steps) # Define lstm cells with tensorflow # Forward direction cell lstm_fw_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0) # Backward direction cell lstm_bw_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0) # Get lstm cell output # try: outputs, _, _ = tf.contrib.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, # dtype=tf.float32) # Linear activation, using rnn inner loop last output return tf.matmul(outputs[-1], weights['out']) + biases['out'] pred = BiRNN(x, weights, biases) # Define loss and optimizer 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.global_variables_initializer() # Launch the graph with tf.Session() as sess: sess.run(init) step = 1 # Keep training until reach max iterations while step * batch_size < max_samples: batch_x, batch_y = mnist.train.next_batch(batch_size) # Reshape data to get 28 seq of 28 elements batch_x = batch_x.reshape((batch_size, n_steps, n_input)) # Run optimization op (backprop) sess.run(optimizer, feed_dict={x: batch_x, y: batch_y}) if step % display_step == 0: # Calculate batch accuracy acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y}) # Calculate batch loss loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y}) print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \ "{:.6f}".format(loss) + ", Training Accuracy= " + \ "{:.5f}".format(acc)) step += 1 print("Optimization Finished!") # Calculate accuracy for 128 mnist test images test_len = 10000 test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input)) test_label = mnist.test.labels[:test_len] print("Testing Accuracy:", \ sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
7_3_BiRNN.py
最新推荐文章于 2022-07-05 10:39:00 发布