Tensorflow实战笔记：下（RNN）

Word2Vec.py

import collections
import math
import os
import random
import zipfile

import numpy as np
import urllib
import tensorflow as tf

# Step 1: Download the data.
url = 'http://mattmahoney.net/dc/'

def maybe_download(filename, expected_bytes):
  """Download a file if not present, and make sure it's the right size."""
  if not os.path.exists(filename):
    filename, _ = urllib.request.urlretrieve(url + filename, filename)
  statinfo = os.stat(filename)
  if statinfo.st_size == expected_bytes:
    print('Found and verified', filename)
  else:
    print(statinfo.st_size)
    raise Exception(
        'Failed to verify ' + filename + '. Can you get to it with a browser?')
  return filename

filename = maybe_download('text8.zip', 31344016)


# Read the data into a list of strings.
def read_data(filename):
  """Extract the first file enclosed in a zip file as a list of words"""
  with zipfile.ZipFile(filename) as f:
    data = tf.compat.as_str(f.read(f.namelist()[0])).split()
  return data

words = read_data(filename)
print('Data size', len(words))

# Step 2: Build the dictionary and replace rare words with UNK token.
vocabulary_size = 50000

def build_dataset(words):
  count = [['UNK', -1]]
  count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
  dictionary = dict()
  for word, _ in count:
    dictionary[word] = len(dictionary)
  data = list()
  unk_count = 0
  for word in words:
    if word in dictionary:
      index = dictionary[word]
    else:
      index = 0  # dictionary['UNK']
      unk_count += 1
    data.append(index)
  count[0][1] = unk_count
  reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
  return data, count, dictionary, reverse_dictionary

data, count, dictionary, reverse_dictionary = build_dataset(words)
del words  # Hint to reduce memory.
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])

data_index = 0


# Step 3: Function to generate a training batch for the skip-gram model.
def generate_batch(batch_size, num_skips, skip_window):
  global data_index
  assert batch_size % num_skips == 0
  assert num_skips <= 2 * skip_window
  batch = np.ndarray(shape=(batch_size), dtype=np.int32)
  labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
  span = 2 * skip_window + 1 # [ skip_window target skip_window ]
  buffer = collections.deque(maxlen=span)
  for _ in range(span):
    buffer.append(data[data_index])
    data_index = (data_index + 1) % len(data)
  for i in range(batch_size // num_skips):
    target = skip_window  # target label at the center of the buffer
    targets_to_avoid = [ skip_window ]
    for j in range(num_skips):
      while target in targets_to_avoid:
        target = random.randint(0, span - 1)
      targets_to_avoid.append(target)
      batch[i * num_skips + j] = buffer[skip_window]
      labels[i * num_skips + j, 0] = buffer[target]
    buffer.append(data[data_index])
    data_index = (data_index + 1) % len(data)
  return batch, labels

batch, labels = generate_batch(batch_size=8, num_skips=2, skip_window=1)
for i in range(8):
  print(batch[i], reverse_dictionary[batch[i]],
      '->', labels[i, 0], reverse_dictionary[labels[i, 0]])

# Step 4: Build and train a skip-gram model.

batch_size = 128
embedding_size = 128  # Dimension of the embedding vector.
skip_window = 1       # How many words to consider left and right.
num_skips = 2         # How many times to reuse an input to generate a label.

# We pick a random validation set to sample nearest neighbors. Here we limit the
# validation samples to the words that have a low numeric ID, which by
# construction are also the most frequent.
valid_size = 16     # Random set of words to evaluate similarity on.
valid_window = 100  # Only pick dev samples in the head of the distribution.
valid_examples = np.random.choice(valid_window, valid_size, replace=False)
num_sampled = 64    # Number of negative examples to sample.


graph = tf.Graph()
with graph.as_default():

  # Input data.
  train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
  train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
  valid_dataset = tf.constant(valid_examples, dtype=tf.int32)

  # Ops and variables pinned to the CPU because of missing GPU implementation
  with tf.device('/cpu:0'):
    # Look up embeddings for inputs.
    embeddings = tf.Variable(
        tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
    embed = tf.nn.embedding_lookup(embeddings, train_inputs)

    # Construct the variables for the NCE loss
    nce_weights = tf.Variable(
        tf.truncated_normal([vocabulary_size, embedding_size],
                            stddev=1.0 / math.sqrt(embedding_size)))
    nce_biases = tf.Variable(tf.zeros([vocabulary_size]))

  # Compute the average NCE loss for the batch.
  # tf.nce_loss automatically draws a new sample of the negative labels each
  # time we evaluate the loss.
  loss = tf.reduce_mean(
      tf.nn.nce_loss(weights=nce_weights,
                     biases=nce_biases,
                     labels=train_labels,
                     inputs=embed,
                     num_sampled=num_sampled,
                     num_classes=vocabulary_size))

  # Construct the SGD optimizer using a learning rate of 1.0.
  optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)

  # Compute the cosine similarity between minibatch examples and all embeddings.
  norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
  normalized_embeddings = embeddings / norm
  valid_embeddings = tf.nn.embedding_lookup(
      normalized_embeddings, valid_dataset)
  similarity = tf.matmul(
      valid_embeddings, normalized_embeddings, transpose_b=True)

  # Add variable initializer.
  init = tf.global_variables_initializer()

# Step 5: Begin training.
num_steps = 100001

with tf.Session(graph=graph) as session:
  # We must initialize all variables before we use them.
  init.run()
  print("Initialized")

  average_loss = 0
  for step in range(num_steps):
    batch_inputs, batch_labels = generate_batch(
        batch_size, num_skips, skip_window)
    feed_dict = {train_inputs : batch_inputs, train_labels : batch_labels}

    # We perform one update step by evaluating the optimizer op (including it
    # in the list of returned values for session.run()
    _, loss_val = session.run([optimizer, loss], feed_dict=feed_dict)
    average_loss += loss_val

    if step % 2000 == 0:
      if step > 0:
        average_loss /= 2000
      # The average loss is an estimate of the loss over the last 2000 batches.
      print("Average loss at step ", step, ": ", average_loss)
      average_loss = 0

    # Note that this is expensive (~20% slowdown if computed every 500 steps)
    if step % 10000 == 0:
      sim = similarity.eval()
      for i in range(valid_size):
        valid_word = reverse_dictionary[valid_examples[i]]
        top_k = 8 # number of nearest neighbors
        nearest = (-sim[i, :]).argsort()[1:top_k+1]
        log_str = "Nearest to %s:" % valid_word
        for k in range(top_k):
          close_word = reverse_dictionary[nearest[k]]
          log_str = "%s %s," % (log_str, close_word)
        print(log_str)
  final_embeddings = normalized_embeddings.eval()

# Step 6: Visualize the embeddings.

def plot_with_labels(low_dim_embs, labels, filename='tsne.png'):
  assert low_dim_embs.shape[0] >= len(labels), "More labels than embeddings"
  plt.figure(figsize=(18, 18))  #in inches
  for i, label in enumerate(labels):
    x, y = low_dim_embs[i,:]
    plt.scatter(x, y)
    plt.annotate(label,
                 xy=(x, y),
                 xytext=(5, 2),
                 textcoords='offset points',
                 ha='right',
                 va='bottom')

  plt.savefig(filename)

  #%%
try:
  from sklearn.manifold import TSNE
  import matplotlib.pyplot as plt

  tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
  plot_only = 200
  low_dim_embs = tsne.fit_transform(final_embeddings[:plot_only,:])
  labels = [reverse_dictionary[i] for i in range(plot_only)]
  plot_with_labels(low_dim_embs, labels)

except ImportError:
  print("Please install sklearn, matplotlib, and scipy to visualize embeddings.")

LSTM.py

import time
import numpy as np
import tensorflow as tf
import reader

#flags = tf.flags
#logging = tf.logging



#flags.DEFINE_string("save_path", None,
#                    "Model output directory.")
#flags.DEFINE_bool("use_fp16", False,
#                  "Train using 16-bit floats instead of 32bit floats")

#FLAGS = flags.FLAGS


#def data_type():
#  return tf.float16 if FLAGS.use_fp16 else tf.float32


class PTBInput(object):
  """The input data."""

  def __init__(self, config, data, name=None):
    self.batch_size = batch_size = config.batch_size
    self.num_steps = num_steps = config.num_steps
    self.epoch_size = ((len(data) // batch_size) - 1) // num_steps
    self.input_data, self.targets = reader.ptb_producer(
        data, batch_size, num_steps, name=name)


class PTBModel(object):
  """The PTB model."""

  def __init__(self, is_training, config, input_):
    self._input = input_

    batch_size = input_.batch_size
    num_steps = input_.num_steps
    size = config.hidden_size
    vocab_size = config.vocab_size

    # Slightly better results can be obtained with forget gate biases
    # initialized to 1 but the hyperparameters of the model would need to be
    # different than reported in the paper.
    def lstm_cell():
      return tf.contrib.rnn.BasicLSTMCell(
          size, forget_bias=0.0, state_is_tuple=True)
    attn_cell = lstm_cell
    if is_training and config.keep_prob < 1:
      def attn_cell():
        return tf.contrib.rnn.DropoutWrapper(
            lstm_cell(), output_keep_prob=config.keep_prob)
    cell = tf.contrib.rnn.MultiRNNCell(
        [attn_cell() for _ in range(config.num_layers)], state_is_tuple=True)

    self._initial_state = cell.zero_state(batch_size, tf.float32)

    with tf.device("/cpu:0"):
      embedding = tf.get_variable(
          "embedding", [vocab_size, size], dtype=tf.float32)
      inputs = tf.nn.embedding_lookup(embedding, input_.input_data)

    if is_training and config.keep_prob < 1:
      inputs = tf.nn.dropout(inputs, config.keep_prob)

    # Simplified version of models/tutorials/rnn/rnn.py's rnn().
    # This builds an unrolled LSTM for tutorial purposes only.
    # In general, use the rnn() or state_saving_rnn() from rnn.py.
    #
    # The alternative version of the code below is:
    #
    # inputs = tf.unstack(inputs, num=num_steps, axis=1)
    # outputs, state = tf.nn.rnn(cell, inputs,
    #                            initial_state=self._initial_state)
    outputs = []
    state = self._initial_state
    with tf.variable_scope("RNN"):
      for time_step in range(num_steps):
        if time_step > 0: tf.get_variable_scope().reuse_variables()
        (cell_output, state) = cell(inputs[:, time_step, :], state)
        outputs.append(cell_output)

    output = tf.reshape(tf.concat(outputs, 1), [-1, size])
    softmax_w = tf.get_variable(
        "softmax_w", [size, vocab_size], dtype=tf.float32)
    softmax_b = tf.get_variable("softmax_b", [vocab_size], dtype=tf.float32)
    logits = tf.matmul(output, softmax_w) + softmax_b
    loss = tf.contrib.legacy_seq2seq.sequence_loss_by_example(
        [logits],
        [tf.reshape(input_.targets, [-1])],
        [tf.ones([batch_size * num_steps], dtype=tf.float32)])
    self._cost = cost = tf.reduce_sum(loss) / batch_size
    self._final_state = state

    if not is_training:
      return

    self._lr = tf.Variable(0.0, trainable=False)
    tvars = tf.trainable_variables()
    grads, _ = tf.clip_by_global_norm(tf.gradients(cost, tvars),
                                      config.max_grad_norm)
    optimizer = tf.train.GradientDescentOptimizer(self._lr)
    self._train_op = optimizer.apply_gradients(
        zip(grads, tvars),
        global_step=tf.contrib.framework.get_or_create_global_step())

    self._new_lr = tf.placeholder(
        tf.float32, shape=[], name="new_learning_rate")
    self._lr_update = tf.assign(self._lr, self._new_lr)

  def assign_lr(self, session, lr_value):
    session.run(self._lr_update, feed_dict={self._new_lr: lr_value})

  @property
  def input(self):
    return self._input

  @property
  def initial_state(self):
    return self._initial_state

  @property
  def cost(self):
    return self._cost

  @property
  def final_state(self):
    return self._final_state

  @property
  def lr(self):
    return self._lr

  @property
  def train_op(self):
    return self._train_op


class SmallConfig(object):
  """Small config."""
  init_scale = 0.1
  learning_rate = 1.0
  max_grad_norm = 5
  num_layers = 2
  num_steps = 20
  hidden_size = 200
  max_epoch = 4
  max_max_epoch = 13
  keep_prob = 1.0
  lr_decay = 0.5
  batch_size = 20
  vocab_size = 10000


class MediumConfig(object):
  """Medium config."""
  init_scale = 0.05
  learning_rate = 1.0
  max_grad_norm = 5
  num_layers = 2
  num_steps = 35
  hidden_size = 650
  max_epoch = 6
  max_max_epoch = 39
  keep_prob = 0.5
  lr_decay = 0.8
  batch_size = 20
  vocab_size = 10000


class LargeConfig(object):
  """Large config."""
  init_scale = 0.04
  learning_rate = 1.0
  max_grad_norm = 10
  num_layers = 2
  num_steps = 35
  hidden_size = 1500
  max_epoch = 14
  max_max_epoch = 55
  keep_prob = 0.35
  lr_decay = 1 / 1.15
  batch_size = 20
  vocab_size = 10000


class TestConfig(object):
  """Tiny config, for testing."""
  init_scale = 0.1
  learning_rate = 1.0
  max_grad_norm = 1
  num_layers = 1
  num_steps = 2
  hidden_size = 2
  max_epoch = 1
  max_max_epoch = 1
  keep_prob = 1.0
  lr_decay = 0.5
  batch_size = 20
  vocab_size = 10000


def run_epoch(session, model, eval_op=None, verbose=False):
  """Runs the model on the given data."""
  start_time = time.time()
  costs = 0.0
  iters = 0
  state = session.run(model.initial_state)

  fetches = {
      "cost": model.cost,
      "final_state": model.final_state,
  }
  if eval_op is not None:
    fetches["eval_op"] = eval_op

  for step in range(model.input.epoch_size):
    feed_dict = {}
    for i, (c, h) in enumerate(model.initial_state):
      feed_dict[c] = state[i].c
      feed_dict[h] = state[i].h

    vals = session.run(fetches, feed_dict)
    cost = vals["cost"]
    state = vals["final_state"]

    costs += cost
    iters += model.input.num_steps

    if verbose and step % (model.input.epoch_size // 10) == 10:
      print("%.3f perplexity: %.3f speed: %.0f wps" %
            (step * 1.0 / model.input.epoch_size, np.exp(costs / iters),
             iters * model.input.batch_size / (time.time() - start_time)))

  return np.exp(costs / iters)




raw_data = reader.ptb_raw_data('simple-examples/data/')
train_data, valid_data, test_data, _ = raw_data

config = SmallConfig()
eval_config = SmallConfig()
eval_config.batch_size = 1
eval_config.num_steps = 1

with tf.Graph().as_default():
  initializer = tf.random_uniform_initializer(-config.init_scale,
                                              config.init_scale)

  with tf.name_scope("Train"):
    train_input = PTBInput(config=config, data=train_data, name="TrainInput")
    with tf.variable_scope("Model", reuse=None, initializer=initializer):
      m = PTBModel(is_training=True, config=config, input_=train_input)
      #tf.scalar_summary("Training Loss", m.cost)
      #tf.scalar_summary("Learning Rate", m.lr)

  with tf.name_scope("Valid"):
    valid_input = PTBInput(config=config, data=valid_data, name="ValidInput")
    with tf.variable_scope("Model", reuse=True, initializer=initializer):
      mvalid = PTBModel(is_training=False, config=config, input_=valid_input)
      #tf.scalar_summary("Validation Loss", mvalid.cost)

  with tf.name_scope("Test"):
    test_input = PTBInput(config=eval_config, data=test_data, name="TestInput")
    with tf.variable_scope("Model", reuse=True, initializer=initializer):
      mtest = PTBModel(is_training=False, config=eval_config,
                       input_=test_input)

  sv = tf.train.Supervisor()
  with sv.managed_session() as session:
    for i in range(config.max_max_epoch):
      lr_decay = config.lr_decay ** max(i + 1 - config.max_epoch, 0.0)
      m.assign_lr(session, config.learning_rate * lr_decay)

      print("Epoch: %d Learning rate: %.3f" % (i + 1, session.run(m.lr)))
      train_perplexity = run_epoch(session, m, eval_op=m.train_op,
                                   verbose=True)
      print("Epoch: %d Train Perplexity: %.3f" % (i + 1, train_perplexity))
      valid_perplexity = run_epoch(session, mvalid)
      print("Epoch: %d Valid Perplexity: %.3f" % (i + 1, valid_perplexity))

    test_perplexity = run_epoch(session, mtest)
    print("Test Perplexity: %.3f" % test_perplexity)

     # if FLAGS.save_path:
     #   print("Saving model to %s." % FLAGS.save_path)
     #   sv.saver.save(session, FLAGS.save_path, global_step=sv.global_step)

#if __name__ == "__main__":
#  tf.app.run()

BiRNN.py

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}))