In this project, you’re going to take a peek into the realm of neural network machine translation. You’ll be training a sequence to sequence model on a dataset of English and French sentences that can translate new sentences from English to French.
Since translating the whole language of English to French will take lots of time to train, we have provided you with a small portion of the English corpus.
In [1]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper
import problem_unittests as tests
source_path = 'data/small_vocab_en'
target_path = 'data/small_vocab_fr'
source_text = helper.load_data(source_path)
target_text = helper.load_data(target_path)
In [2]:
view_sentence_range = (0, 10)
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np
print('Dataset Stats')
print('Roughly the number of unique words: {}'.format(len({word: None for word in source_text.split()})))
sentences = source_text.split('\n')
word_counts = [len(sentence.split()) for sentence in sentences]
print('Number of sentences: {}'.format(len(sentences)))
print('Average number of words in a sentence: {}'.format(np.average(word_counts)))
print()
print('English sentences {} to {}:'.format(*view_sentence_range))
print('\n'.join(source_text.split('\n')[view_sentence_range[0]:view_sentence_range[1]]))
print()
print('French sentences {} to {}:'.format(*view_sentence_range))
print('\n'.join(target_text.split('\n')[view_sentence_range[0]:view_sentence_range[1]]))
As you did with other RNNs, you must turn the text into a number so the computer can understand it. In the function text_to_ids(), you'll turn source_text and target_text from words to ids. However, you need to add the <EOS> word id at the end of target_text. This will help the neural network predict when the sentence should end.
You can get the <EOS> word id by doing:
target_vocab_to_int['<EOS>']
You can get other word ids using source_vocab_to_int and target_vocab_to_int.
In [3]:
def text_to_ids(source_text, target_text, source_vocab_to_int, target_vocab_to_int):
"""
Convert source and target text to proper word ids
:param source_text: String that contains all the source text.
:param target_text: String that contains all the target text.
:param source_vocab_to_int: Dictionary to go from the source words to an id
:param target_vocab_to_int: Dictionary to go from the target words to an id
:return: A tuple of lists (source_id_text, target_id_text)
"""
eos = target_vocab_to_int['<EOS>']
source_sentences = [s for s in source_text.split('\n')]
target_sentences = [s for s in target_text.split('\n')]
#print(eos)
#print(source_sentences)
#print(target_sentences)
source_id_text = [[source_vocab_to_int[w] for w in s.split()] for s in source_sentences]
target_id_text = [[target_vocab_to_int[w] for w in s.split()] + [eos] for s in target_sentences]
return source_id_text, target_id_text
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_text_to_ids(text_to_ids)
In [4]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
helper.preprocess_and_save_data(source_path, target_path, text_to_ids)
In [5]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np
import helper
import problem_unittests as tests
(source_int_text, target_int_text), (source_vocab_to_int, target_vocab_to_int), _ = helper.load_preprocess()
In [6]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from distutils.version import LooseVersion
import warnings
import tensorflow as tf
from tensorflow.python.layers.core import Dense
# Check TensorFlow Version
assert LooseVersion(tf.__version__) >= LooseVersion('1.1'), 'Please use TensorFlow version 1.1 or newer'
print('TensorFlow Version: {}'.format(tf.__version__))
# Check for a GPU
if not tf.test.gpu_device_name():
warnings.warn('No GPU found. Please use a GPU to train your neural network.')
else:
print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))
You'll build the components necessary to build a Sequence-to-Sequence model by implementing the following functions below:
model_inputsprocess_decoder_inputencoding_layerdecoding_layer_traindecoding_layer_inferdecoding_layerseq2seq_modelImplement the model_inputs() function to create TF Placeholders for the Neural Network. It should create the following placeholders:
Return the placeholders in the following the tuple (input, targets, learning rate, keep probability, target sequence length, max target sequence length, source sequence length)
In [7]:
def model_inputs():
"""
Create TF Placeholders for input, targets, learning rate, and lengths of source and target sequences.
:return: Tuple (input, targets, learning rate, keep probability, target sequence length,
max target sequence length, source sequence length)
"""
input_data = tf.placeholder(tf.int32, [None, None], name='input')
targets = tf.placeholder(tf.int32, [None, None], name='target')
learning_rate = tf.placeholder(tf.float32, name='learning_rate')
keep_probability = tf.placeholder(tf.float32, None, name='keep_prob')
target_squence_length = tf.placeholder(tf.int32, (None,), name='target_sequence_length')
max_target_sequence_length = tf.reduce_max(target_squence_length, name='max_target_len')
source_sequence_length = tf.placeholder(tf.int32, (None,), name='source_sequence_length')
return (input_data,
targets,
learning_rate,
keep_probability,
target_squence_length,
max_target_sequence_length,
source_sequence_length)
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_inputs(model_inputs)
In [8]:
def process_decoder_input(target_data, target_vocab_to_int, batch_size):
"""
Preprocess target data for encoding
:param target_data: Target Placehoder
:param target_vocab_to_int: Dictionary to go from the target words to an id
:param batch_size: Batch Size
:return: Preprocessed target data
"""
ending = tf.strided_slice(target_data, [0, 0], [batch_size, -1], [1, 1])
dec_input = tf.concat([tf.fill([batch_size, 1], target_vocab_to_int['<GO>']), ending], 1)
return dec_input
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_process_encoding_input(process_decoder_input)
Implement encoding_layer() to create a Encoder RNN layer:
tf.contrib.layers.embed_sequencetf.contrib.rnn.LSTMCell wrapped in a tf.contrib.rnn.DropoutWrappertf.nn.dynamic_rnn()
In [9]:
def make_stacked_lstm_rnn_cell(rnn_size, num_layers, keep_prob):
def rnn_cell(rnn_size):
# Construct a stacked tf.contrib.rnn.LSTMCell
# __init__(num_units, use_peepholes=False, cell_clip=None, initializer=None,
# num_proj=None, proj_clip=None, num_unit_shards=None, num_proj_shards=None,
# forget_bias=1.0, state_is_tuple=True, activation=None, reuse=None)
lstm_cell = tf.contrib.rnn.LSTMCell(rnn_size, initializer=tf.random_uniform_initializer(-0.1, 0.1, seed=2))
# wrapped in a tf.contrib.rnn.DropoutWrapper
# __init__(cell, input_keep_prob=1.0, output_keep_prob=1.0, state_keep_prob=1.0,
# variational_recurrent=False, input_size=None, dtype=None, seed=None)
return tf.contrib.rnn.DropoutWrapper(lstm_cell, keep_prob, keep_prob, keep_prob)
# stacked_lstm = tf.contrib.rnn.MultiRNNCell([lstm_cell() for _ in range(number_of_layers)])
stacked_lstm_cell = tf.contrib.rnn.MultiRNNCell([rnn_cell(rnn_size) for _ in range(num_layers)])
return stacked_lstm_cell
In [10]:
from imp import reload
reload(tests)
def encoding_layer(rnn_inputs, rnn_size, num_layers, keep_prob,
source_sequence_length, source_vocab_size,
encoding_embedding_size):
"""
Create encoding layer
:param rnn_inputs: Inputs for the RNN
:param rnn_size: RNN Size
:param num_layers: Number of layers
:param keep_prob: Dropout keep probability
:param source_sequence_length: a list of the lengths of each sequence in the batch
:param source_vocab_size: vocabulary size of source data
:param encoding_embedding_size: embedding size of source data
:return: tuple (RNN output, RNN state)
"""
# Encoder embedding - Embed the encoder input using tf.contrib.layers.embed_sequence
# embed_sequence(ids, vocab_size=None, embed_dim=None, unique=False, initializer=None, regularizer=None, trainable=True, scope=None, reuse=None)
# Returns: Tensor of [batch_size, doc_length, embed_dim] with embedded sequences.'''
enc_embed_input = tf.contrib.layers.embed_sequence(rnn_inputs, source_vocab_size, encoding_embedding_size)
# Construct a stacked tf.contrib.rnn.LSTMCell wrapped in a tf.contrib.rnn.DropoutWrapper
stacked_cell = make_stacked_lstm_rnn_cell(rnn_size, num_layers, keep_prob)
# Pass cell and embedded input to tf.nn.dynamic_rnn()
# dynamic_rnn(cell, inputs, sequence_length=None, initial_state=None, dtype=None, parallel_iterations=None, swap_memory=False, time_major=False, scope=None)
# Returns: A pair (outputs, state)
return tf.nn.dynamic_rnn(stacked_cell, enc_embed_input, sequence_length=source_sequence_length, dtype=tf.float32)
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_encoding_layer(encoding_layer)
Create a training decoding layer:
tf.contrib.seq2seq.TrainingHelper tf.contrib.seq2seq.BasicDecodertf.contrib.seq2seq.dynamic_decode
In [11]:
def decoding_layer_train(encoder_state, dec_cell, dec_embed_input,
target_sequence_length, max_summary_length,
output_layer, keep_prob):
"""
Create a decoding layer for training
:param encoder_state: Encoder State
:param dec_cell: Decoder RNN Cell
:param dec_embed_input: Decoder embedded input
:param target_sequence_length: The lengths of each sequence in the target batch
:param max_summary_length: The length of the longest sequence in the batch
:param output_layer: Function to apply the output layer
:param keep_prob: Dropout keep probability
:return: BasicDecoderOutput containing training logits and sample_id
"""
# Create a tf.contrib.seq2seq.TrainingHelper
# __init__(inputs, sequence_length, time_major=False, name=None)
training_helper = tf.contrib.seq2seq.TrainingHelper(inputs=dec_embed_input,
sequence_length=target_sequence_length,
time_major=False)
# Create a tf.contrib.seq2seq.BasicDecoder
# __init__(cell, helper, initial_state, output_layer=None)
training_decoder = tf.contrib.seq2seq.BasicDecoder(dec_cell, training_helper, encoder_state, output_layer)
# Obtain the decoder outputs from tf.contrib.seq2seq.dynamic_decode
# dynamic_decode(decoder, output_time_major=False, impute_finished=False, maximum_iterations=None, parallel_iterations=32, swap_memory=False, scope=None)
# Returns: (final_outputs, final_state, final_sequence_lengths)
training_decoder_output, _ = tf.contrib.seq2seq.dynamic_decode(training_decoder, impute_finished=True,
maximum_iterations=max_summary_length)
return training_decoder_output
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_decoding_layer_train(decoding_layer_train)
Create inference decoder:
tf.contrib.seq2seq.GreedyEmbeddingHelpertf.contrib.seq2seq.BasicDecodertf.contrib.seq2seq.dynamic_decode
In [12]:
def decoding_layer_infer(encoder_state, dec_cell, dec_embeddings, start_of_sequence_id,
end_of_sequence_id, max_target_sequence_length,
vocab_size, output_layer, batch_size, keep_prob):
"""
Create a decoding layer for inference
:param encoder_state: Encoder state
:param dec_cell: Decoder RNN Cell
:param dec_embeddings: Decoder embeddings
:param start_of_sequence_id: GO ID
:param end_of_sequence_id: EOS Id
:param max_target_sequence_length: Maximum length of target sequences
:param vocab_size: Size of decoder/target vocabulary
:param decoding_scope: TenorFlow Variable Scope for decoding
:param output_layer: Function to apply the output layer
:param batch_size: Batch size
:param keep_prob: Dropout keep probability
:return: BasicDecoderOutput containing inference logits and sample_id
"""
# Create a tf.contrib.seq2seq.GreedyEmbeddingHelper
# __init__(embedding, start_tokens, end_token)
# embedding: A callable that takes a vector tensor of ids (argmax ids), or the params argument for embedding_lookup. The returned tensor will be passed to the decoder input.
# start_tokens: int32 vector shaped [batch_size], the start tokens.
# end_token: int32 scalar, the token that marks end of decoding.
start_tokens = tf.tile(tf.constant([start_of_sequence_id], dtype=tf.int32), [batch_size], name='start_tokens')
inference_helper = tf.contrib.seq2seq.GreedyEmbeddingHelper(dec_embeddings, start_tokens, end_of_sequence_id)
# Create a tf.contrib.seq2seq.BasicDecoder
# __init__(cell, helper, initial_state, output_layer=None)
# cell: An RNNCell instance.
# helper: A Helper instance.
# initial_state: A (possibly nested tuple of...) tensors and TensorArrays. The initial state of the RNNCell.
# output_layer: (Optional) An instance of tf.layers.Layer, i.e., tf.layers.Dense. Optional layer to apply to the RNN output prior to storing the result or sampling.
inference_decoder = tf.contrib.seq2seq.BasicDecoder(dec_cell, inference_helper, encoder_state, output_layer)
# Obtain the decoder outputs from tf.contrib.seq2seq.dynamic_decode
# dynamic_decode(decoder, output_time_major=False, impute_finished=False, maximum_iterations=None, parallel_iterations=32, swap_memory=False, scope=None)
# Returns: (final_outputs, final_state, final_sequence_lengths)
decoder_output, _ = tf.contrib.seq2seq.dynamic_decode(inference_decoder,
impute_finished=True,
maximum_iterations=max_target_sequence_length)
return decoder_output
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_decoding_layer_infer(decoding_layer_infer)
Implement decoding_layer() to create a Decoder RNN layer.
decoding_layer_train(encoder_state, dec_cell, dec_embed_input, target_sequence_length, max_target_sequence_length, output_layer, keep_prob) function to get the training logits.decoding_layer_infer(encoder_state, dec_cell, dec_embeddings, start_of_sequence_id, end_of_sequence_id, max_target_sequence_length, vocab_size, output_layer, batch_size, keep_prob) function to get the inference logits.Note: You'll need to use tf.variable_scope to share variables between training and inference.
In [13]:
# Construct the decoder LSTM cell (just like you constructed the encoder cell above)
def decode_stacked_lstm_rnn_cell(rnn_size, num_layers, keep_prob=1.0): # remove keep_prob?
def rnn_cell(rnn_size):
# Construct a stacked tf.contrib.rnn.LSTMCell
# __init__(num_units, use_peepholes=False, cell_clip=None, initializer=None,
# num_proj=None, proj_clip=None, num_unit_shards=None, num_proj_shards=None,
# forget_bias=1.0, state_is_tuple=True, activation=None, reuse=None)
lstm_cell = tf.contrib.rnn.LSTMCell(rnn_size, initializer=tf.random_uniform_initializer(-0.1, 0.1, seed=2))
# wrapped in a tf.contrib.rnn.DropoutWrapper
# __init__(cell, input_keep_prob=1.0, output_keep_prob=1.0, state_keep_prob=1.0,
# variational_recurrent=False, input_size=None, dtype=None, seed=None)
# return tf.contrib.rnn.DropoutWrapper(lstm_cell, keep_prob, keep_prob, keep_prob)
return lstm_cell
# stacked_lstm = tf.contrib.rnn.MultiRNNCell([lstm_cell() for _ in range(number_of_layers)])
decoded_lstm_cell = tf.contrib.rnn.MultiRNNCell([rnn_cell(rnn_size) for _ in range(num_layers)])
return decoded_lstm_cell
In [15]:
def decoding_layer(dec_input, encoder_state,
target_sequence_length, max_target_sequence_length,
rnn_size,
num_layers, target_vocab_to_int, target_vocab_size,
batch_size, keep_prob, decoding_embedding_size):
"""
Create decoding layer
:param dec_input: Decoder input
:param encoder_state: Encoder state
:param target_sequence_length: The lengths of each sequence in the target batch
:param max_target_sequence_length: Maximum length of target sequences
:param rnn_size: RNN Size
:param num_layers: Number of layers
:param target_vocab_to_int: Dictionary to go from the target words to an id
:param target_vocab_size: Size of target vocabulary
:param batch_size: The size of the batch
:param keep_prob: Dropout keep probability
:param decoding_embedding_size: Decoding embedding size
:return: Tuple of (Training BasicDecoderOutput, Inference BasicDecoderOutput)
"""
# Embed the target sequences
decoder_embeddings = tf.Variable(tf.random_uniform([target_vocab_size, decoding_embedding_size]))
decoder_embeddings_input = tf.nn.embedding_lookup(decoder_embeddings, dec_input)
# Construct the decoder LSTM cell (just like you constructed the encoder cell above)
decoded_cell = decode_stacked_lstm_rnn_cell(rnn_size, num_layers)
# Create an output layer to map the outputs of the decoder to the elements of our vocabulary
output_layer = Dense(target_vocab_size,
kernel_initializer=tf.truncated_normal_initializer(mean=0.0, stddev=0.1))
# Use the your decoding_layer_train(encoder_state, dec_cell, dec_embed_input, target_sequence_length,
# max_target_sequence_length, output_layer, keep_prob) function to get the training logits.
with tf.variable_scope("decoding") as training_scope:
training_logits = decoding_layer_train(encoder_state, decoded_cell, decoder_embeddings_input,
target_sequence_length, max_target_sequence_length,
output_layer, keep_prob)
# Use your decoding_layer_infer(encoder_state, dec_cell, dec_embeddings, start_of_sequence_id,
# end_of_sequence_id, max_target_sequence_length, vocab_size, output_layer, batch_size, keep_prob)
# function to get the inference logits.
start_of_sequence_id = target_vocab_to_int['<GO>']
end_of_sequence_id = target_vocab_to_int['<EOS>']
with tf.variable_scope("decoding", reuse=True) as inference_scope:
inference_logits = decoding_layer_infer(encoder_state, decoded_cell, decoder_embeddings,
start_of_sequence_id, end_of_sequence_id,
max_target_sequence_length, target_vocab_size,
output_layer, batch_size, keep_prob)
return training_logits, inference_logits
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_decoding_layer(decoding_layer)
Apply the functions you implemented above to:
encoding_layer(rnn_inputs, rnn_size, num_layers, keep_prob, source_sequence_length, source_vocab_size, encoding_embedding_size).process_decoder_input(target_data, target_vocab_to_int, batch_size) function.decoding_layer(dec_input, enc_state, target_sequence_length, max_target_sentence_length, rnn_size, num_layers, target_vocab_to_int, target_vocab_size, batch_size, keep_prob, dec_embedding_size) function.
In [18]:
def seq2seq_model(input_data, target_data, keep_prob, batch_size,
source_sequence_length, target_sequence_length,
max_target_sentence_length,
source_vocab_size, target_vocab_size,
enc_embedding_size, dec_embedding_size,
rnn_size, num_layers, target_vocab_to_int):
"""
Build the Sequence-to-Sequence part of the neural network
:param input_data: Input placeholder
:param target_data: Target placeholder
:param keep_prob: Dropout keep probability placeholder
:param batch_size: Batch Size
:param source_sequence_length: Sequence Lengths of source sequences in the batch
:param target_sequence_length: Sequence Lengths of target sequences in the batch
:param source_vocab_size: Source vocabulary size
:param target_vocab_size: Target vocabulary size
:param enc_embedding_size: Decoder embedding size
:param dec_embedding_size: Encoder embedding size
:param rnn_size: RNN Size
:param num_layers: Number of layers
:param target_vocab_to_int: Dictionary to go from the target words to an id
:return: Tuple of (Training BasicDecoderOutput, Inference BasicDecoderOutput)
"""
# Encode the input using your encoding_layer(rnn_inputs, rnn_size, num_layers, keep_prob,
# source_sequence_length, source_vocab_size, encoding_embedding_size).
# Returns: A pair (outputs, state)
enc_output, enc_state = encoding_layer(input_data, rnn_size, num_layers, keep_prob,
source_sequence_length, source_vocab_size, enc_embedding_size)
# Process target data using your process_decoder_input(target_data, target_vocab_to_int, batch_size) function.
# Returns: Preprocessed target data
# ending = tf.strided_slice(target_data, [0, 0], [batch_size, -1], [1, 1])
# return = tf.concat([tf.fill([batch_size, 1], target_vocab_to_int['<GO>']), ending], 1)
dec_input = process_decoder_input(target_data, target_vocab_to_int, batch_size)
# Decode the encoded input using your decoding_layer(dec_input, enc_state, target_sequence_length,
# max_target_sentence_length, rnn_size, num_layers, target_vocab_to_int, target_vocab_size,
# batch_size, keep_prob, dec_embedding_size) function.
# Returns: Tuple of (Training BasicDecoderOutput, Inference BasicDecoderOutput)
training_output, inference_output = decoding_layer(dec_input, enc_state, target_sequence_length,
max_target_sentence_length, rnn_size, num_layers,
target_vocab_to_int, target_vocab_size,
batch_size, keep_prob, dec_embedding_size)
return training_output, inference_output
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_seq2seq_model(seq2seq_model)
Tune the following parameters:
epochs to the number of epochs.batch_size to the batch size.rnn_size to the size of the RNNs.num_layers to the number of layers.encoding_embedding_size to the size of the embedding for the encoder.decoding_embedding_size to the size of the embedding for the decoder.learning_rate to the learning rate.keep_probability to the Dropout keep probabilitydisplay_step to state how many steps between each debug output statement
In [33]:
# Number of Epochs
epochs = 10
# Batch Size
batch_size = 134
# RNN Size
rnn_size = 512
# Number of Layers
num_layers = 2
# Embedding Size
encoding_embedding_size = 269
decoding_embedding_size = 269
# Learning Rate
learning_rate = 0.001
# Dropout Keep Probability
keep_probability = 0.8
display_step = 25
In [34]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
save_path = 'checkpoints/dev'
(source_int_text, target_int_text), (source_vocab_to_int, target_vocab_to_int), _ = helper.load_preprocess()
max_target_sentence_length = max([len(sentence) for sentence in source_int_text])
train_graph = tf.Graph()
with train_graph.as_default():
input_data, targets, lr, keep_prob, target_sequence_length, max_target_sequence_length, source_sequence_length = model_inputs()
#sequence_length = tf.placeholder_with_default(max_target_sentence_length, None, name='sequence_length')
input_shape = tf.shape(input_data)
train_logits, inference_logits = seq2seq_model(tf.reverse(input_data, [-1]),
targets,
keep_prob,
batch_size,
source_sequence_length,
target_sequence_length,
max_target_sequence_length,
len(source_vocab_to_int),
len(target_vocab_to_int),
encoding_embedding_size,
decoding_embedding_size,
rnn_size,
num_layers,
target_vocab_to_int)
training_logits = tf.identity(train_logits.rnn_output, name='logits')
inference_logits = tf.identity(inference_logits.sample_id, name='predictions')
masks = tf.sequence_mask(target_sequence_length, max_target_sequence_length, dtype=tf.float32, name='masks')
with tf.name_scope("optimization"):
# Loss function
cost = tf.contrib.seq2seq.sequence_loss(
training_logits,
targets,
masks)
# Optimizer
optimizer = tf.train.AdamOptimizer(lr)
# Gradient Clipping
gradients = optimizer.compute_gradients(cost)
capped_gradients = [(tf.clip_by_value(grad, -1., 1.), var) for grad, var in gradients if grad is not None]
train_op = optimizer.apply_gradients(capped_gradients)
Batch and pad the source and target sequences
In [35]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
def pad_sentence_batch(sentence_batch, pad_int):
"""Pad sentences with <PAD> so that each sentence of a batch has the same length"""
max_sentence = max([len(sentence) for sentence in sentence_batch])
return [sentence + [pad_int] * (max_sentence - len(sentence)) for sentence in sentence_batch]
def get_batches(sources, targets, batch_size, source_pad_int, target_pad_int):
"""Batch targets, sources, and the lengths of their sentences together"""
for batch_i in range(0, len(sources)//batch_size):
start_i = batch_i * batch_size
# Slice the right amount for the batch
sources_batch = sources[start_i:start_i + batch_size]
targets_batch = targets[start_i:start_i + batch_size]
# Pad
pad_sources_batch = np.array(pad_sentence_batch(sources_batch, source_pad_int))
pad_targets_batch = np.array(pad_sentence_batch(targets_batch, target_pad_int))
# Need the lengths for the _lengths parameters
pad_targets_lengths = []
for target in pad_targets_batch:
pad_targets_lengths.append(len(target))
pad_source_lengths = []
for source in pad_sources_batch:
pad_source_lengths.append(len(source))
yield pad_sources_batch, pad_targets_batch, pad_source_lengths, pad_targets_lengths
In [36]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
def get_accuracy(target, logits):
"""
Calculate accuracy
"""
max_seq = max(target.shape[1], logits.shape[1])
if max_seq - target.shape[1]:
target = np.pad(
target,
[(0,0),(0,max_seq - target.shape[1])],
'constant')
if max_seq - logits.shape[1]:
logits = np.pad(
logits,
[(0,0),(0,max_seq - logits.shape[1])],
'constant')
return np.mean(np.equal(target, logits))
# Split data to training and validation sets
train_source = source_int_text[batch_size:]
train_target = target_int_text[batch_size:]
valid_source = source_int_text[:batch_size]
valid_target = target_int_text[:batch_size]
(valid_sources_batch, valid_targets_batch, valid_sources_lengths, valid_targets_lengths ) = next(get_batches(valid_source,
valid_target,
batch_size,
source_vocab_to_int['<PAD>'],
target_vocab_to_int['<PAD>']))
with tf.Session(graph=train_graph) as sess:
sess.run(tf.global_variables_initializer())
loss_list = []
valid_acc_list = []
for epoch_i in range(epochs):
for batch_i, (source_batch, target_batch, sources_lengths, targets_lengths) in enumerate(
get_batches(train_source, train_target, batch_size,
source_vocab_to_int['<PAD>'],
target_vocab_to_int['<PAD>'])):
_, loss = sess.run(
[train_op, cost],
{input_data: source_batch,
targets: target_batch,
lr: learning_rate,
target_sequence_length: targets_lengths,
source_sequence_length: sources_lengths,
keep_prob: keep_probability})
loss_list.append(loss)
if batch_i % display_step == 0 and batch_i > 0:
batch_train_logits = sess.run(
inference_logits,
{input_data: source_batch,
source_sequence_length: sources_lengths,
target_sequence_length: targets_lengths,
keep_prob: 1.0})
batch_valid_logits = sess.run(
inference_logits,
{input_data: valid_sources_batch,
source_sequence_length: valid_sources_lengths,
target_sequence_length: valid_targets_lengths,
keep_prob: 1.0})
train_acc = get_accuracy(target_batch, batch_train_logits)
valid_acc = get_accuracy(valid_targets_batch, batch_valid_logits)
valid_acc_list.append(valid_acc)
print('Epoch {:>3} Batch {:>4}/{} - Train Accuracy: {:>6.4f}, Validation Accuracy: {:>6.4f}, Loss: {:>6.4f}'
.format(epoch_i, batch_i, len(source_int_text) // batch_size, train_acc, valid_acc, loss))
# Save Model
saver = tf.train.Saver()
saver.save(sess, save_path)
print('Model Trained and Saved')
In [37]:
# Visualize the loss and accuracy
import matplotlib.pyplot as plt
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(18, 6))
ax1.plot(loss_list, color='red')
ax1.set_title('Traning Loss')
ax1.set_ylabel('Loss value')
ax2.plot(valid_acc_list)
ax2.set_xlabel('Iterations')
ax2.set_ylabel('Accuracy')
ax2.set_title('Validation Accuracy')
plt.show()
In [38]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
# Save parameters for checkpoint
helper.save_params(save_path)
In [39]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import tensorflow as tf
import numpy as np
import helper
import problem_unittests as tests
_, (source_vocab_to_int, target_vocab_to_int), (source_int_to_vocab, target_int_to_vocab) = helper.load_preprocess()
load_path = helper.load_params()
To feed a sentence into the model for translation, you first need to preprocess it. Implement the function sentence_to_seq() to preprocess new sentences.
vocab_to_int<UNK> word id.
In [40]:
def sentence_to_seq(sentence, vocab_to_int):
"""
Convert a sentence to a sequence of ids
:param sentence: String
:param vocab_to_int: Dictionary to go from the words to an id
:return: List of word ids
"""
# Convert the sentence to lowercase
slower = sentence.lower()
# Convert words into ids using vocab_to_int
word_ids = []
for s in slower.split():
# Convert words not in the vocabulary, to the <UNK> word id.
if s not in vocab_to_int:
s = '<UNK>'
word_ids.append(vocab_to_int[s])
return word_ids
"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_sentence_to_seq(sentence_to_seq)
In [48]:
#translate_sentence = 'he saw a old yellow truck .' # il a vu un vieux camion jaune = He saw an old yellow truck
#translate_sentence = 'what a beautiful day' # californie est beau au mois de hiver = California is beautiful in winter
#translate_sentence = 'what time is it' # chine est sec en septembre , et il = China is dry in September, and
#translate_sentence = 'lets go for a ride' # elle est au volant d' une petite voiture rouge = She is driving a small red car
#translate_sentence = 'lets watch a movie' # elle aime une une voiture rouge = She likes a red car
translate_sentence = 'have a great day' # elle est généralement beau en californie = She is generally beautiful in california
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
translate_sentence = sentence_to_seq(translate_sentence, source_vocab_to_int)
loaded_graph = tf.Graph()
with tf.Session(graph=loaded_graph) as sess:
# Load saved model
loader = tf.train.import_meta_graph(load_path + '.meta')
loader.restore(sess, load_path)
input_data = loaded_graph.get_tensor_by_name('input:0')
logits = loaded_graph.get_tensor_by_name('predictions:0')
target_sequence_length = loaded_graph.get_tensor_by_name('target_sequence_length:0')
source_sequence_length = loaded_graph.get_tensor_by_name('source_sequence_length:0')
keep_prob = loaded_graph.get_tensor_by_name('keep_prob:0')
translate_logits = sess.run(logits, {input_data: [translate_sentence]*batch_size,
target_sequence_length: [len(translate_sentence)*2]*batch_size,
source_sequence_length: [len(translate_sentence)]*batch_size,
keep_prob: 1.0})[0]
print('Input')
print(' Word Ids: {}'.format([i for i in translate_sentence]))
print(' English Words: {}'.format([source_int_to_vocab[i] for i in translate_sentence]))
print('\nPrediction')
print(' Word Ids: {}'.format([i for i in translate_logits]))
print(' French Words: {}'.format(" ".join([target_int_to_vocab[i] for i in translate_logits])))
You might notice that some sentences translate better than others. Since the dataset you're using only has a vocabulary of 227 English words of the thousands that you use, you're only going to see good results using these words. For this project, you don't need a perfect translation. However, if you want to create a better translation model, you'll need better data.
You can train on the WMT10 French-English corpus. This dataset has more vocabulary and richer in topics discussed. However, this will take you days to train, so make sure you've a GPU and the neural network is performing well on dataset we provided. Just make sure you play with the WMT10 corpus after you've submitted this project.
When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as "dlnd_language_translation.ipynb" and save it as a HTML file under "File" -> "Download as". Include the "helper.py" and "problem_unittests.py" files in your submission.