def c4_bare_preprocess_fn(dataset,
training=True,
spm_path=None,
copy_plaintext=True,
sequence_length=None):
"""Returns a dataset that contains 'inputs' and 'targets' from C4."""
# Set target key to be equal to the text content.
dataset = t5_processors.rekey(dataset,
key_map={
'targets': 'text',
'inputs': None
})
# Vocabulary for tokenization.
vocab = t5_spc_vocab.SentencePieceVocabulary(
sentencepiece_model_file=spm_path or t5_utils.DEFAULT_SPM_PATH)
feature = t5_data.Feature(vocab)
output_features = {'targets': feature, 'inputs': feature}
# Tokenize the targets.
keys = output_features
def encode_string_features_fn(features):
"""Encode all specified feature that are strings and return a dictionary.
Args:
features: a dictionary
Returns:
a dictionary
"""
ret = {}
for k, v in features.items():
if k in keys and v.dtype == tf.string:
if copy_plaintext:
ret['%s_plaintext' % k] = v
v = tf.cast(output_features[k].vocabulary.encode_tf(v),
tf.int64)
ret[k] = v
return ret
dataset = dataset.map(encode_string_features_fn,
num_parallel_calls=tf.data.experimental.AUTOTUNE)
# Preprocess the tokens - the exact preprocessors are set via gin.
dataset = t5_processors.unsupervised(dataset,
sequence_length=sequence_length,
output_features=output_features)
# Add EOS.
dataset = add_eos_to_output_features(dataset, training)
# Truncate and then pad the examples -- all examples have the same shape.
dataset = truncate_dataset_on_len(dataset, training, sequence_length, True)
dataset = pad_dataset_to_length(dataset, training, sequence_length)
return dataset
def generic_text_dataset_preprocess_fn(dataset,
training=True,
text_preprocess_fns=None,
token_preprocess_fns=None,
spm_path=None,
copy_plaintext=False,
debug_print_examples=False,
debug_print_examples_rate=0.01):
"""Pre-processes, tokenizes and post-processes a `tf.data.Dataset`.
Args:
dataset: `tf.data.Dataset` to process.
training: boolean, set to True if training, False otherwise.
text_preprocess_fns: None or list of callables: `tf.data.Dataset`, bool ->
`tf.data.Dataset` this operates before tokenization. Typically used to
select which fields we want to learn over or change something into
"text to text" form.
token_preprocess_fns: None or list of callables: `tf.data.Dataset`, bool ->
`tf.data.Dataset`, this operates after tokenization. Since this can view
the tokenized fields, this can be used to filter on length etc.
spm_path: None or str, path to a sentencepiece model to use for tokenization
by default uses the 32k vocabulary from T5.
copy_plaintext: bool, if True retains the original fields after
tokenization.
debug_print_examples: bool, if True this prints examples to the logging
stream for inspection, both before and after tokenization.
debug_print_examples_rate: float, [0, 1.0], on average this fraction of
dataset examples will be printed out in each phase i.e. pre and post
tokenization.
Returns:
a `tf.data.Dataset` with all the preprocessing and tokenization performed.
"""
# The assumption is that `text_preprocess_fns` finally gives us a dataset
# which has `inputs` and `targets`.
if text_preprocess_fns is not None:
for text_preprocess_fn in text_preprocess_fns:
dataset = text_preprocess_fn(dataset, training)
# Print debugging examples if needed before tokenization.
if debug_print_examples:
def print_examples(x):
if np.random.uniform() < debug_print_examples_rate:
tf.print(x, output_stream=logging.info)
return x
dataset = dataset.map(print_examples)
# Vocabulary for tokenization.
vocab = t5_spc_vocab.SentencePieceVocabulary(
sentencepiece_model_file=spm_path or t5_utils.DEFAULT_SPM_PATH)
feature = t5_data.Feature(vocab)
output_features = {'targets': feature, 'inputs': feature}
# Tokenize the inputs and targets.
dataset = t5_processors.tokenize(dataset,
output_features,
copy_plaintext=copy_plaintext)
# Apply the token-preprocessors.
if token_preprocess_fns is not None:
for token_preprocess_fn in token_preprocess_fns:
dataset = token_preprocess_fn(dataset, training)
if debug_print_examples:
def print_examples_and_shapes(x):
if np.random.uniform() < debug_print_examples_rate:
tf.print(
{
'inputs_shape': tf.size(x['inputs']),
'targets_shape': tf.size(x['targets']),
'inputs': x['inputs'],
'targets': x['targets'],
},
output_stream=logging.info)
return x
dataset = dataset.map(print_examples_and_shapes)
return dataset