def load_dataset(self, split, combine=False, **kwargs):
"""Load a given dataset split (e.g., train, valid, test)."""
def get_path(key, split):
return os.path.join(self.cfg.data, key, split)
def make_dataset(key, dictionary):
split_path = get_path(key, split)
try:
dataset = data_utils.load_indexed_dataset(
split_path,
dictionary,
combine=combine,
)
except Exception as e:
if "StorageException: [404] Path not found" in str(e):
logger.warning(f"dataset {e} not found")
dataset = None
else:
raise e
return dataset
input0 = make_dataset("input0", self.source_dictionary)
assert input0 is not None, "could not find dataset: {}".format(
get_path("input0", split))
input1 = make_dataset("input1", self.source_dictionary)
if self.cfg.init_token is not None:
input0 = PrependTokenDataset(input0, self.cfg.init_token)
if input1 is None:
src_tokens = input0
else:
if self.cfg.separator_token is not None:
input1 = PrependTokenDataset(input1, self.cfg.separator_token)
src_tokens = ConcatSentencesDataset(input0, input1)
with data_utils.numpy_seed(self.cfg.seed):
shuffle = np.random.permutation(len(src_tokens))
src_tokens = maybe_shorten_dataset(
src_tokens,
split,
self.cfg.shorten_data_split_list,
self.cfg.shorten_method,
self.max_positions(),
self.cfg.seed,
)
dataset = {
"id": IdDataset(),
"net_input": {
"src_tokens":
RightPadDataset(
src_tokens,
pad_idx=self.source_dictionary.pad(),
),
"src_lengths":
NumelDataset(src_tokens, reduce=False),
},
"nsentences": NumSamplesDataset(),
"ntokens": NumelDataset(src_tokens, reduce=True),
}
if self.cfg.add_prev_output_tokens:
prev_tokens_dataset = RightPadDataset(
RollDataset(src_tokens, 1),
pad_idx=self.dictionary.pad(),
)
dataset["net_input"].update(
prev_output_tokens=prev_tokens_dataset, )
if not self.cfg.regression_target:
label_dataset = make_dataset("label", self.label_dictionary)
if label_dataset is not None:
dataset.update(target=OffsetTokensDataset(
StripTokenDataset(
label_dataset,
id_to_strip=self.label_dictionary.eos(),
),
offset=-self.label_dictionary.nspecial,
))
else:
label_path = "{0}.label".format(get_path("label", split))
if os.path.exists(label_path):
def parse_regression_target(i, line):
values = line.split()
assert (
len(values) == self.cfg.num_classes
), f'expected num_classes={self.cfg.num_classes} regression target values on line {i}, found: "{line}"'
return [float(x) for x in values]
with open(label_path) as h:
dataset.update(target=RawLabelDataset([
parse_regression_target(i, line.strip())
for i, line in enumerate(h.readlines())
]))
nested_dataset = NestedDictionaryDataset(
dataset,
sizes=[src_tokens.sizes],
)
if self.cfg.no_shuffle:
dataset = nested_dataset
else:
dataset = SortDataset(
nested_dataset,
# shuffle
sort_order=[shuffle],
)
logger.info("Loaded {0} with #samples: {1}".format(
split, len(dataset)))
self.datasets[split] = dataset
return self.datasets[split]
def load_dataset(self, split, combine=False, **kwargs):
"""Load a given dataset split (e.g., train, valid, test)."""
def get_path(type, split):
return os.path.join(self.args.data, type, split)
def make_dataset(type, dictionary):
split_path = get_path(type, split)
dataset = data_utils.load_indexed_dataset(
split_path,
dictionary,
self.args.dataset_impl,
combine=combine,
)
return dataset
input0 = make_dataset('input0', self.source_dictionary)
assert input0 is not None, 'could not find dataset: {}'.format(get_path(type, split))
input1 = make_dataset('input1', self.source_dictionary)
if self.args.init_token is not None:
input0 = PrependTokenDataset(input0, self.args.init_token)
if input1 is None:
src_tokens = input0
else:
if self.args.separator_token is not None:
input1 = PrependTokenDataset(input1, self.args.separator_token)
src_tokens = ConcatSentencesDataset(input0, input1)
with data_utils.numpy_seed(self.args.seed):
shuffle = np.random.permutation(len(src_tokens))
src_tokens = maybe_shorten_dataset(
src_tokens,
split,
self.args.shorten_data_split_whitelist,
self.args.shorten_method,
self.args.max_positions,
self.args.seed,
)
dataset = {
'id': IdDataset(),
'net_input': {
'src_tokens': RightPadDataset(
src_tokens,
pad_idx=self.source_dictionary.pad(),
),
'src_lengths': NumelDataset(src_tokens, reduce=False),
},
'nsentences': NumSamplesDataset(),
'ntokens': NumelDataset(src_tokens, reduce=True),
}
if self.args.add_prev_output_tokens:
prev_tokens_dataset = RightPadDataset(
RollDataset(src_tokens, 1),
pad_idx=self.dictionary.pad(),
)
dataset['net_input'].update(
prev_output_tokens=prev_tokens_dataset,
)
if not self.args.regression_target:
label_dataset = make_dataset('label', self.label_dictionary)
if label_dataset is not None:
dataset.update(
target=OffsetTokensDataset(
StripTokenDataset(
label_dataset,
id_to_strip=self.label_dictionary.eos(),
),
offset=-self.label_dictionary.nspecial,
)
)
else:
label_path = "{0}.label".format(get_path('label', split))
if os.path.exists(label_path):
def parse_regression_target(i, line):
values = line.split()
assert len(values) == self.args.num_classes, \
f'expected num_classes={self.args.num_classes} regression target values on line {i}, found: "{line}"'
return [float(x) for x in values]
dataset.update(
target=RawLabelDataset([
parse_regression_target(i, line.strip()) for i, line in enumerate(open(label_path).readlines())
])
)
nested_dataset = NestedDictionaryDataset(
dataset,
sizes=[src_tokens.sizes],
)
if self.args.no_shuffle:
dataset = nested_dataset
else:
dataset = SortDataset(
nested_dataset,
# shuffle
sort_order=[shuffle],
)
logger.info("Loaded {0} with #samples: {1}".format(split, len(dataset)))
self.datasets[split] = dataset
return self.datasets[split]
def load_dataset(self, split, combine=False, **kwargs):
"""Load a given dataset split (e.g., train, valid, test)."""
def get_path(type, split):
return os.path.join(self.args.data, type, split)
def make_dataset(type, dictionary):
split_path = get_path(type, split)
dataset = data_utils.load_indexed_dataset(
split_path,
self.source_dictionary,
self.args.dataset_impl,
combine=combine,
)
return dataset
input0 = make_dataset("input0", self.source_dictionary)
assert input0 is not None, "could not find dataset: {}".format(
get_path(type, split))
input1 = make_dataset("input1", self.source_dictionary)
if self.args.init_token is not None:
input0 = PrependTokenDataset(input0, self.args.init_token)
if input1 is None:
src_tokens = input0
else:
if self.args.separator_token is not None:
input1 = PrependTokenDataset(input1, self.args.separator_token)
src_tokens = ConcatSentencesDataset(input0, input1)
with data_utils.numpy_seed(self.args.seed):
shuffle = np.random.permutation(len(src_tokens))
if self.args.truncate_sequence:
src_tokens = TruncateDataset(src_tokens, self.args.max_positions)
dataset = {
"id": IdDataset(),
"net_input": {
"src_tokens":
RightPadDataset(
src_tokens,
pad_idx=self.source_dictionary.pad(),
),
"src_lengths":
NumelDataset(src_tokens, reduce=False),
},
"nsentences": NumSamplesDataset(),
"ntokens": NumelDataset(src_tokens, reduce=True),
}
if self.args.add_prev_output_tokens:
prev_tokens_dataset = RightPadDataset(
RollDataset(src_tokens, 1),
pad_idx=self.dictionary.pad(),
)
dataset["net_input"].update(
prev_output_tokens=prev_tokens_dataset, )
if not self.args.regression_target:
label_dataset = make_dataset("label", self.target_dictionary)
if label_dataset is not None:
dataset.update(target=OffsetTokensDataset(
StripTokenDataset(
label_dataset,
id_to_strip=self.target_dictionary.eos(),
),
offset=-self.target_dictionary.nspecial,
))
else:
label_path = "{0}.label".format(get_path("label", split))
if os.path.exists(label_path):
dataset.update(target=RawLabelDataset(
[float(x.strip()) for x in open(label_path).readlines()]))
nested_dataset = NestedDictionaryDataset(
dataset,
sizes=[src_tokens.sizes],
)
if self.args.no_shuffle:
dataset = nested_dataset
else:
dataset = SortDataset(
nested_dataset,
# shuffle
sort_order=[shuffle],
)
print("| Loaded {0} with #samples: {1}".format(split, len(dataset)))
self.datasets[split] = dataset
return self.datasets[split]
def load_dataset(self, split, combine=False, **kwargs):
"""Load a given dataset split (e.g., train, valid, test)."""
def get_path(key, split):
return os.path.join(self.args.data, key, split)
def make_dataset(key, dictionary):
split_path = get_path(key, split)
dataset = data_utils.load_indexed_dataset(
split_path,
dictionary,
self.args.dataset_impl,
combine=combine,
)
return dataset
input0 = make_dataset("input0", self.source_dictionary)
assert input0 is not None, "could not find dataset: {}".format(
get_path("input0", split))
input1 = make_dataset("input1", self.source_dictionary)
if self.args.init_token is not None:
input0 = PrependTokenDataset(input0, self.args.init_token)
if input1 is None:
src_tokens = input0
else:
if self.args.separator_token is not None:
input1 = PrependTokenDataset(input1, self.args.separator_token)
src_tokens = ConcatSentencesDataset(input0, input1)
with data_utils.numpy_seed(self.args.seed):
shuffle = np.random.permutation(len(src_tokens))
src_tokens = maybe_shorten_dataset(
src_tokens,
split,
self.args.shorten_data_split_list,
self.args.shorten_method,
self.args.max_positions,
self.args.seed,
)
dataset = {
"id": IdDataset(),
"net_input": {
"src_tokens":
RightPadDataset(
src_tokens,
pad_idx=self.source_dictionary.pad(),
),
"src_lengths":
NumelDataset(src_tokens, reduce=False),
},
"nsentences": NumSamplesDataset(),
"ntokens": NumelDataset(src_tokens, reduce=True),
}
if self.args.add_prev_output_tokens:
prev_tokens_dataset = RightPadDataset(
RollDataset(src_tokens, 1),
pad_idx=self.dictionary.pad(),
)
dataset["net_input"].update(
prev_output_tokens=prev_tokens_dataset, )
label_path = "{0}.npz".format(get_path("label", split))
if os.path.exists(label_path):
csr_matrix = load_npz(label_path)
dataset.update(target=CSRLabelDataset(csr_matrix))
nested_dataset = NestedDictionaryDataset(
dataset,
sizes=[src_tokens.sizes],
)
if self.args.no_shuffle:
dataset = nested_dataset
else:
dataset = SortDataset(
nested_dataset,
# shuffle
sort_order=[shuffle],
)
logger.info("Loaded {0} with #samples: {1}".format(
split, len(dataset)))
self.datasets[split] = dataset
return self.datasets[split]
def load_dataset(self, split, combine=False, **kwargs):
"""Load a given dataset split (e.g., train, valid, test)."""
def get_path(split):
return os.path.join(self.args.data, split)
def make_dataset(split_path, dictionary):
dataset = data_utils.load_indexed_dataset(
split_path,
self.source_dictionary,
self.args.dataset_impl,
combine=combine)
return dataset
input0 = make_dataset(
os.path.join(self.args.data, split), self.source_dictionary)
assert input0 is not None, 'could not find dataset: {}'.format(
os.path.join(self.args.data, split))
if self.args.init_token is not None:
input0 = PrependTokenDataset(input0, self.args.init_token)
src_tokens = input0
with data_utils.numpy_seed(self.args.seed):
shuffle = np.random.permutation(len(src_tokens))
if self.args.truncate_sequence:
src_tokens = TruncateDataset(src_tokens, self.args.max_positions)
dataset = {
'id': IdDataset(),
'net_input': {
'src_tokens': RightPadDataset(
src_tokens,
pad_idx=self.source_dictionary.pad()),
'src_lengths': NumelDataset(src_tokens, reduce=False)},
'nsentences': NumSamplesDataset(),
'ntokens': NumelDataset(src_tokens, reduce=True),
}
if self.args.add_prev_output_tokens:
prev_tokens_dataset = RightPadDataset(
RollDataset(src_tokens, 1),
pad_idx=self.dictionary.pad())
dataset['net_input'].update(
prev_output_tokens=prev_tokens_dataset)
if not self.args.regression_target:
label_dataset = make_dataset(
os.path.join(self.args.data, split + '.label'), self.target_dictionary)
if label_dataset is not None:
dataset.update(
target=OffsetTokensDataset(
StripTokenDataset(
label_dataset,
id_to_strip=self.target_dictionary.eos()),
offset=-self.target_dictionary.nspecial,
)
)
else:
label_path = os.path.join(self.args.data, split + '.label')
if os.path.exists(label_path):
dataset.update(target=RawLabelDataset([
float(x.strip()) for x in open(label_path).readlines()]))
nested_dataset = NestedDictionaryDataset(dataset, sizes=[src_tokens.sizes])
if self.args.no_shuffle:
dataset = nested_dataset
else:
dataset = SortDataset(
nested_dataset,
sort_order=[shuffle]) # shuffle
print("| Loaded {0} with #samples: {1}".format(split, len(dataset)))
self.datasets[split] = dataset
return self.datasets[split]
def load_dataset(self, split, combine=False, **kwargs):
"""Load a given dataset split (e.g., train, valid, test)."""
def get_path(type, split):
return os.path.join(self.args.data, type, split)
def make_dataset(type, dictionary):
split_path = get_path(type, split)
dataset = data_utils.load_indexed_dataset(
split_path,
dictionary,
self.args.dataset_impl,
combine=combine,
)
return dataset
# input0 is source, input1 is synthetic target, input2 is reference
input0 = make_dataset(self.args.input0, self.source_dictionary)
assert input0 is not None, 'could not find dataset: {}'.format(
get_path(type, split))
input1 = make_dataset(self.args.input1, self.source_dictionary)
if self.args.init_token is not None:
input0 = PrependTokenDataset(input0, self.args.init_token)
if self.args.input2 is not None:
input2 = make_dataset(self.args.input2, self.source_dictionary)
if self.args.input2 is not None and self.add_ref_prob > 0 and split != 'valid':
input3 = PrependTokenDataset(input2, self.args.separator_token)
else:
input3 = None
if input1 is None:
src_tokens = input0
else:
if self.args.separator_token is not None:
input1 = PrependTokenDataset(input1, self.args.separator_token)
if self.args.input2 is not None and self.add_ref_prob > 0. and split != 'valid':
src_tokens = ConcatSentencesDataset(
input0,
input3,
input1,
add_ref_prob=self.add_ref_prob,
drop_ref_rate=self.args.dropout_ref,
pad_idx=self.source_dictionary.pad(),
eos_idx=self.source_dictionary.eos(),
bos_idx=self.source_dictionary.bos())
else:
src_tokens = ConcatSentencesDataset(input0, input1)
with data_utils.numpy_seed(self.args.seed):
shuffle = np.random.permutation(len(src_tokens))
if self.args.truncate_sequence:
src_tokens = TruncateDataset(src_tokens, self.args.max_positions)
if self.args.input2 is not None and self.args.add_tran_loss:
# create masked input and targets
mask_whole_words = get_whole_word_mask(self.args, self.source_dictionary) \
if self.args.mask_whole_words else None
ref_dataset, ref_target_dataset = MaskTokensDataset.apply_mask(
input2,
self.source_dictionary,
pad_idx=self.source_dictionary.pad(),
mask_idx=self.mask_idx,
seed=self.args.seed,
mask_prob=self.args.mask_prob,
leave_unmasked_prob=self.args.leave_unmasked_prob,
random_token_prob=self.args.random_token_prob,
freq_weighted_replacement=self.args.freq_weighted_replacement,
mask_whole_words=mask_whole_words,
)
if self.args.separator_token is not None:
input2 = PrependTokenDataset(ref_dataset,
self.args.separator_token)
parallel_src_tokens = ConcatSentencesDataset(input0, input2)
if self.args.truncate_sequence:
parallel_src_tokens = TruncateDataset(parallel_src_tokens,
self.args.max_positions)
dataset = {
'id': IdDataset(),
'net_input': {
'src_tokens':
RightPadDataset(
src_tokens,
pad_idx=self.source_dictionary.pad(),
),
'src_lengths':
NumelDataset(src_tokens, reduce=False),
},
'nsentences': NumSamplesDataset(),
'ntokens': NumelDataset(src_tokens, reduce=True),
}
if self.args.input2 is not None and self.args.add_tran_loss:
dataset['net_input']['parallel_src_tokens'] = RightPadDataset(
parallel_src_tokens,
pad_idx=self.source_dictionary.pad(),
)
if self.args.add_prev_output_tokens:
prev_tokens_dataset = RightPadDataset(
RollDataset(src_tokens, 1),
pad_idx=self.dictionary.pad(),
)
dataset['net_input'].update(
prev_output_tokens=prev_tokens_dataset, )
if not self.args.regression_target:
label_dataset = make_dataset('label', self.label_dictionary)
if label_dataset is not None:
dataset.update(target=OffsetTokensDataset(
StripTokenDataset(
label_dataset,
id_to_strip=self.label_dictionary.eos(),
),
offset=-self.label_dictionary.nspecial,
))
if self.args.input2 is not None and self.args.add_tran_loss:
# used as translation target when calculating loss
dataset.update(parallel_target=RightPadDataset(
ref_target_dataset,
pad_idx=self.source_dictionary.pad(),
))
else:
label_path = "{0}.label".format(get_path('label', split))
if os.path.exists(label_path):
def parse_regression_target(i, line):
values = line.split()
assert len(values) == self.args.num_classes, \
f'expected num_classes={self.args.num_classes} regression target values on line {i}, found: "{line}"'
return [float(x) for x in values]
dataset.update(target=RawLabelDataset([
parse_regression_target(i, line.strip())
for i, line in enumerate(open(label_path).readlines())
]))
nested_dataset = NestedDictionaryDataset(
dataset,
sizes=[src_tokens.sizes],
all_sizes=src_tokens.all_sizes
if self.args.add_target_num_tokens else None,
padding_idx=self.source_dictionary.pad(),
add_ref_prob=self.add_ref_prob if split != 'valid' else 0.,
)
if self.args.no_shuffle:
dataset = nested_dataset
else:
dataset = SortDataset(
nested_dataset,
# shuffle
sort_order=[shuffle],
)
logger.info("Loaded {0} with #samples: {1}".format(
split, len(dataset)))
self.datasets[split] = dataset
return self.datasets[split]