def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = cast(Iterable[List[str]],
dataset.maybe_get_series(self.data_id))
if sentences is None and train:
raise ValueError("When training, you must feed "
"reference sentences")
if sentences is not None:
vectors, paddings = self.vocabulary.sentences_to_tensor(
list(sentences), train_mode=train, max_len=self.max_length)
# sentences_to_tensor returns time-major tensors, targets need to
# be batch-major
vectors = vectors.T
paddings = paddings.T
bool_mask = (paddings > 0.5)
flat_labels = vectors[bool_mask]
label_lengths = bool_mask.sum(axis=1)
fd[self.label_lengths] = label_lengths
fd[self.flat_labels] = flat_labels
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Populate the feed dictionary with the encoder inputs.
Arguments:
dataset: The dataset to use
train: Boolean flag telling whether it is training time
"""
fd = ModelPart.feed_dict(self, dataset, train)
series = list(dataset.get_series(self.data_id))
lengths = []
inputs = []
max_len = max(x.shape[0] for x in series)
if self.max_input_len is not None:
max_len = min(self.max_input_len, max_len)
for x in series:
length = min(max_len, x.shape[0])
x_padded = np.zeros(shape=(max_len, ) + x.shape[1:], dtype=x.dtype)
x_padded[:length] = x[:length]
lengths.append(length)
inputs.append(x_padded)
fd[self.inputs] = inputs
fd[self._input_lengths] = lengths
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Populate the feed dictionary for the decoder object.
Arguments:
dataset: The dataset to use for the decoder.
train: Boolean flag, telling whether this is a training run.
"""
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is None and train:
raise ValueError("When training, you must feed "
"reference sentences")
go_symbol_idx = self.vocabulary.get_word_index(START_TOKEN)
fd[self.go_symbols] = np.full([len(dataset)], go_symbol_idx,
dtype=np.int32)
if sentences is not None:
sentences_list = list(sentences)
# train_mode=False, since we don't want to <unk>ize target words!
inputs, weights = self.vocabulary.sentences_to_tensor(
sentences_list, self.max_output_len, train_mode=False,
add_start_symbol=False, add_end_symbol=True,
pad_to_max_len=False)
fd[self.train_inputs] = inputs
fd[self.train_mask] = weights
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = cast(Iterable[List[str]],
dataset.maybe_get_series(self.data_id))
if sentences is None and train:
raise ValueError("When training, you must feed "
"reference sentences")
if sentences is not None:
vectors, paddings = self.vocabulary.sentences_to_tensor(
list(sentences), train_mode=train, max_len=self.max_length)
# sentences_to_tensor returns time-major tensors, targets need to
# be batch-major
vectors = vectors.T
paddings = paddings.T
# Need to convert the data to a sparse representation
bool_mask = (paddings > 0.5)
indices = np.stack(np.where(bool_mask), axis=1)
values = vectors[bool_mask]
fd[self.train_targets] = tf.SparseTensorValue(
indices=indices, values=values, dense_shape=vectors.shape)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
# if it is from the pickled file, it is a list, not a numpy tensor,
# so convert it as as a prevention
images = np.array(list(dataset.get_series(self.data_id)))
fd[self.image_input] = images / 255.0
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is not None:
fd[self.target_tokens] = pad_batch(list(sentences))
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
# if it is from the pickled file, it is a list, not a numpy tensor,
# so convert it as as a prevention
images = np.array(list(dataset.get_series(self.data_id)))
fd[self.image_input] = images / 255.0
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
images = np.array(dataset.get_series(self.data_id))
assert images.shape[1:] == (self.height, self.width, 3)
fd[self.input_image] = images
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
sentences_list = list(sentences) if sentences is not None else None
if sentences_list is not None:
fd[self.train_inputs] = list(zip(*sentences_list))[0]
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
sentences_list = list(sentences) if sentences is not None else None
if sentences_list is not None:
fd[self.train_inputs] = list(zip(*sentences_list))[0]
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is not None:
vectors, _ = self.vocabulary.sentences_to_tensor(
list(sentences), pad_to_max_len=False, train_mode=train)
fd[self.train_targets] = vectors.T
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is not None:
fd[self.target_tokens] = pad_batch(
list(sentences), self.max_output_len, self.add_start_symbol,
self.add_end_symbol)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is not None:
labels = [l[0] for l in pad_batch(list(sentences),
self.max_output_len)]
fd[self.targets] = labels
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is not None:
label_tensors, _ = self.vocabulary.sentences_to_tensor(
list(sentences), self.max_output_len)
fd[self.gt_inputs[0]] = label_tensors[0]
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is not None:
fd[self.target_tokens] = pad_batch(list(sentences),
self.max_output_len,
self.add_start_symbol,
self.add_end_symbol)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is not None:
labels = [
l[0] for l in pad_batch(list(sentences), self.max_output_len)
]
fd[self.targets] = labels
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Populate the feed dictionary with the encoder inputs.
Arguments:
dataset: The dataset to use
train: Boolean flag telling whether it is training time
"""
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.get_series(self.data_id)
fd[self.input_tokens] = pad_batch(list(sentences), self.max_input_len)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is None and train:
raise ValueError("You must feed reference sentences when training")
if sentences is not None:
fd[self.target_tokens] = pad_batch(list(sentences),
self.max_length)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is None and train:
raise ValueError("You must feed reference sentences when training")
if sentences is not None:
fd[self.target_tokens] = pad_batch(list(sentences),
self.max_length)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
# if it is from the pickled file, it is a list, not a numpy tensor,
# so convert it as as a prevention
images = np.array(list(dataset.get_series(self.data_id)))
fd[self.image_input] = images / 255.0
# the image mask is one everywhere where the image is non-zero, i.e.
# zero pixels are masked out
fd[self.image_mask] = np.sign(np.sum(images, axis=3, keepdims=True))
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
alignment = dataset.maybe_get_series(self.data_id)
if alignment is None:
if train:
warn("Training alignment not present!")
alignment = np.zeros((len(dataset), self.decoder.max_output_len,
self.enc_input.max_length), np.float32)
fd[self.ref_alignment] = alignment
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Populate the feed dictionary with the encoder inputs.
Arguments:
dataset: The dataset to use
train: Boolean flag telling whether it is training time
"""
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.get_series(self.data_id)
vectors, _ = self.vocabulary.sentences_to_tensor(
list(sentences), self.max_input_len, pad_to_max_len=False,
train_mode=train)
# as sentences_to_tensor returns lists of shape (time, batch),
# we need to transpose
fd[self.inputs] = list(zip(*vectors))
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Feed the placholders with the data.
Arguments:
dataset: The dataset.
train: A flag whether the train mode is enabled.
Returns:
The constructed feed dictionary that contains the factor data and
the mask.
"""
fd = ModelPart.feed_dict(self, dataset, train)
# for checking the lengths of individual factors
arr_strings = []
last_paddings = None
for factor_plc, name, vocabulary in zip(self.input_factors,
self.data_ids,
self.vocabularies):
factors = dataset.get_series(name)
vectors, paddings = vocabulary.sentences_to_tensor(
list(factors),
self.max_length,
pad_to_max_len=False,
train_mode=train,
add_start_symbol=self.add_start_symbol,
add_end_symbol=self.add_end_symbol)
fd[factor_plc] = list(zip(*vectors))
arr_strings.append(paddings.tostring())
last_paddings = paddings
if len(set(arr_strings)) > 1:
raise ValueError("The lenghts of factors do not match")
assert last_paddings is not None
fd[self.mask] = list(zip(*last_paddings))
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Populate the feed dictionary for the decoder object.
Arguments:
dataset: The dataset to use for the decoder.
train: Boolean flag, telling whether this is a training run.
"""
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is None and train:
raise ValueError("When training, you must feed "
"reference sentences")
if sentences is not None:
fd[self.train_tokens] = pad_batch(
list(sentences), self.max_output_len, add_start_symbol=False,
add_end_symbol=True)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Feed the placholders with the data.
Arguments:
dataset: The dataset.
train: A flag whether the train mode is enabled.
Returns:
The constructed feed dictionary that contains the factor data and
the mask.
"""
fd = ModelPart.feed_dict(self, dataset, train)
# for checking the lengths of individual factors
for factor_plc, name in zip(self.input_factors, self.data_ids):
sentences = dataset.get_series(name)
fd[factor_plc] = pad_batch(
list(sentences), self.max_length, self.add_start_symbol,
self.add_end_symbol)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Feed the placholders with the data.
Arguments:
dataset: The dataset.
train: A flag whether the train mode is enabled.
Returns:
The constructed feed dictionary that contains the factor data and
the mask.
"""
fd = ModelPart.feed_dict(self, dataset, train)
# for checking the lengths of individual factors
for factor_plc, name in zip(self.input_factors, self.data_ids):
sentences = dataset.get_series(name)
fd[factor_plc] = pad_batch(list(sentences), self.max_length,
self.add_start_symbol,
self.add_end_symbol)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
"""Populate the feed dictionary for the decoder object.
Arguments:
dataset: The dataset to use for the decoder.
train: Boolean flag, telling whether this is a training run.
"""
fd = ModelPart.feed_dict(self, dataset, train)
sentences = dataset.maybe_get_series(self.data_id)
if sentences is None and train:
raise ValueError("When training, you must feed "
"reference sentences")
if sentences is not None:
fd[self.train_tokens] = pad_batch(list(sentences),
self.max_output_len,
add_start_symbol=False,
add_end_symbol=True)
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
series = list(dataset.get_series(self.data_id))
lengths = []
inputs = []
max_len = max(x.shape[0] for x in series)
if self.max_input_len is not None:
max_len = min(self.max_input_len, max_len)
for x in series:
length = min(max_len, x.shape[0])
x_padded = np.zeros(shape=(max_len, ) + x.shape[1:], dtype=x.dtype)
x_padded[:length] = x[:length]
lengths.append(length)
inputs.append(x_padded)
fd[self.temporal_states] = inputs
fd[self._input_lengths] = lengths
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
series = list(dataset.get_series(self.data_id))
lengths = []
inputs = []
max_len = max(x.shape[0] for x in series)
if self.max_input_len is not None:
max_len = min(self.max_input_len, max_len)
for x in series:
length = min(max_len, x.shape[0])
x_padded = np.zeros(shape=(max_len,) + x.shape[1:],
dtype=x.dtype)
x_padded[:length] = x[:length]
lengths.append(length)
inputs.append(x_padded)
fd[self.temporal_states] = inputs
fd[self._input_lengths] = lengths
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
fd[self.spatial_input] = list(dataset.get_series(self.data_id))
return fd
def feed_dict(self, dataset: Dataset, train: bool = True) -> FeedDict:
return ModelPart.feed_dict(self, dataset, train)
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
fd[self.spatial_input] = list(dataset.get_series(self.data_id))
return fd
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
fd[self.vector] = dataset.get_series(self.data_id)
return fd
def feed_dict(self, dataset: Dataset, train: bool = True) -> FeedDict:
return ModelPart.feed_dict(self, dataset, train)
def feed_dict(self, dataset: Dataset, train: bool = False) -> FeedDict:
fd = ModelPart.feed_dict(self, dataset, train)
fd[self.vector] = dataset.get_series(self.data_id)
return fd
