def make_embedding(emb_hparams, token_to_id_map):
"""Optionally loads embedding from file (if provided), and returns
an instance of :class:`texar.data.Embedding`.
"""
embedding = None
if emb_hparams["file"] is not None and len(emb_hparams["file"]) > 0:
embedding = Embedding(token_to_id_map, emb_hparams)
return embedding
def make_embedding(src_emb_hparams, src_token_to_id_map,
tgt_emb_hparams=None, tgt_token_to_id_map=None,
emb_init_share=False):
r"""Optionally loads source and target embeddings from files
(if provided), and returns respective :class:`texar.data.Embedding`
instances.
"""
src_embedding = MonoTextData.make_embedding(src_emb_hparams,
src_token_to_id_map)
if emb_init_share:
tgt_embedding = src_embedding
else:
tgt_emb_file = tgt_emb_hparams["file"]
tgt_embedding = None
if tgt_emb_file is not None and tgt_emb_file != "":
tgt_embedding = Embedding(tgt_token_to_id_map, tgt_emb_hparams)
return src_embedding, tgt_embedding
def _default_mono_text_dataset_hparams():
"""Returns hyperparameters of a mono text dataset with default values.
"""
return {
"files": [],
"compression_type": None,
"vocab_file": "",
"embedding_init": Embedding.default_hparams(),
"delimiter": " ",
"max_seq_length": None,
"length_filter_mode": "truncate",
"pad_to_max_seq_length": False,
"bos_token": SpecialTokens.BOS,
"eos_token": SpecialTokens.EOS,
"other_transformations": [],
"variable_utterance": False,
"utterance_delimiter": "|||",
"max_utterance_cnt": 5,
"data_name": None,
"@no_typecheck": ["files"]
}
def make_embedding(hparams, vocabs):
r"""Optionally loads embeddings from files (if provided), and
returns respective :class:`texar.data.Embedding` instances.
"""
if not isinstance(hparams, (list, tuple)):
hparams = [hparams]
embs = []
for i, hparams_i in enumerate(hparams):
if not _is_text_data(hparams_i["data_type"]):
embs.append(None)
continue
emb_share = hparams_i["embedding_init_share_with"]
if emb_share is not None:
if emb_share >= i:
MultiAlignedData._raise_sharing_error(
i, emb_share, "embedding_init_share_with")
if not embs[emb_share]:
raise ValueError("Cannot share embedding with dataset %d "
"which does not have an embedding." %
emb_share)
if emb_share != hparams_i["vocab_share_with"]:
raise ValueError("'embedding_init_share_with' != "
"vocab_share_with. embedding_init can "
"be shared only when vocab is shared.")
emb = embs[emb_share]
else:
emb = None
emb_file = hparams_i["embedding_init"]["file"]
if emb_file and emb_file != "":
emb = Embedding(vocabs[i].token_to_id_map_py,
hparams_i["embedding_init"])
embs.append(emb)
return embs
