Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[bugfix] Bugfix embed_loader.py #128

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[bugfix] Bugfix embed_loader.py #128

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions fastNLP/io/embed_loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ def __init__(self):
super(EmbedLoader, self).__init__()

@staticmethod
def _load_glove(emb_file):
def _load_glove(emb_dim, emb_file):
"""Read file as a glove embedding

file format:
Expand All @@ -28,20 +28,20 @@ def _load_glove(emb_file):
with open(emb_file, 'r', encoding='utf-8') as f:
for line in f:
line = list(filter(lambda w: len(w) > 0, line.strip().split(' ')))
if len(line) > 2:
if len(line) == emb_dim + 1:
emb[line[0]] = torch.Tensor(list(map(float, line[1:])))
return emb

@staticmethod
def _load_pretrain(emb_file, emb_type):
def _load_pretrain(emb_dim, emb_file, emb_type):
"""Read txt data from embedding file and convert to np.array as pre-trained embedding

:param str emb_file: the pre-trained embedding file path
:param str emb_type: the pre-trained embedding data format
:return: a dict of ``{str: np.array}``
"""
if emb_type == 'glove':
return EmbedLoader._load_glove(emb_file)
return EmbedLoader._load_glove(emb_dim, emb_file)
else:
raise Exception("embedding type {} not support yet".format(emb_type))

Expand All @@ -58,7 +58,7 @@ def load_embedding(emb_dim, emb_file, emb_type, vocab):
vocab - input vocab or vocab built by pre-train

"""
pretrain = EmbedLoader._load_pretrain(emb_file, emb_type)
pretrain = EmbedLoader._load_pretrain(emb_dim, emb_file, emb_type)
if vocab is None:
# build vocabulary from pre-trained embedding
vocab = Vocabulary()
Expand Down