char_vocab.english.txt not accessible
Closed this issue · 2 comments
Hello,
I'm trying to go through the README steps, to run python demo.py final
It seems like the latest commit removed the lines to curl char_vocab.english.txt.
Doing curl -o char_vocab.english.txt https://www.googleapis.com/storage/v1/b/e2e-coref/o/char_vocab.english.txt?alt=media
directly leaves me with an empty file though.
After that demo.py crashes at line 47 with a tensorshape mismatch in the coref_model.py at line 90.
I suspect it might be related to my char_vocab.english.txt being empty?
Could you tell me how I could get this file?
EDIT: Found what I needed here: https://raw.githubusercontent.com/luheng/lsgn/master/embeddings/char_vocab.english.txt
I recently moved the resources to yet again for various uninteresting reasons. Please see the latest https://github.com/kentonl/e2e-coref/blob/master/README.md for how to get all the files.
I suspect that I am observing something to what @Natithan has observed.
(env3.6) huntsman-ve506-0062:e2e-coref daniel$ python demo.py final
WARNING: Logging before flag parsing goes to stderr.
W0429 19:46:45.946565 140735615419264 __init__.py:56] Some hub symbols are not available because TensorFlow version is less than 1.14
WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
* https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
* https://github.com/tensorflow/addons
If you depend on functionality not listed there, please file an issue.
[nltk_data] Error loading punkt: <urlopen error [SSL:
[nltk_data] CERTIFICATE_VERIFY_FAILED] certificate verify failed
[nltk_data] (_ssl.c:852)>
Setting CUDA_VISIBLE_DEVICES to:
Running experiment: final
max_top_antecedents = 50
max_training_sentences = 50
top_span_ratio = 0.4
.
.
.
Done loading word embeddings.
Loading word embeddings from glove_50_300_2.txt...
Done loading word embeddings.
Traceback (most recent call last):
File "demo.py", line 45, in <module>
model = cm.CorefModel(config)
File "/Users/daniel/ideaProjects/e2e-coref/coref_model.py", line 27, in __init__
self.char_dict = util.load_char_dict(config["char_vocab_path"])
File "/Users/daniel/ideaProjects/e2e-coref/util.py", line 58, in load_char_dict
with codecs.open(char_vocab_path, encoding="utf-8") as f:
File "/Users/daniel/ideaProjects/e2e-coref/env3.6/bin/../lib/python3.6/codecs.py", line 897, in open
file = builtins.open(filename, mode, buffering)
FileNotFoundError: [Errno 2] No such file or directory: 'char_vocab.english.txt'
I suspect that , probably during commit #5dc53a5dc2c852f9b8886a01ca57c8b893acca09.
Had to curl it manually: curl -O https://lil.cs.washington.edu/coref/char_vocab.english.txt