Using fasttext pre-trained embedding

[NewEnglandML]

Hi, If the boolean flags for fasttext changed to True, the pre processing does not work properly. The modification for config.py is more that changing the size of embedding or not?

[wzhouad]

The error may be caused by missing dataset. Uncomment the corresponding line in download.sh to download it.

[NewEnglandML]

I have uncommented that line, when running config.py --mode prepro, during the creating the word embedding the error appears:

Traceback (most recent call last): File "config.py", line 134, in tf.app.run() File "/home/farshid/anaconda3/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run _sys.exit(main(argv)) File "config.py", line 119, in main prepro(config) File "/home/farshid/Desktop/tensorflow/New_RNET/R-Net-0.1 (copy)/prepro.py", line 223, in prepro size=config.glove_word_size, vec_size=config.glove_dim, token2idx_dict=word2idx_dict) File "/home/farshid/Desktop/tensorflow/New_RNET/R-Net-0.1 (copy)/prepro.py", line 116, in get_embedding for token, idx in token2idx_dict.items()} File "/home/farshid/Desktop/tensorflow/New_RNET/R-Net-0.1 (copy)/prepro.py", line 116, in for token, idx in token2idx_dict.items()} KeyError: "n't"