Mercurial > pylearn

annotate sandbox/embeddings/files.py @ 459:f400f62e7f9e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Fixed embedding preprocessing
author Joseph Turian <turian@iro.umontreal.ca>
date Tue, 07 Oct 2008 23:00:10 -0400
parents ed6b0b3be8d2
children
rev   line source
458
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
1 """
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
2 Locations of the embedding data files.
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
3 """
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
4 WEIGHTSFILE = "/u/turian/data/word_embeddings.collobert-and-weston/lm-weights.txt"
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
5 VOCABFILE = "/u/turian/data/word_embeddings.collobert-and-weston/words.asc"
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
6 NUMBER_OF_WORDS = 30000
ed6b0b3be8d2 Polished embeddings module
Joseph Turian <turian@iro.umontreal.ca>
parents:
diff changeset
7 DIMENSIONS = 50
459
f400f62e7f9e Fixed embedding preprocessing
Joseph Turian <turian@iro.umontreal.ca>
parents: 458
diff changeset
8 UNKNOWN = "UNKNOWN"