76 Commits

Author	SHA1	Message	Date
Roman Grundkiewicz	68363b817d	Remove unwanted print in server.py	2017-08-18 22:10:50 +01:00
Roman Grundkiewicz	640c3ecb24	Unify python translate() interface with amunmt	2017-08-18 21:40:06 +01:00
Roman Grundkiewicz	4793818148	Copy python scripts from amunmt	2017-08-18 20:55:08 +01:00
Marcin Junczys-Dowmunt	b5dfd43a52	make hard-attention models work	2017-07-10 18:14:43 +00:00
Marcin Junczys-Dowmunt	1f78f38400	prepare_corpus	2017-07-04 14:07:46 +02:00
Roman Grundkiewicz	32f604a67f	Add --dim-voc option to process_word2vec.py	2017-07-04 12:43:31 +01:00
Roman Grundkiewicz	73c84ac17d	Fix loading YAML vocab	2017-07-04 09:37:33 +01:00
Jim Geovedi	622141e60b	handle different model type embeddings	2017-07-04 07:24:53 +07:00
Jim Geovedi	c9dffee841	added embedding exporter from model	2017-07-04 06:57:54 +07:00
Roman Grundkiewicz	52dab8ec3a	Update and rename word2vec script	2017-07-03 18:18:17 +01:00
Roman Grundkiewicz	3fa084f90a	Fix corpus in word2vec script	2017-07-02 07:56:38 +01:00
Roman Grundkiewicz	a6ffafbf0d	Add loading embedding vectors from files	2017-06-30 16:51:31 +01:00
Roman Grundkiewicz	54632eac03	Replace words with IDs in embedding vectors	2017-06-30 14:59:37 +01:00
Roman Grundkiewicz	3173a56422	Add script to train word2vec embeddings	2017-06-30 13:47:30 +01:00
Marcin Junczys-Dowmunt	8087a0449b	remove old scripts and examples	2017-01-21 13:14:00 +00:00
Marcin Junczys-Dowmunt	828a0db8bc	avoid reallocation of temporary tensors	2016-09-21 02:38:12 +02:00
Marcin Junczys-Dowmunt	a057ff1776	working dropout node	2016-09-21 00:39:27 +02:00
Marcin Junczys-Dowmunt	8797b5ffd3	reluplus node for testing, clean up	2016-09-19 22:43:12 +02:00
Marcin Junczys-Dowmunt	0f64f338cb	better visualization, Relu specific functions	2016-09-19 19:31:45 +02:00
Marcin Junczys-Dowmunt	9f9ca7a02b	broadcasting in kernels	2016-09-19 17:12:56 +02:00
Marcin Junczys-Dowmunt	cd7dbfc0f6	attempts at relu and dropout nodes	2016-09-19 12:06:04 +02:00
Marcin Junczys-Dowmunt	2800fcd904	fixed(?) bug in TanhOpNode, weird operator priority in bound lambdas	2016-09-19 02:07:16 +02:00
Marcin Junczys-Dowmunt	bfd9c369f8	preparing mnist benchmark	2016-09-17 19:52:56 +02:00
Maximiliana Behnke	ea04f8a6ba	Modify single layer training script, add 2-layer training script	2016-09-14 18:56:13 +02:00
Maximiliana Behnke	2c39bad1d6	Add test model training script	2016-09-14 14:27:08 +02:00
Marcin Junczys-Dowmunt	3db0f30312	function keywords	2016-05-08 18:42:19 +02:00