41 Commits

Author	SHA1	Message	Date
Jin Yong Yoo	21496460fe	add embedding layer retrieval to models	2020-11-01 00:58:15 -04:00
Yanjun Qi	23d0de6b43	clean up the docstring of each module and module content section	2020-10-25 23:15:07 -04:00
Jack Morris	576876257f	merge and format	2020-07-12 20:40:22 -04:00
jakegrigsby	185c17eb77	set emb_layer grad back to original flag (fix #209)	2020-07-12 16:05:09 -04:00
Hanyu Liu	974061c0aa	Reformatting-try1	2020-07-10 19:21:02 -04:00
Jack Morris	c0a3a734d8	adding AG News models	2020-07-07 20:45:51 -04:00
jind11	f72f49d5db	make embedding layer default to be trainable	2020-07-05 22:19:33 -04:00
Jack Morris	58cada77d5	isort updates	2020-07-05 21:51:53 -04:00
jind11	d7476b30ad	refine model training code	2020-07-04 21:17:57 -04:00
Jack Morris	b6eed3dd08	update tests	2020-06-25 22:54:01 -04:00
Jack Morris	af2541cf2b	remove spacy; add 3 MR models	2020-06-25 22:26:12 -04:00
Jack Morris	249f6e4841	updates; examples; docs	2020-06-24 14:15:56 -04:00
Jack Morris	75304e1f98	fix lstm dataparallel and print pearson correlation	2020-06-24 10:49:31 -04:00
Jack Morris	4b2cb255cb	update and pass tests	2020-06-24 00:58:27 -04:00
Jack Morris	0d91781e88	write logs to files	2020-06-23 21:45:06 -04:00
Jack Morris	4772831527	fix classes typo	2020-06-21 00:04:00 -04:00
Jack Morris	05e86a8f03	support training for entailment and fix test, update README	2020-06-20 23:46:52 -04:00
Jack Morris	f3a4accdc4	merge in tokenized-text-refactor	2020-06-18 16:33:06 -04:00
Jack Morris	462620e074	trimming the fat; removing excess stuff; changing names	2020-06-18 11:12:36 -04:00
Jack Morris	90e6872eb4	ugly merge with recent master	2020-06-17 21:45:50 -04:00
Jack Morris	d6e90065c2	format pre-merge	2020-06-17 19:47:33 -04:00
Jack Morris	4d74aa5316	adding models; refactoring to use nlp datasets where possible	2020-06-17 19:39:56 -04:00
Jack Morris	07e927e3e4	add isort and fix import loops, preparing to shorten tests	2020-06-15 20:40:44 -04:00
Jack Morris	1d8a172c05	code formatting; tokenizers->models/tokenizers	2020-06-15 18:36:04 -04:00
Jack Morris	fcb82dac5e	makefile and setup; need to fix imports	2020-06-15 17:07:12 -04:00
Jack Morris	c4329985a0	working on SST models and parallel memory issue	2020-06-15 13:55:07 -04:00
Jack Morris	62d3a1070c	README; get_logger()->logger	2020-06-05 20:12:14 -04:00
Jack Morris	6ea77cca6d	Merge branch 'master' of github.com:QData/TextAttack into kuleshov	2020-05-06 13:33:17 -04:00
Jack Morris	d647133230	add thought vectors	2020-05-06 11:16:17 -04:00
Jack Morris	1a5ff59190	hotflip works, slowly -- need to reduce # of backwards passes	2020-05-05 13:46:02 -04:00
Jack Morris	0b400f3330	hotflip not registering hook	2020-05-05 12:25:58 -04:00
Jack Morris	ad75e69b1b	reorganize: scripts/ folder; shared/ folder; attack_methods/ instead of attack/; only take a single transformation as an argument	2020-01-19 14:25:30 -05:00
Jack Morris	0de4e181b6	move config cache location, download datasets as text files, add helper method for loading nn.module models from cache	2020-01-09 12:51:51 -05:00
Jack Morris	da1613d663	upload word vectors, CNN, LSTM	2020-01-08 18:28:54 -05:00
Jack Morris	a2e3ec739c	move tokenizer out of model class and fix some bugs	2019-11-29 16:53:00 -05:00
Jack Morris	88996d4a05	separate model and tokenizer functionality	2019-11-29 16:02:52 -05:00
Jack Morris	ea489de447	add softmax for CNN and LSTM and remove unneeded code	2019-11-19 12:12:02 -05:00
Jack Morris	f71e09ec15	rename stuff after Eli's suggestions and fix dropout warning when lstm has 1 layer	2019-11-08 11:53:56 -05:00
Jack Morris	689b79fd20	ensure models work when cuda is not available	2019-11-07 19:01:31 -05:00
Jack Morris	883e135439	fix CNN dimensionality issue and add documentation everywhere	2019-11-07 17:36:14 -05:00
Jack Morris	a85e11538c	reorganize models and add helpers. add lstm. add cnn. need to fix dimension mismatch in pretrained cnn	2019-11-07 15:46:26 -05:00