decagon-pytorch

IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an email to s dot adaszewski at gmail dot com. User accounts are meant only to report issues and/or generate pull requests. This is a purpose-specific Git hosting for ADARED projects. Thank you for your understanding!

作成者	SHA1	メッセージ	日付
Stanislaw Adaszewski	b5d2f8fcda	Start implementing RelationFamily.	4年前
Stanislaw Adaszewski	56ce7aa60b	Add type checks to DecodeLayer.	4年前
Stanislaw Adaszewski	15e95bdc72	Use hints instead of is_autogenerated.	4年前
Stanislaw Adaszewski	53cd182e6b	Modify decoders to handle one relation at a time.	4年前
Stanislaw Adaszewski	eda27bee0e	Increase test coverage.	4年前
Stanislaw Adaszewski	bd894a0257	Move back to using single-level dictionary for Data.relation_types.	4年前
Stanislaw Adaszewski	f51855e5b3	Add first test for declayer.	4年前
Stanislaw Adaszewski	1868014ca3	Work on declayer.	4年前
Stanislaw Adaszewski	dd0eb81251	Add tests for decode.	4年前
Stanislaw Adaszewski	a305dc70aa	Add tests for convlayer.	4年前
Stanislaw Adaszewski	d4dd1f2923	Add input to icosagon.	4年前
Stanislaw Adaszewski	07a82e0da9	Work on icosagon.	4年前
Stanislaw Adaszewski	d503fb5738	Bring more elements to icosagon.	4年前
Stanislaw Adaszewski	706ff0b009	New implementation of normalize for one/two node types and sparse/dense - good.	4年前
Stanislaw Adaszewski	6f80b65a46	New implementation for one node type normalization seems to work.	4年前
Stanislaw Adaszewski	05b1ecf47a	Start rework normalize.	4年前
Stanislaw Adaszewski	584bf19c3f	Work on icosagon.trainprep.	4年前
Stanislaw Adaszewski	7ed4bc373a	Work on icosagon.trainprep.	4年前
Stanislaw Adaszewski	3795545674	Start icosagon.	4年前
Stanislaw Adaszewski	456a037e58	Fix typo.	4年前
Stanislaw Adaszewski	a272a17f23	Work on trainprep.	4年前
Stanislaw Adaszewski	e201608caf	Add trainprep.	4年前
Stanislaw Adaszewski	28272e3d29	Add AdjListRelationType, AdjListData.	4年前
Stanislaw Adaszewski	fab210448d	Correct support for assymetric relations in Data.	4年前
Stanislaw Adaszewski	a74884dadd	Add train_val_test_split_adj_mat().	4年前
Stanislaw Adaszewski	7ab97e2fb6	Add test_unigram_03().	4年前
Stanislaw Adaszewski	f2121bef53	Add fixed_unigram_candidate_sampler().	4年前
Stanislaw Adaszewski	39aa1b4211	Implement and test pairwise decoders.	4年前
Stanislaw Adaszewski	c1689b4985	Split decoders into cartesian and pairwise.	4年前
Stanislaw Adaszewski	b08ae2e160	Test for an approach to pairwise (rather than cartesian product) link predition.	4年前
Stanislaw Adaszewski	4f243fbc04	Copyright notes.	4年前
Stanislaw Adaszewski	c37e4dc01e	Ok the very first decoding seems to work end-to-end.	4年前
Stanislaw Adaszewski	1d2fac0919	Split layer into submodules.	4年前
Stanislaw Adaszewski	52be4061b3	Adjust DecagonLayer to normalize per edge type.	4年前
Stanislaw Adaszewski	241a2f92b9	Fix tests.	4年前
Stanislaw Adaszewski	c74555fef5	Refactor convolve into 3 separate modules.	4年前
Stanislaw Adaszewski	02bbfc4958	Add test_decagon_layer_04().	4年前
Stanislaw Adaszewski	69e8ce5081	Add universal convolution units that can handle both sparse and dense inputs.	4年前
Stanislaw Adaszewski	99dbcdeb91	Prefix dense versions of convolution classes with Dense.	4年前
Stanislaw Adaszewski	29e81f4eba	Add test for DecagonLayer.	4年前
Stanislaw Adaszewski	69dd9a49e2	Dummy run of DecagonLayer seems to work, that's something.	4年前
Stanislaw Adaszewski	2188dc7ae2	Basic constructor test for DecagonLayer passes.	4年前
Stanislaw Adaszewski	60d8a43c12	Fix the DecagonLayer logic.	4年前
Stanislaw Adaszewski	d56bbf745f	Better way to compute DecagonLayer.	4年前
Stanislaw Adaszewski	8c3e949637	Baby steps.	4年前
Stanislaw Adaszewski	2cdc76fac7	Prepare to make Decagon layer work.	4年前
Stanislaw Adaszewski	c45e0fa9f1	Make InputLayer support variable dimensionality representations.	4年前
Stanislaw Adaszewski	2e5e1d69ac	Add support for multiple input_dim in MultiDGCA.	4年前
Stanislaw Adaszewski	e371a83352	Add support for multiple input_dim in SparseMultiDGCA.	4年前
Stanislaw Adaszewski	46c2c676ba	Add type annotations to convolve.	4年前

1 2

66 コミット (b5d2f8fcda9288394504427477eb6514310c73a0)