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!

58 コミット (53cd182e6ba2f0d4d42203bdb035a52ca802cf24)

作成者 SHA1 メッセージ 日付
  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 dc92634830 Same test with torch.nn.Sequential. 4年前
  Stanislaw Adaszewski 1868014ca3 Work on declayer. 4年前
  Stanislaw Adaszewski 6d0039b447 Add test for init_glorot. 4年前
  Stanislaw Adaszewski 702079c7e9 Add sampling tests. 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 28272e3d29 Add AdjListRelationType, AdjListData. 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 0f1afa3d2c Put back layer tests. 4年前
  Stanislaw Adaszewski c37e4dc01e Ok the very first decoding seems to work end-to-end. 4年前
  Stanislaw Adaszewski 4ac42e5b3c Add test_decagon_layer_05(). 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 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 5d8c2d08c4 Add tests for OneHotInputLayer. 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 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 5464c5a4c1 Add InputLayer. 4年前
  Stanislaw Adaszewski 21b2565720 Changed Data architecture a bit. 4年前
  Stanislaw Adaszewski 71bf338491 Start implementing Minibatch. 4年前
  Stanislaw Adaszewski d835b049b0 test_normalize 4年前
  Stanislaw Adaszewski ecabdc0540 Add simple class to hold graph data. 4年前
  Stanislaw Adaszewski e26ccd4222 Added InnerProductDecoder and test. 4年前
  Stanislaw Adaszewski 438ba67565 Add BilinearDecoder and test. 4年前
  Stanislaw Adaszewski c4aefc0150 Added DistMultDecoder with test. 4年前
  Stanislaw Adaszewski 353fc8913e Added DEDICOMDecoder with test. 4年前