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!

84 次程式碼提交 (f17f97caf4182231f97e40f32ac0039acff29f7b)

作者 SHA1 備註 提交日期
  Stanislaw Adaszewski f17f97caf4 Add test_model_07(). 4 年之前
  Stanislaw Adaszewski 414c93419f Add test_model_06(). 4 年之前
  Stanislaw Adaszewski cfb3d308a0 Add test_model_03(). 4 年之前
  Stanislaw Adaszewski 0578b13ea4 Fix prepare_adj_mat() by specifying shape explicitly. 4 年之前
  Stanislaw Adaszewski d5779daac3 Add test_model_01(). 4 年之前
  Stanislaw Adaszewski 346cc747a6 Add shuffle to PredictionsBatch. 4 年之前
  Stanislaw Adaszewski 908100cf45 Add Model. 4 年之前
  Stanislaw Adaszewski 72356545aa Remove loss as no longer necessary. 4 年之前
  Stanislaw Adaszewski a9f14d14a8 Add PredictionsBatch and test_predictions_btch_01(). 4 年之前
  Stanislaw Adaszewski ff4fb96bed Add CrossEntropyLoss and test_cross_entropy_loss_01(). 4 年之前
  Stanislaw Adaszewski 25e05cf1c2 Use torch.nn.Parameter(List) in decode. 4 年之前
  Stanislaw Adaszewski 55a5f3a2d2 Use torch.nn.ModuleList in convlayer. 4 年之前
  Stanislaw Adaszewski 8767db601d Remove node_type_row/node_type_column as redundant in add_relation_type(). 4 年之前
  Stanislaw Adaszewski e8122c3321 Get test_decode_layer_01 to pass. 4 年之前
  Stanislaw Adaszewski 832f620a78 Store relation types in a list instead of a dictionary and related fixes. 4 年之前
  Stanislaw Adaszewski 7eda6bdfb9 Fix regressions in trainprep. 4 年之前
  Stanislaw Adaszewski 915c568490 Small fix. 4 年之前
  Stanislaw Adaszewski 6c52bc1f71 Fix regressions in test_convlayer. 4 年之前
  Stanislaw Adaszewski b5d2f8fcda Start implementing RelationFamily. 4 年之前
  Stanislaw Adaszewski 56ce7aa60b Add type checks to DecodeLayer. 4 年之前
  Stanislaw Adaszewski 15e95bdc72 Use hints instead of is_autogenerated. 4 年之前
  Stanislaw Adaszewski 53cd182e6b Modify decoders to handle one relation at a time. 4 年之前
  Stanislaw Adaszewski eda27bee0e Increase test coverage. 4 年之前
  Stanislaw Adaszewski bd894a0257 Move back to using single-level dictionary for Data.relation_types. 4 年之前
  Stanislaw Adaszewski f51855e5b3 Add first test for declayer. 4 年之前
  Stanislaw Adaszewski 1868014ca3 Work on declayer. 4 年之前
  Stanislaw Adaszewski dd0eb81251 Add tests for decode. 4 年之前
  Stanislaw Adaszewski a305dc70aa Add tests for convlayer. 4 年之前
  Stanislaw Adaszewski d4dd1f2923 Add input to icosagon. 4 年之前
  Stanislaw Adaszewski 07a82e0da9 Work on icosagon. 4 年之前
  Stanislaw Adaszewski d503fb5738 Bring more elements to icosagon. 4 年之前
  Stanislaw Adaszewski 706ff0b009 New implementation of normalize for one/two node types and sparse/dense - good. 4 年之前
  Stanislaw Adaszewski 6f80b65a46 New implementation for one node type normalization seems to work. 4 年之前
  Stanislaw Adaszewski 05b1ecf47a Start rework normalize. 4 年之前
  Stanislaw Adaszewski 584bf19c3f Work on icosagon.trainprep. 4 年之前
  Stanislaw Adaszewski 7ed4bc373a Work on icosagon.trainprep. 4 年之前
  Stanislaw Adaszewski 3795545674 Start icosagon. 4 年之前
  Stanislaw Adaszewski 456a037e58 Fix typo. 4 年之前
  Stanislaw Adaszewski a272a17f23 Work on trainprep. 4 年之前
  Stanislaw Adaszewski e201608caf Add trainprep. 4 年之前
  Stanislaw Adaszewski 28272e3d29 Add AdjListRelationType, AdjListData. 4 年之前
  Stanislaw Adaszewski fab210448d Correct support for assymetric relations in Data. 4 年之前
  Stanislaw Adaszewski a74884dadd Add train_val_test_split_adj_mat(). 4 年之前
  Stanislaw Adaszewski 7ab97e2fb6 Add test_unigram_03(). 4 年之前
  Stanislaw Adaszewski f2121bef53 Add fixed_unigram_candidate_sampler(). 4 年之前
  Stanislaw Adaszewski 39aa1b4211 Implement and test pairwise decoders. 4 年之前
  Stanislaw Adaszewski c1689b4985 Split decoders into cartesian and pairwise. 4 年之前
  Stanislaw Adaszewski b08ae2e160 Test for an approach to pairwise (rather than cartesian product) link predition. 4 年之前
  Stanislaw Adaszewski 4f243fbc04 Copyright notes. 4 年之前
  Stanislaw Adaszewski c37e4dc01e Ok the very first decoding seems to work end-to-end. 4 年之前