Release v4.0 · dreamquark-ai/tabnet

What's Changed

fixes minor README typos and improves readability and consistency by @discdiver in #272
feat: raise error in case cat_dims and cat_idxs are incoherent by @eduardocarvp in #289
feat: pretraining matches paper by @Optimox in #302
docs: add conventional commits to readme by @eduardocarvp in #286
WIP fix: update gpg key in docker file gpu by @Optimox in #339
feat-312: replace prints by warnings by @Optimox in #337
fix: custom loss using inplace operations by @eduardocarvp in #323
feat: disable tests in docker file gpu to save CI time by @Optimox in #342
feat/336 : check if pandas df and drop_last default to True by @Optimox in #338
feat: add warm_start matching scikit-learn by @Optimox in #340
Added conda install instruction by @sugatoray in #347
Bugfix - pretraining oom by @eduardocarvp in #348
fix: feature importance not dependent from dataloader by @Optimox in #372
feat: add augmentations inside the fit method by @Optimox in #363
chore: update dockerfile_gpu to latest version by @Hartorn in #409
fix: README patience to 10 by @Optimox in #396
chore: fix release scripts by @Hartorn in #412

Full Changelog: v3.1.1...v4.0