- 06 8月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 05 8月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 03 8月, 2021 2 次提交
- 19 7月, 2021 1 次提交
-
-
由 Javier 提交于
Added option for custom dataloader and the possibility of using metrics from torchmetrics
-
- 18 7月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 17 7月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Fixed a series of breaking changes related to the metrics returning arrays. Adapted docs to the new functionalities
-
- 11 7月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 07 7月, 2021 2 次提交
-
-
由 Pavol Mulinka 提交于
-
由 Pavol Mulinka 提交于
I kept almost all previous code as it was, I just added functionality for custom dataloaders and possibility to use torchmetrics
-
- 26 6月, 2021 7 次提交
-
-
由 Javier 提交于
Tabnet
-
由 jrzaurin 提交于
Specified python 3.7 version to avoid a test fail when using travis that I cannot reproduce locally neither on the mac or on a ubuntu machine
-
由 jrzaurin 提交于
Specified python 3.7 version to avoid a test fail when using travis that I cannot reproduce locally neither on the mac or on a ubuntu machine
-
由 jrzaurin 提交于
-
由 jrzaurin 提交于
-
由 jrzaurin 提交于
-
由 jrzaurin 提交于
-
- 21 6月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Refined documentation. Added some test for saving model. Added an example notebook. Ready to test installations and publish v1 to pypi
-
- 19 6月, 2021 3 次提交
- 23 5月, 2021 1 次提交
-
-
由 jrzaurin 提交于
added get and setstate methods in the EarlyStopping and ModelCheckpoint callbacks. Added the possibility of using GRUs in the deeptext component and also predict using the hidden state or the output. Fixed a small bug in the text processor. Improved the save method in the Trainer
-
- 30 4月, 2021 1 次提交
-
-
由 jrzaurin 提交于
ModelCheckpoint saves best epoch as well. Added dropout option for tabnet. Adjusted RAdam for new signatures. Adjusted the training so it can take ReduceLROnPlateau. Also so that it automatically restores the best weights after training
-
- 16 4月, 2021 2 次提交
- 09 4月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Fixed a documentation error. For the tabtransformer the input_embed is a list with tuples of 2 elements, not 3
-
- 19 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 18 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Change tab_resnet to tab_resnet_blks. Added types to tab_net.py. Cleaned up trainer by moving some methods to tab_net_utils. Adjusted tests
-
- 15 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Added a few types, refined the docs and added tests for tabnet and the corresponding functionalities
-
- 12 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
added an option to automatically set embed size via fastai's rule of thumb. Re-structure the preprocessing module, breaking it up in a smaller modules for better debugging and 'tractability'
-
- 11 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
added explain and compute feature importance methods to the trainer. Need to add error handling and messaging since these funcionalities are intended only for tabnet. Move the general_utils module to the training module and rename it as trainer_utils. Adapted the create_explain_matrix function to WideDeep
-
- 06 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 05 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
finished implementing TabNet encoder. Next I need to implement the interpretability methods. Also adjusted WideDeep class to be able to work with TabNet. Renamed some example scripts to be consistent with each other
-
- 02 3月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 28 2月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 22 2月, 2021 1 次提交
-
-
由 jrzaurin 提交于
fixed a naming inconsistency. The Transformer encoder blocks were named 'blks'. A more consistent name relative to the other two tab models would be 'tab_transformer_blks', and so I have changed it. This leads to a small inconsistency between pypi version and that in github, which is almost irrelevant
-
- 14 2月, 2021 2 次提交
- 11 2月, 2021 2 次提交