- 26 12月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 06 12月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Fix some minor type and style issues. Adjusted the ZILN Loss so it works with former versions of pytorch and rename quantile regression multilabel label as qregression
-
- 29 11月, 2021 1 次提交
-
-
由 Pavol Mulinka 提交于
-
- 20 11月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Against all good practices, this is a massive commit that adds an entire new module with Bayesian models (that are still not functional). Making them functional requires some work. Also the entire models module has been restrucured in preparation for better days to come
-
- 19 11月, 2021 1 次提交
-
-
由 Pavol Mulinka 提交于
-
- 01 9月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 24 8月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 11 7月, 2021 1 次提交
-
-
由 jrzaurin 提交于
-
- 07 7月, 2021 1 次提交
-
-
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
-
- 16 4月, 2021 1 次提交
-
-
由 jrzaurin 提交于
Modified the callbacks to accomodate the neccessity of the ReduceLROnPlateau scheduler. Replace weight by pos_weight in BCEWithLogitsLoss. Added on_eval_begin method to reset metrics
-
- 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
-
- 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
-
- 24 1月, 2021 1 次提交
-
-
由 jrzaurin 提交于
added the possibility of passing a few more loss functions and custom ones if required. Now I need to think if I want it registered as a child or not. Also, need to test all new implementation
-