A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch
Mostly fixed issue #204
Added two new embedding methods for numerical features described in On Embeddings for Numerical Features in Tabular Deep Learning and adjusted all models and functionalities accordingly
This release mainly adds the functionality to be able to deal with large datasets via the load_from_folder
module.
This module is inspired by the ImageFolder
class in the torchvision
library but adapted to the needs of our library. See the docs for details.
TabPerceiver
. This functionality is accessed via the feature_importance
attribute in the trainer (computed during training with a sample of observations) and at predict time via de explain
method.EarlyStopping
and the ModelCheckpoint
Callbacks. Prior to this release there was a bug and the weights were not restored.Simple minor release fixing the implementation of the additive attention (see #110 )
There are a number of changes and new features in this release, here is a summary:
Refactored the code related to the 3 forms of training in the library:
Trainer
class)EncoderDecoderTrainer
class): this is inspired by the TabNet paper
ConstrastiveDenoising
class): this is inspired by the SAINT paper
BayesianTrainer
: this is inspired by the paper Weight Uncertainty in Neural Networks
Just as a reminder, the current deep learning models for tabular data available in the library are:
The text related component has now 3 available models, all based on RNNs. There are reasons for that although the integration with the Hugginface Transformer library is the next step in the development of the library. The 3 models available are:
The last two are based on Hierarchical Attention Networks for Document Classification. See the docs for details
The image related component is now fully integrated with the latest torchvision release, with a new Multi-Weight Support API. Currently, the model variants supported by our library are: