This is because this library is designed to address classification and regression tasks and these are the most 'popular' encoder-only models, which have proved to be those that work best for these tasks. If there is demand for other models, they will be included in the future....
In [30], various linguistic features, such as term frequency, LDA and Word2Vec, are merged in a single input, and processed to train a classifier (e.g., SVM, Logistic Regression or Multi-Layer Perceptron). In [31], a semantic language model is used to extract prominent concepts and ...
The Mask R-CNN method is based on the Faster R-CNN structure by adding a mask branch that predicts the segmentation target mask, in parallel with the classification and regression branches, so that the Mask R-CNN has the function of instance segmentation [27]. The Rol Pooling layer is repl...
This is because this library is designed to address classification and regression tasks and these are the most 'popular' encoder-only models, which have proved to be those that work best for these tasks. If there is demand for other models, they will be included in the future....