mlr3torch
mlr3torch copied to clipboard
mlr-org
Deep learning framework for the mlr3 ecosystem based on torch
The goal here is to add a callback that logs the training and the validation error (if the latter exists) and is then displayed in the browser via tensorboard. The...
I would like to build a neural network with a tunable number of layers. While I can tune the number of neurons per layer, I’m encountering issues when it comes...
Goal: Compare random forests with a simple multi layer perceptron in a simple benchmark experiment. 1. We need to define the tasks: Use three simple small tasks from OpenML: https://mlr3book.mlr-org.com/chapters/chapter11/large-scale_benchmarking.html....
* [ ] think of some use-cases * [x] simple use case: xgboost vs torch: no factors, no missing values * [ ] xgboost vs deep learning: use datasets from...
[See learner_torch_methods.R ](https://github.com/mlr-org/mlr3torch/blob/40a3b17ccf73f928ee1bbd40684559346d76561f/R/learner_torch_methods.R#L150)
- [ ] As a sanity check, train the learner on a benchmark dataset. It should perform reasonably good predictions. Use early stopping. Time this training as well.
When we implemented the `FTTransformer`, it feels like a lot of unnecessary/duplicated code had to be written. If one wants to work with `mlr3torch`, we should have a convenience function...