mlr3torch
mlr3torch copied to clipboard
Deep learning framework for the mlr3 ecosystem based on torch
A sketch of the FT-Transformer graph.
Especially categ
The general approach would be to: * Define a `TaskClassifTorch` where the target feature type is a `lazy_tensor` (a long) * Define a `TaskRegrTorch` where the target feature type is...
Also requires: https://github.com/mlr-org/mlr3pipelines/issues/888 This would enable: ```{r} graph = po("torch_ingress_num") %>>% po("nn_head") %>>% ... graph$configure( torch_model_classif.callbacks = t_clbk("history") ) ```
Hi, I'm trying to implement a couple of torch learners on some custom data sets (tasks). I'm reading https://mlr3torch.mlr-org.com/articles/pipeop_torch.html which how do implement a convolutional network for the tiny_imagenet pre-defined...
https://arxiv.org/abs/1506.01186 I believe this might be the same as implemented here: https://mlverse.github.io/luz/reference/lr_finder.html but this needs to be checked. Whether this is a callback or just a simple function that takes...