mlr3torch
mlr3torch copied to clipboard
mlr-org
Deep learning framework for the mlr3 ecosystem based on torch
What we want to compare: **Deep Learning Libraries** * R: torch * R: mlr3torch * python: pytorch **Dataset**: guess the corellation -> regression problem **Device**: cpu and cuda
Better error message: Say which shape is expected.
Bumps [JamesIves/github-pages-deploy-action](https://github.com/jamesives/github-pages-deploy-action) from 4.6.0 to 4.6.1. Release notes Sourced from JamesIves/github-pages-deploy-action's releases. v4.6.1 What's Changed Fixes Resolved an issue where workflows were suddenly failing due to a worktree in use...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
``` r library(mlr3torch) #> Loading required package: mlr3 #> Loading required package: mlr3pipelines #> Loading required package: torch task = tsk("lazy_iris") x = task$data(cols = "x") d = data.table(x,y =...
depends on: https://github.com/mlverse/torch/pull/1134 * [ ] Ensure that the parameters that the optimizer points to are those of the network after cloning * [ ] run expect deep clone on...
suggestion: ```r learner = lrn("classif.mlp", callbacks = t_clbk("history")) learner$param_set$set_values(history = FALSE) disactivates the history ``` This is needed for early stopping.
* [ ] Graph (PipeOpModule) * [ ] nn_graph * [ ] GraphLearner * [ ] also check that hash and phash differ