Skip to content

Issues: mlr-org/mlr3torch

Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

45 Open 231 Closed
45 Open 231 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

LearnerTorch Base class should offer private method .task_dataset that is used by default in .task method
#387 opened Apr 17, 2025 by sebffischer
nn_graph should not require specifying input shapes
#383 opened Apr 14, 2025 by sebffischer
Improve documentation for PipeOpTorchIngress
#380 opened Apr 10, 2025 by sebffischer
1
Better options for debugging a deep learning graph
#379 opened Apr 10, 2025 by sebffischer
Maybe consider specialized dataloader when tensor_dataset = TRUE
#378 opened Apr 7, 2025 by sebffischer
LearnerTorchModel should be added to dictionary of learners
#376 opened Apr 3, 2025 by sebffischer
tensor size errors for bce_with_logits loss / net which outputs 1d tensor
#373 opened Apr 2, 2025 by tdhock
5
Add po("trafo_custom") that wraps or replaces pipeop_preproc_torch
#368 opened Mar 21, 2025 by sebffischer
PipeOpTorchModel should expose fields callbacks, optimizer and loss so they can be changed afterwards
#366 opened Mar 21, 2025 by sebffischer
example of creating your own task?
#361 opened Feb 17, 2025 by tdhock
8
Add feature that allows to train a LearnerTorch on task where the target is also a lazy tensor
#357 opened Feb 14, 2025 by sebffischer
Better error messages when network diverges and yields NA predictions
#353 opened Feb 8, 2025 by sebffischer
Use nn(" instead of po("nn_") in examples
#346 opened Feb 6, 2025 by sebffischer
Add vignette on performance
#342 opened Feb 4, 2025 by sebffischer
Create LearnerTorchFTTransformer
#338 opened Jan 24, 2025 by sebffischer
Create PipeOpTorch for nn_cls token
#337 opened Jan 24, 2025 by sebffischer
Create PipeOp for the refactored nn_ft_transformer_block
#336 opened Jan 24, 2025 by sebffischer
nn_ft_transformer_block should just be a single block, not multiple blocks. Seperate the output head in its own nn_module
#335 opened Jan 24, 2025 by sebffischer
More callbacks
#331 opened Jan 23, 2025 by sebffischer
Implement a learning rate finder
#325 opened Jan 20, 2025 by sebffischer
1
Possibility to easily display images from a lazy-tensor
#324 opened Jan 15, 2025 by sebffischer
Add tuningspace for tabular resnet, mlp, ft
#304 opened Nov 25, 2024 by sebffischer
How to Dynamically Tune the Number of Layers in a Neural Network Using mlr3torch?
#285 opened Sep 26, 2024 by iLivius
13
simple use case: rf vs torch: no factors, no missing values
#284 opened Sep 12, 2024 by sebffischer
@cxzhang4
1
Create realistic use cases for the package
#273 opened Aug 21, 2024 by sebffischer
8 tasks
ProTip! Adding no:label will show everything without a label.