Releases: mlr-org/mlr3torch
Releases · mlr-org/mlr3torch
0.3.0
Breaking Changes:
- The output dimension of neural networks for binary classification tasks is now
expected to be 1 and not 2 as before. The behavior ofnn("head")
was also changed to match this.
This means that for binary classification tasks,t_loss("cross_entropy")
now generates
nn_bce_with_logits_loss
instead ofnn_cross_entropy_loss
.
This also came with a reparametrization of thet_loss("cross_entropy")
loss (thanks to @tdhock, #374).
New Features:
PipeOps & Learners:
- Added
po("nn_identity")
- Added
po("nn_fn")
for calling custom functions in a network. - Added the FT Transformer model for tabular data.
- Added encoders for numericals and categoricals
nn("block")
(which allows to repeat the same network segment multiple
times) now has an extra argumenttrafo
, which allows to modify the
parameter values per layer.
Callbacks:
- The context for callbacks now includes the network prediction (
y_hat
). - The
lr_one_cycle
callback now infers the total number of steps. - Progress callback got argument
digits
for controlling the precision
with which validation/training scores are logged.
Other:
TorchIngressToken
now also can take aSelector
as argumentfeatures
.- Added function
lazy_shape()
to get the shape of a lazy tensor. - Better error messages for MLP and TabResNet learners.
- TabResNet learner now supports lazy tensors.
- The
LearnerTorch
base class now supports the private method$.ingress_tokens(task, param_vals)
for generating thetorch::dataset
. - Shapes can now have multiple
NA
s and not only the batch dimension can be missing. However, mostnn()
operators
still expect only one missing values and will throw an error if multiple dimensions are unknown. - Training now does not fail anymore when encountering a missing value
during validation but usesNA
instead. - It is now possible to specify parameter groups for optimizers via the
param_groups
parameter.
0.2.1
See NEWS.md
0.2.0
See NEWS.md
0.1.2
v0.1.2 release 0.1.2
0.1.1
v0.1.1 cran release (#287)
0.1.0
Initial CRAN release