eschibli

max_model_size is not useful with ImageClassifier

10

### Bug Description When `max_model_size` is set below 63812570, ImageClassifier will repeatedly try to build a model with an EfficientNet-B7 backbone, then throw a RuntimeError. EfficientNet-B7 is a very large...

Hello devs, I have a small amount of data and need to oversample outliers without undersampling my original data. However, running SMOGN with `under_samp`=False appears to return _only_ the synthetic...

[BUG] ImportError: cannot import name 'case_insensitive_dict' from 'azure.core.utils'

2

## Which example? Describe the issue example: image_classification_keras_minist_convnet.ipynb description: I am unable to run this example as `from azure.ai.ml import MLClient` in the first cell throws an import error. ##...

Allow other initialization strategies for IterativeImputer

1

### Describe the workflow you want to enable I want to initialize an `IterativeImputer` using a `KNNImputer` rather than a `SimpleImputer`. ### Describe your proposed solution Modifying `IterativeImputer` to accept...

Improvement/Adds temporal_hidden_size_past and temporal_hidden_size_future hyperparams to TiDEModel

1

Checklist before merging this PR: - [x] Mentioned all issues that this PR fixes or addresses. - [x] Summarized the updates of this PR under **Summary**. - [x] Added an...

The implementation of TiDE currently uses `hidden_size` for both the hidden layer of the covariates encoder (applied timestep-wise) and for the dense encoder (applied after flattening). This does not seem...

[FEAT] Add tsmixer-basic

2

tsmixer was original reported as two different models, tsmixer-basic (which allows for past covariates and is called simply tsmixer in the paper) and tsmixer-ext, which allows for past, future, and...

Imp/tsmixer basic

13

Checklist before merging this PR: - [x] Mentioned all issues that this PR fixes or addresses. - [x] Summarized the updates of this PR under **Summary**. - [x] Added an...

Clarify intended behavior of model.backtest and model.historical_forecast with multiple series and allow training on multiple series per fold when backtesting

2

**Is your feature request related to a current problem? Please describe.** It is unclear from the documentation that `model.historical_forecasts` and `model.backtest` will only ever train on a single series at...

[FEAT] Expose RINorm kwargs

1

**Is your feature request related to a current problem? Please describe.** This would largely address [#2739 - RIN is not scale invariant](https://github.com/unit8co/darts/issues/2739) **Describe proposed solution** Exposing the RINorm hyperparameters would...