v1.4.0

What's Changed

• Support arrowdataset by @parmidaatg in #142
• Give ability for users to get uncertainty values. by @Dref360 in #144
• #146 Fix issue where at most a single submodule was affected by Dropout by @Dref360 in #147
• #131 Use poetry instead of setup.py by @Dref360 in #148
• #145 Example using MLP on MNIST by @Dref360 in #150
• mlp regression experiment by @parmidaatg in #152
• #130 Add mypy and step to test imports by @Dref360 in #155

Full Changelog: v1.3.1...1.4.0

v1.3.1

Changelog:

• Update pytorch-lightning to > 1.3.0 API
• Make torchvision and huggingface optional dependencies.
• New tutorial on Fairness and how to use Label Studio.

v1.3.0

BaaL 1.3.0 is a release focused on UX.

Features

• Initial support for HF Trainer along with tutorials to use HuggingFace.
• Initial support for Semi-supervised learning, we are eager to see what the community will do with such a powerful tool!
• Fixes in ECE computation

Documentation

The biggest change in this release is the new website along with tons of content.

1. Tutorial on Deep Ensembles #94
2. Tutorial on NLP Classification #87
3. Tutorial on visualisation.
4. Added a BaaL cheatsheet to translate equations to code easily.
5. Added a list of "Core papers" to get new users started in Bayesian deep learning.

BaaL v1.2.1

Changelogs

Features

• Initial support for ensembles. Example to come.
• Initial support for Pytorch Lightning. Example here.

Bugfixes

• Fix BALD for binary classification
• Fix Random heuristic for generators
• Fix to_cuda for strings.
• Fix a bug where MCDropconnect would not work with DataParallel

Misc

• Warning when no layers are affected by patch_layers in MCDropout, MCDropconnect.

v1.2.0

Changelist for v1.2.0

• Add DirichletCalibration (Kull et al. 2019), see our blog post.
• Add ECE Metrics for computing model's calibration.
• Add support for Multi-Input/Output for ModelWrapper
• Fix BatchBALD to be consistent with the official implementation
• Add ConsistentDropout, where the masks used in MC-Dropout are the same for each input.

Important notes

• BaaL is now part of Pytorch Ecosystem!

V1.1.0

BaaL v1.1 release notes

Changelog

• Support for MC-Dropconnect (Mobiny, 2019)
• ActiveLearningDataset now has better support for attributes specifics to the pool (see below).
• More flexible support multi-inputs/outputs in ModelWrapper.
  • Can support list of inputs or outputs.
• QoL features on ActiveLearningDataset
  • Can use a RandomState and add load_state_dict.
• Add replicate_in_memory flag to ModelWrapper.
  • If False, the MC iterations are done in a for-loop instead of making a batch in memory.
  • (This means predict_on_batch would not take up more memory than e.g. test_on_batch)
• Add patience and min_epoch_for_es to ModelWrapper.train_and_test_on_datasets.
  • Allows early stopping.
• New tutorial on how to use BaaL with scikit-learn.
• Can now combine heuristics for multi-outputs models (see baal.active.heuristics.Combine).
• Fix documentation

New ActiveLearningDataset

To better support new tasks, ActiveLearningDataset can now support any attributes to be overrided when the pool is created.

Example:

from PIL import Image
from torch.utils.data import Dataset
from torchvision.transforms import Compose, ToTensor, RandomHorizontalFlip
from baal.active.dataset import ActiveLearningDataset


class MyDataset(Dataset):
    def __init__(self):
        self.my_tansforms = Compose([RandomHorizontalFlip(), ToTensor()])
        
    def __len__(self):
        return 10
        
    def __getitem__(self, idx):
        x = Image.open('an_image.png')
        return self.my_tansforms(x)
        
al_dataset = ActiveLearningDataset(MyDataset(),
                                   pool_specifics={
                                   'my_tansforms': ToTensor()
                                   })
                                   
# Now `pool.my_tansforms = ToTensor()`
pool = al_dataset.pool