1.1.4

[1.1.4] - 2022-09-29

Changed

• Improoved mltu.torch.dataProvider.DataProvider to hangle multiprocessing when it doesn't work to switch to multithreading

1.1.3

[1.1.3] - 2022-09-29

Changed

• Removed Librosa library dependency in requirements, now it is optional and required only with modules that use librosa

Added

• Created Tutorials.05_sound_to_text.train_no_limit.py that demonstrates how to train audio recognition model with mltu without audio length limit

1.1.1

[1.1.1] - 2022-09-26

Changed

• Included self._executor as generator in mltu.dataProvider.DataProvider object, to enable functionality to modify batch preprocessing without changing original code
• Introduced changes in mltu.torch.dataProvider.py to handle data in multiprocessing and multithreading modes, for faster preprocessing while torch models
• Modified mltu.transformers.AudioPadding object, to work with batches of raw audio data

Added

• Created tutorial 10_wav2vec2_torch (Audio to Text model) that shows how to train wav2vec2 model with mltu

1.1.0

[1.1.0] - 2022-08-28

Changed

• Changed mltu.transformers.SpectrogramPadding object, to pad spectrogram end with zeros instead of start

Added

• Created Tutorials/09_translation_transformer tutorial, that shows how to train translation transformer model
• Created mltu.tensorflow.tokenizers module, that contains CustomTokenizer for text data
• Created mltu.tensorflow.transformer.attention module, that contains BaseAttention, CrossAttention, GlobalSelfAttention and CausalSelfAttention layers
• Created mltu.tensorflow.transformer.layers module, that contains positional_encoding function, PositionalEmbedding, FeedForward, EncoderLayer, DecoderLayer, Encoder, Decoder layers and Transformer model
• Created mltu.tensorflow.transformer.callbacks module, that contains EncDecSplitCallback callback, to split Transformer model into separate encoder and decoder models
• Created mltu.tensorflow.transformer.utils module, that contains MaskedLoss loss and MaskedAccuracy metric, used for training Transformer models

1.0.15

[1.0.15] - 2022-07-15

Changed

• Fixed bug in mltu.dataProvider.DataProvider to work with batch_postprocessors.

1.0.14

[1.0.14] - 2022-07-13

Changed

• Included augment_annotation bool option to all mltu.augmentors to be able to choose whether to augment annotation or not
• Changed mltu.augmentors.RandomRotate to have @staticmethod of rotate_image to be able to use it without creating object

Added

• Added batch_postprocessor option to mltu.dataProvider.DataProvider to be able to postprocess batch after augmentation

1.0.12

1.0.12

1.0.11

Release 1.0.11 with some bug fixes

1.0.10

new release with minor changes

1.0.9

Spelling mistake fixes, single quotes to double quotes, introduced CVImage and PillowImage objects