mmlearn.modules.layers

Custom, reusable layers for models and tasks.

attention	Attention modules for Vision Transformer (ViT) and related models.
embedding	Embedding layers.
logit_scaling	Learnable logit scaling layer.
mlp	Multi-layer perceptron (MLP).
normalization	Normalization layers.
patch_dropout	Patch dropout layer.
transformer_block	Transformer Block and Embedding Modules for Vision Transformers (ViT).