Crate candle_nn

source

Re-exports§

Modules§

  • Batch Normalization.
  • Convolution Layers.
  • Embedding Layer.
  • Encoding Utilities. (e.g., one-hot/cold encoding)
  • Layers defined by closures.
  • Group Normalization.
  • Variable initialization.
  • Layer Normalization.
  • Linear layer
  • Various optimization algorithms.
  • Recurrent Neural Networks
  • A sequential layer used to chain multiple layers and closures.
  • A VarBuilder is used to retrieve variables used by a model. These variables can either come from a pre-trained checkpoint, e.g. using VarBuilder::from_mmaped_safetensors, or initialized for training, e.g. using VarBuilder::from_varmap.

Traits§