Expand description
nn modules for zyx ML library
Structs§
- Batch
Norm - Batch norm
- Causal
Self Attention - Causal self attention
- Conv2d
- Applies a 2D convolution over an input signal composed of several input planes.
- Embedding
- Embedding layer
- GRUCell
- GRU cell (PyTorch-style)
- Group
Norm - Group normalization
- LSTM
Cell - A single LSTM (Long Short-Term Memory) cell.
- Layer
Norm - A Layer Normalization layer.
- Linear
- Linear layer
- Multihead
Attention - Implements multi-head attention as described in “Attention Is All You Need”.
- Positional
Encoding - Sinusoidal positional encoding module for transformers.
- RMSNorm
- RMS norm layer
- RNNCell
- An Elman RNN cell with optional nonlinearity.
- Transformer
Decoder Layer - A single layer of a Transformer decoder.
- Transformer
Encoder Layer - A single Transformer Encoder layer, analogous to
torch.nn.TransformerEncoderLayer.
Derive Macros§
- Module
- Procedural macro Module