Eager neural network modules using the nn API.

Classes

• Module: Base class for all eager neural network modules.
• Conv2d: 2D convolution layer.
• Embedding: Embedding lookup table.
• Linear: Linear (fully connected) layer.
• Sequential: Sequential container of modules.

Subpackages

• max.experimental.nn.norm: Normalization layers (RMSNorm, LayerNorm, GroupNorm, GemmaRMSNorm).
• max.experimental.nn.rope: Rotary positional embeddings (RotaryEmbedding, TransposedRotaryEmbedding).

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit