Expand description
Inference-only model format for WASM deployment
This module provides a pure Rust implementation of neural network inference
that stays off the training-side Burn tensor stack so it can compile to
WebAssembly with a minimal bundle size. The training side (PPO/DQN) runs
on Burn; weights are exported as JSON and consumed here for browser
inference. See crate::inference module docs and docs/WASM_ROADMAP.md.
Structs§
- Inference
Model - A serializable MLP model for inference
- SnakeCNN
Inference - A serializable CNN model for Snake inference
- Training
Metadata - Training metadata for the model
Enums§
- Inference
Activation - Activation function type for inference