"""Configurable MLP / linear model for multi-output regression or distribution heads.""" from __future__ import annotations from typing import Iterable, List import torch import torch.nn as nn from .registry import register_model def _activation(name: str) -> nn.Module: name = (name or "relu").lower() if name == "relu": return nn.ReLU() if name == "gelu": return nn.GELU() if name == "silu" or name == "swish": return nn.SiLU() if name == "tanh": return nn.Tanh() if name == "leaky_relu": return nn.LeakyReLU(0.01) raise ValueError(f"Unknown activation: {name}") def _output_activation(name: str | None) -> nn.Module: name = (name or "none").lower() if name in {"none", "identity"}: return nn.Identity() if name == "softplus": return nn.Softplus() if name == "relu": return nn.ReLU() if name == "sigmoid": return nn.Sigmoid() raise ValueError(f"Unknown output activation: {name}") @register_model("mlp") class MLP(nn.Module): def __init__( self, input_dim: int, output_dim: int, hidden_dims: Iterable[int] = (64, 64), dropout: float = 0.1, activation: str = "relu", output_activation: str = "softplus", output_type: str = "regression", n_classes: int = 87, input_dropout: float = 0.0, ): super().__init__() self.input_dim = int(input_dim) self.output_dim = int(output_dim) self.output_type = output_type self.n_classes = int(n_classes) dims: List[int] = [self.input_dim] + [int(x) for x in hidden_dims] layers: List[nn.Module] = [] if input_dropout and input_dropout > 0: layers.append(nn.Dropout(float(input_dropout))) for i in range(len(dims) - 1): layers.append(nn.Linear(dims[i], dims[i + 1])) layers.append(_activation(activation)) if dropout and dropout > 0: layers.append(nn.Dropout(float(dropout))) self.trunk = nn.Sequential(*layers) if layers else nn.Identity() final_dim = self.output_dim * self.n_classes if output_type == "distribution" else self.output_dim self.head = nn.Linear(dims[-1], final_dim) self.out_act = _output_activation(output_activation) if output_type == "regression" else nn.Identity() def forward(self, x: torch.Tensor) -> torch.Tensor: h = self.trunk(x) out = self.head(h) if self.output_type == "distribution": return out.view(-1, self.output_dim, self.n_classes) return self.out_act(out) @register_model("linear") class LinearModel(MLP): def __init__(self, *args, **kwargs): kwargs["hidden_dims"] = [] kwargs["dropout"] = 0.0 super().__init__(*args, **kwargs)