Source code for cosense3d.modules.utils.init

from torch import nn
import numpy as np


def bias_init_with_prob(prior_prob: float) -> float:
    """initialize conv/fc bias value according to a given probability value."""
    bias_init = float(-np.log((1 - prior_prob) / prior_prob))
    return bias_init


def constant_init(module: nn.Module, val: float, bias: float = 0) -> None:
    if hasattr(module, 'weight') and module.weight is not None:
        nn.init.constant_(module.weight, val)
    if hasattr(module, 'bias') and module.bias is not None:
        nn.init.constant_(module.bias, bias)


def xavier_init(module: nn.Module,
                gain: float = 1,
                bias: float = 0,
                distribution: str = 'normal') -> None:
    assert distribution in ['uniform', 'normal']
    if hasattr(module, 'weight') and module.weight is not None:
        if distribution == 'uniform':
            nn.init.xavier_uniform_(module.weight, gain=gain)
        else:
            nn.init.xavier_normal_(module.weight, gain=gain)
    if hasattr(module, 'bias') and module.bias is not None:
        nn.init.constant_(module.bias, bias)


def normal_init(module: nn.Module,
                mean: float = 0,
                std: float = 1,
                bias: float = 0) -> None:
    if hasattr(module, 'weight') and module.weight is not None:
        nn.init.normal_(module.weight, mean, std)
    if hasattr(module, 'bias') and module.bias is not None:
        nn.init.constant_(module.bias, bias)


def trunc_normal_init(module: nn.Module,
                      mean: float = 0,
                      std: float = 1,
                      a: float = -2,
                      b: float = 2,
                      bias: float = 0) -> None:
    if hasattr(module, 'weight') and module.weight is not None:
        trunc_normal_(module.weight, mean, std, a, b)  # type: ignore
    if hasattr(module, 'bias') and module.bias is not None:
        nn.init.constant_(module.bias, bias)  # type: ignore


def uniform_init(module: nn.Module,
                 a: float = 0,
                 b: float = 1,
                 bias: float = 0) -> None:
    if hasattr(module, 'weight') and module.weight is not None:
        nn.init.uniform_(module.weight, a, b)
    if hasattr(module, 'bias') and module.bias is not None:
        nn.init.constant_(module.bias, bias)


def kaiming_init(module: nn.Module,
                 a: float = 0,
                 mode: str = 'fan_out',
                 nonlinearity: str = 'relu',
                 bias: float = 0,
                 distribution: str = 'normal') -> None:
    assert distribution in ['uniform', 'normal']
    if hasattr(module, 'weight') and module.weight is not None:
        if distribution == 'uniform':
            nn.init.kaiming_uniform_(
                module.weight, a=a, mode=mode, nonlinearity=nonlinearity)
        else:
            nn.init.kaiming_normal_(
                module.weight, a=a, mode=mode, nonlinearity=nonlinearity)
    if hasattr(module, 'bias') and module.bias is not None:
        nn.init.constant_(module.bias, bias)