import torch


def init_weights(m, mean=0.0, std=0.01):
    classname = m.__class__.__name__
    if classname.find("Conv") != -1:
        m.weight.data.normal_(mean, std)


def get_padding(kernel_size, dilation=1):
    return int((kernel_size * dilation - dilation) / 2)


def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
    n_channels_int = n_channels[0]
    in_act = input_a + input_b
    t_act = torch.tanh(in_act[:, :n_channels_int, :])
    s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
    acts = t_act * s_act
    return acts


def sequence_mask(length, max_length=None):
    if max_length is None:
        max_length = length.max()
    x = torch.arange(max_length, dtype=length.dtype, device=length.device)
    return x.unsqueeze(0) < length.unsqueeze(1)