# FROM LSTR
import math
import torch.nn as nn

def weights_init(m):
    if isinstance(m, nn.Linear):
        nn.init.kaiming_uniform_(m.weight.data, a=math.sqrt(5))
    elif isinstance(m, nn.Conv1d):
        nn.init.normal_(m.weight.data)
        if m.bias is not None:
            nn.init.normal_(m.bias.data)
    elif isinstance(m, nn.Conv2d):
        nn.init.xavier_normal_(m.weight.data)
        if m.bias is not None:
            nn.init.normal_(m.bias.data)
    elif isinstance(m, nn.ConvTranspose1d):
        nn.init.normal_(m.weight.data)
        if m.bias is not None:
            nn.init.normal_(m.bias.data)
    elif isinstance(m, nn.ConvTranspose2d):
        nn.init.xavier_normal_(m.weight.data)
        if m.bias is not None:
            nn.init.normal_(m.bias.data)
    elif isinstance(m, nn.BatchNorm1d):
        nn.init.normal_(m.weight.data, mean=1, std=0.02)
        nn.init.constant_(m.bias.data, 0)
    elif isinstance(m, nn.BatchNorm2d):
        nn.init.normal_(m.weight.data, mean=1, std=0.02)
        nn.init.constant_(m.bias.data, 0)
    elif isinstance(m, nn.GRUCell):
        for param in m.parameters():
            if len(param.shape) >= 2:
                nn.init.orthogonal_(param.data)
            else:
                nn.init.normal_(param.data)