import torch
import torch.nn as nn


def get_activation(act_type=None):
    if act_type == 'relu':
        return nn.ReLU(inplace=True)
    elif act_type == 'lrelu':
        return nn.LeakyReLU(0.1, inplace=True)
    elif act_type == 'mish':
        return nn.Mish(inplace=True)
    elif act_type == 'silu':
        return nn.SiLU(inplace=True)
    elif act_type == 'gelu':
        return nn.GELU()
    elif act_type is None:
        return nn.Identity()
    else:
        raise NotImplementedError
        
def get_norm(norm_type, dim):
    if norm_type == 'BN':
        return nn.BatchNorm2d(dim)
    elif norm_type == 'GN':
        return nn.GroupNorm(num_groups=32, num_channels=dim)
    elif norm_type is None:
        return nn.Identity()
    else:
        raise NotImplementedError


# ----------------- MLP modules -----------------
class MLP(nn.Module):
    def __init__(self, in_dim, hidden_dim, out_dim, num_layers):
        super().__init__()
        self.num_layers = num_layers
        h = [hidden_dim] * (num_layers - 1)
        self.layers = nn.ModuleList(nn.Linear(n, k) for n, k in zip([in_dim] + h, h + [out_dim]))

    def forward(self, x):
        for i, layer in enumerate(self.layers):
            x = nn.functional.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
        return x

class FFN(nn.Module):
    def __init__(self, d_model=256, mlp_ratio=4.0, dropout=0., act_type='relu'):
        super().__init__()
        self.fpn_dim = round(d_model * mlp_ratio)
        self.linear1 = nn.Linear(d_model, self.fpn_dim)
        self.activation = get_activation(act_type)
        self.dropout2 = nn.Dropout(dropout)
        self.linear2 = nn.Linear(self.fpn_dim, d_model)
        self.dropout3 = nn.Dropout(dropout)
        self.norm = nn.LayerNorm(d_model)

    def forward(self, src):
        src2 = self.linear2(self.dropout2(self.activation(self.linear1(src))))
        src = src + self.dropout3(src2)
        src = self.norm(src)
        
        return src
    

# ----------------- Basic CNN Ops -----------------
class FrozenBatchNorm2d(torch.nn.Module):
    def __init__(self, n):
        super(FrozenBatchNorm2d, self).__init__()
        self.register_buffer("weight", torch.ones(n))
        self.register_buffer("bias", torch.zeros(n))
        self.register_buffer("running_mean", torch.zeros(n))
        self.register_buffer("running_var", torch.ones(n))

    def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict,
                              missing_keys, unexpected_keys, error_msgs):
        num_batches_tracked_key = prefix + 'num_batches_tracked'
        if num_batches_tracked_key in state_dict:
            del state_dict[num_batches_tracked_key]

        super(FrozenBatchNorm2d, self)._load_from_state_dict(
            state_dict, prefix, local_metadata, strict,
            missing_keys, unexpected_keys, error_msgs)

    def forward(self, x):
        # move reshapes to the beginning
        # to make it fuser-friendly
        w = self.weight.reshape(1, -1, 1, 1)
        b = self.bias.reshape(1, -1, 1, 1)
        rv = self.running_var.reshape(1, -1, 1, 1)
        rm = self.running_mean.reshape(1, -1, 1, 1)
        eps = 1e-5
        scale = w * (rv + eps).rsqrt()
        bias = b - rm * scale
        return x * scale + bias