# most of the codes are borrowed from Query2label and DETR
import torch
import torch.nn.functional as F
from torch import nn, Tensor
from torch.nn import MultiheadAttention
from typing import Optional
import copy
def _get_activation_fn(activation):
    if activation == "relu":
        return F.relu
    if activation == "gelu":
        return F.gelu
    if activation == "glu":
        return F.glu
    raise RuntimeError(F"activation should be relu/gelu, not {activation}.")
class TransformerEncoderLayer(nn.Module):
    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1,
                 activation="relu"):
        super().__init__()
        self.self_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)
        self.activation = _get_activation_fn(activation)
    def with_pos_embed(self, tensor, pos: Optional[Tensor]):
        return tensor if pos is None else tensor + pos
    def forward(self, src,
                    src_mask: Optional[Tensor] = None,
                    src_key_padding_mask: Optional[Tensor] = None,
                    pos: Optional[Tensor] = None):
        src2 = self.norm1(src)
        q = k = self.with_pos_embed(src2, pos)
        src2 = self.self_attn(q, k, value=src2, attn_mask=src_mask,
                              key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src2 = self.norm2(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src2))))
        src = src + self.dropout2(src2)
        return src


def _get_clones(module, N):
    return nn.ModuleList([copy.deepcopy(module) for i in range(N)])
class TransformerEncoder(nn.Module):
    def __init__(self, encoder_layer, num_layers, norm=None):
        super().__init__()
        self.layers = _get_clones(encoder_layer, num_layers)
        self.num_layers = num_layers
        self.norm = norm
    def forward(self, src,
                mask: Optional[Tensor] = None,
                src_key_padding_mask: Optional[Tensor] = None,
                pos: Optional[Tensor] = None):
        output = src
        for layer in self.layers:
            output = layer(output, src_mask=mask,
                           src_key_padding_mask=src_key_padding_mask, pos=pos)
        if self.norm is not None:
            output = self.norm(output)
        return output


class Transformer(nn.Module):
    def __init__(self, d_model=512, nhead=8, num_encoder_layers=6,
                 num_decoder_layers=6, dim_feedforward=2048, dropout=0.1,
                 activation="relu"
                 ):
        super().__init__()
        self.num_encoder_layers = num_encoder_layers
        if num_decoder_layers > 0:
            encoder_layer = TransformerEncoderLayer(d_model, nhead, dim_feedforward,
                                                    dropout, activation)
            encoder_norm = nn.LayerNorm(d_model)
            self.encoder = TransformerEncoder(encoder_layer, num_encoder_layers, encoder_norm)

        self._reset_parameters()
        self.d_model = d_model
        self.nhead = nhead

    def _reset_parameters(self):
        for p in self.parameters():
            if p.dim() > 1:
                nn.init.xavier_uniform_(p)

    def forward(self, src, pos_embed=None, mask=None):
        src = src.permute(2, 0, 1)
        if mask is not None:
            mask = mask.flatten(1)
        memory = self.encoder(src, src_key_padding_mask=mask, pos=pos_embed)
        return memory.transpose(0,1)