# Copyright (c) Meta Platforms, Inc. and affiliates.
#
# This source code is licensed under the Apache License, Version 2.0
# found in the LICENSE file in the root directory of this source tree.

# References:
#   https://github.com/facebookresearch/dino/blob/master/vision_transformer.py
#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/patch_embed.py

from typing import Callable, List

import torch
from torch import nn, Tensor

from .attention import Attention, MemEffAttention
from .drop_path import DropPath
from .layer_scale import LayerScale
from .mlp import Mlp


class Block(nn.Module):
    def __init__(
        self,
        dim: int,
        num_heads: int,
        mlp_ratio: float = 4.0,
        qkv_bias: bool = False,
        proj_bias: bool = True,
        ffn_bias: bool = True,
        drop: float = 0.0,
        attn_drop: float = 0.0,
        init_values=None,
        drop_path: float = 0.0,
        act_layer: Callable[..., nn.Module] = nn.GELU,
        norm_layer: Callable[..., nn.Module] = nn.LayerNorm,
        attn_class: Callable[..., nn.Module] = MemEffAttention,
        ffn_layer: Callable[..., nn.Module] = Mlp,
        no_attn: bool = False
    ) -> None:
        super().__init__()
        self.norm1 = norm_layer(dim)
        if no_attn:
            self.attn = nn.Identity()
        else:
            self.attn = attn_class(
                dim,
                num_heads=num_heads,
                qkv_bias=qkv_bias,
                proj_bias=proj_bias,
                attn_drop=attn_drop,
                proj_drop=drop,
            )
        self.ls1 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
        self.drop_path1 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()

        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = ffn_layer(
            in_features=dim,
            hidden_features=mlp_hidden_dim,
            act_layer=act_layer,
            drop=drop,
            bias=ffn_bias,
        )
        self.ls2 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
        self.drop_path2 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()

        self.sample_drop_ratio = drop_path

    def forward(self, x: Tensor, y: Tensor | None = None) -> Tensor:
        def attn_residual_func(x: Tensor) -> Tensor:
            return self.ls1(self.attn(self.norm1(x), y=y))

        def ffn_residual_func(x: Tensor) -> Tensor:
            return self.ls2(self.mlp(self.norm2(x)))

        if self.training and self.sample_drop_ratio > 0.1:
            x = drop_add_residual_stochastic_depth(
                x,
                residual_func=attn_residual_func,
                sample_drop_ratio=self.sample_drop_ratio,
            )
            x = drop_add_residual_stochastic_depth(
                x,
                residual_func=ffn_residual_func,
                sample_drop_ratio=self.sample_drop_ratio,
            )
        elif self.training and self.sample_drop_ratio > 0.0:
            x = x + self.drop_path1(attn_residual_func(x))
            x = x + self.drop_path2(ffn_residual_func(x))
        else:
            x = x + attn_residual_func(x)
            x = x + ffn_residual_func(x)
        return x


def drop_add_residual_stochastic_depth(
    x: Tensor,
    residual_func: Callable[[Tensor], Tensor],
    sample_drop_ratio: float = 0.0,
) -> Tensor:
    b, n, d = x.shape
    sample_subset_size = max(int(b * (1 - sample_drop_ratio)), 1)
    brange = (torch.randperm(b, device=x.device))[:sample_subset_size]
    x_subset = x[brange]

    residual = residual_func(x_subset)

    x_flat = x.flatten(1)
    residual = residual.flatten(1)

    residual_scale_factor = b / sample_subset_size

    x_plus_residual = torch.index_add(x_flat, 0, brange, residual.to(dtype=x.dtype), alpha=residual_scale_factor)
    return x_plus_residual.view_as(x)


class NestedTensorBlock(Block):
    def forward_nested(self, x_list: List[Tensor]) -> List[Tensor]:
        raise NotImplementedError("Nested tensor support requires xformers, which has been removed")

    def forward(self, x_or_x_list):
        if isinstance(x_or_x_list, Tensor):
            return super().forward(x_or_x_list)
        elif isinstance(x_or_x_list, list):
            raise NotImplementedError("Nested tensor support requires xformers, which has been removed")
        else:
            raise AssertionError