# --------------------------------------------------------
# Adapted from  https://github.com/microsoft/unilm/tree/master/beit
# --------------------------------------------------------

import os
from functools import partial

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.checkpoint import checkpoint

try:
    from timm.models.layers import drop_path, to_2tuple
except:
    from timm.layers import drop_path, to_2tuple

try:
    import xformers.ops as xops
except ImportError:
    xops = None
    print("Please 'pip install xformers'")


class PatchDropout(nn.Module):
    """
    https://arxiv.org/abs/2212.00794
    """

    def __init__(self, prob, exclude_first_token=True):
        super().__init__()
        assert 0 <= prob < 1.
        self.prob = prob
        self.exclude_first_token = exclude_first_token  # exclude CLS token
        print(f"os.getenv('RoPE')={os.getenv('RoPE')}")

    def forward(self, x):
        if not self.training or self.prob == 0.:
            return x

        if self.exclude_first_token:
            cls_tokens, x = x[:, :1], x[:, 1:]
        else:
            cls_tokens = torch.jit.annotate(torch.Tensor, x[:, :1])

        batch = x.size()[0]
        num_tokens = x.size()[1]

        batch_indices = torch.arange(batch)
        batch_indices = batch_indices[..., None]

        keep_prob = 1 - self.prob
        num_patches_keep = max(1, int(num_tokens * keep_prob))

        rand = torch.randn(batch, num_tokens)
        patch_indices_keep = rand.topk(num_patches_keep, dim=-1).indices

        x = x[batch_indices, patch_indices_keep]

        if self.exclude_first_token:
            x = torch.cat((cls_tokens, x), dim=1)

        if self.training and os.getenv('RoPE') == '1':
            return x, patch_indices_keep

        return x

class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """
    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training)
    
    def extra_repr(self) -> str:
        return 'p={}'.format(self.drop_prob)


class Mlp(nn.Module):
    def __init__(
        self, 
        in_features, 
        hidden_features=None, 
        out_features=None, 
        act_layer=nn.GELU, 
        norm_layer=nn.LayerNorm, 
        drop=0.,
        subln=False,

        ):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()

        self.ffn_ln = norm_layer(hidden_features) if subln else nn.Identity()

        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        # x = self.drop(x)
        # commit this for the orignal BERT implement 
        x = self.ffn_ln(x)

        x = self.fc2(x)
        x = self.drop(x)
        return x

class SwiGLU(nn.Module):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.SiLU, drop=0., 
                norm_layer=nn.LayerNorm, subln=False):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features

        self.w1 = nn.Linear(in_features, hidden_features)
        self.w2 = nn.Linear(in_features, hidden_features)

        self.act = act_layer()
        self.ffn_ln = norm_layer(hidden_features) if subln else nn.Identity()
        self.w3 = nn.Linear(hidden_features, out_features)
        
        self.drop = nn.Dropout(drop)

    def forward(self, x):
        x1 = self.w1(x)
        x2 = self.w2(x)
        hidden = self.act(x1) * x2
        x = self.ffn_ln(hidden)
        x = self.w3(x)
        x = self.drop(x)
        return x

class Attention(nn.Module):
    def __init__(
            self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0.,
            proj_drop=0., window_size=None, attn_head_dim=None, xattn=False, rope=None, subln=False, norm_layer=nn.LayerNorm):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        if attn_head_dim is not None:
            head_dim = attn_head_dim
        all_head_dim = head_dim * self.num_heads
        self.scale = qk_scale or head_dim ** -0.5

        self.subln = subln
        if self.subln:
            self.q_proj = nn.Linear(dim, all_head_dim, bias=False)
            self.k_proj = nn.Linear(dim, all_head_dim, bias=False)
            self.v_proj = nn.Linear(dim, all_head_dim, bias=False)
        else:
            if qkv_bias:
                self.qkv = nn.Linear(dim, all_head_dim * 3, bias=True)
            else:
                self.qkv = nn.Linear(dim, all_head_dim * 3, bias=False)

        # if qkv_bias:
        #     self.q_bias = nn.Parameter(torch.zeros(all_head_dim))
        #     self.v_bias = nn.Parameter(torch.zeros(all_head_dim))
        # else:
        #     self.q_bias = None
        #     self.v_bias = None

        self.window_size = None
        self.relative_position_bias_table = None
        self.relative_position_index = None

        self.attn_drop = nn.Dropout(attn_drop)
        self.inner_attn_ln = norm_layer(all_head_dim) if subln else nn.Identity()
        # self.proj = nn.Linear(all_head_dim, all_head_dim)
        self.proj = nn.Linear(all_head_dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)
        self.xattn = xattn
        self.xattn_drop = attn_drop

        self.rope = rope

    def forward(self, x, rel_pos_bias=None, attn_mask=None):
        B, N, C = x.shape
        if self.subln: 
            q = F.linear(input=x, weight=self.q_proj.weight, bias=self.q_bias)
            k = F.linear(input=x, weight=self.k_proj.weight, bias=None)
            v = F.linear(input=x, weight=self.v_proj.weight, bias=self.v_bias)

            q = q.reshape(B, N, self.num_heads, -1).permute(0, 2, 1, 3)     # B, num_heads, N, C
            k = k.reshape(B, N, self.num_heads, -1).permute(0, 2, 1, 3)  
            v = v.reshape(B, N, self.num_heads, -1).permute(0, 2, 1, 3) 
        else: 

            # qkv_bias = None
            # if self.q_bias is not None:
            #     qkv_bias = torch.cat((self.q_bias, torch.zeros_like(self.v_bias, requires_grad=False), self.v_bias))
            
            # qkv = F.linear(input=x, weight=self.qkv.weight, bias=qkv_bias)

            qkv = self.qkv(x)

            qkv = qkv.reshape(B, N, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4)   # 3, B, num_heads, N, C
            q, k, v = qkv[0], qkv[1], qkv[2]

        if self.rope:
            q_t = q[:, :, 1:, :]
            ro_q_t = self.rope(q_t)
            q = torch.cat((q[:, :, :1, :], ro_q_t), -2).type_as(v)

            k_t = k[:, :, 1:, :]
            ro_k_t = self.rope(k_t)
            k = torch.cat((k[:, :, :1, :], ro_k_t), -2).type_as(v)

        if self.xattn:
            q = q.permute(0, 2, 1, 3)   # B, num_heads, N, C -> B, N, num_heads, C
            k = k.permute(0, 2, 1, 3)
            v = v.permute(0, 2, 1, 3)

            x = xops.memory_efficient_attention(
                q, k, v,
                p=self.xattn_drop,
                scale=self.scale,
                )
            x = x.reshape(B, N, -1)
            x = self.inner_attn_ln(x)
            x = self.proj(x)
            x = self.proj_drop(x)
        else:
            q = q * self.scale
            attn = (q @ k.transpose(-2, -1))

            if self.relative_position_bias_table is not None:
                relative_position_bias = \
                    self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
                        self.window_size[0] * self.window_size[1] + 1,
                        self.window_size[0] * self.window_size[1] + 1, -1)  # Wh*Ww,Wh*Ww,nH
                relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
                attn = attn + relative_position_bias.unsqueeze(0).type_as(attn)

            if rel_pos_bias is not None:
                attn = attn + rel_pos_bias.type_as(attn)

            if attn_mask is not None:
                attn_mask = attn_mask.bool()
                attn = attn.masked_fill(~attn_mask[:, None, None, :], float("-inf"))
            
            attn = attn.softmax(dim=-1)
            attn = self.attn_drop(attn)

            x = (attn @ v).transpose(1, 2).reshape(B, N, -1)
            x = self.inner_attn_ln(x)
            x = self.proj(x)
            x = self.proj_drop(x)
        return x


class Block(nn.Module):

    def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., init_values=None, act_layer=nn.GELU, norm_layer=nn.LayerNorm,
                 window_size=None, attn_head_dim=None, xattn=False, rope=None, postnorm=False,
                 subln=False, naiveswiglu=False):
        super().__init__()
        self.norm1 = norm_layer(dim)
        self.attn = Attention(
            dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
            attn_drop=attn_drop, proj_drop=drop, window_size=window_size, attn_head_dim=attn_head_dim,
            xattn=xattn, rope=rope, subln=subln, norm_layer=norm_layer)
        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)

        if naiveswiglu:
            self.mlp = SwiGLU(
                in_features=dim, 
                hidden_features=mlp_hidden_dim, 
                subln=subln,
                norm_layer=norm_layer,
            )
        else:
            self.mlp = Mlp(
                in_features=dim, 
                hidden_features=mlp_hidden_dim, 
                act_layer=act_layer,
                subln=subln,
                drop=drop
            )

        if init_values is not None and init_values > 0:
            self.gamma_1 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)
            self.gamma_2 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)
        else:
            self.gamma_1, self.gamma_2 = None, None

        self.postnorm = postnorm

    def forward(self, x, rel_pos_bias=None, attn_mask=None):
        if self.gamma_1 is None:
            if self.postnorm:
                x = x + self.drop_path(self.norm1(self.attn(x, rel_pos_bias=rel_pos_bias, attn_mask=attn_mask)))
                x = x + self.drop_path(self.norm2(self.mlp(x)))
            else:
                x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias, attn_mask=attn_mask))
                x = x + self.drop_path(self.mlp(self.norm2(x)))
        else:
            if self.postnorm:
                x = x + self.drop_path(self.gamma_1 * self.norm1(self.attn(x, rel_pos_bias=rel_pos_bias, attn_mask=attn_mask)))
                x = x + self.drop_path(self.gamma_2 * self.norm2(self.mlp(x)))
            else:
                x = x + self.drop_path(self.gamma_1 * self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias, attn_mask=attn_mask))
                x = x + self.drop_path(self.gamma_2 * self.mlp(self.norm2(x)))
        return x


class PatchEmbed(nn.Module):
    """ Image to Patch Embedding
    """
    def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768):
        super().__init__()
        img_size = to_2tuple(img_size)
        patch_size = to_2tuple(patch_size)
        num_patches = (img_size[1] // patch_size[1]) * (img_size[0] // patch_size[0])
        self.patch_shape = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
        self.img_size = img_size
        self.patch_size = patch_size
        self.num_patches = num_patches

        self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)

    def forward(self, x, **kwargs):
        B, C, H, W = x.shape
        # FIXME look at relaxing size constraints
        assert H == self.img_size[0] and W == self.img_size[1], \
            f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
        x = self.proj(x).flatten(2).transpose(1, 2)
        return x


class EVAVisionTransformer(nn.Module):
    """ Vision Transformer with support for patch or hybrid CNN input stage
    """
    def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12,
                 num_heads=12, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop_rate=0., attn_drop_rate=0.,
                 drop_path_rate=0., norm_layer=nn.LayerNorm, init_values=None, patch_dropout=0.,
                 use_abs_pos_emb=True, use_rel_pos_bias=False, use_shared_rel_pos_bias=False, rope=False,
                 use_mean_pooling=True, init_scale=0.001, grad_checkpointing=False, xattn=False, postnorm=False,
                 pt_hw_seq_len=16, intp_freq=False, naiveswiglu=False, subln=False,
                 ):
        super().__init__()
        self.image_size = img_size
        # self.num_classes = num_classes
        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models

        self.patch_embed = PatchEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim)
        num_patches = self.patch_embed.num_patches

        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
        if use_abs_pos_emb:
            self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
        else:
            self.pos_embed = None
        self.pos_drop = nn.Dropout(p=drop_rate)

        self.rel_pos_bias = None
        self.rope = None

        self.naiveswiglu = naiveswiglu

        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]  # stochastic depth decay rule
        self.use_rel_pos_bias = use_rel_pos_bias
        self.blocks = nn.ModuleList([
            Block(
                dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
                drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[i], norm_layer=norm_layer,
                init_values=init_values, window_size=self.patch_embed.patch_shape if use_rel_pos_bias else None,
                xattn=xattn, rope=self.rope, postnorm=postnorm, subln=subln, naiveswiglu=naiveswiglu)
            for i in range(depth)])

        # setting a patch_dropout of 0. would mean it is disabled and this function would be the identity fn
        self.patch_dropout = PatchDropout(patch_dropout) if patch_dropout > 0. else nn.Identity()

        self.grad_checkpointing = grad_checkpointing


    def get_num_layers(self):
        return len(self.blocks)
    
    def lock(self, unlocked_groups=0, freeze_bn_stats=False):
        assert unlocked_groups == 0, 'partial locking not currently supported for this model'
        for param in self.parameters():
            param.requires_grad = False

    @torch.jit.ignore
    def set_grad_checkpointing(self, enable=True):
        self.grad_checkpointing = enable

    @torch.jit.ignore
    def no_weight_decay(self):
        return {'pos_embed', 'cls_token'}


    def forward_features(self, x):
        x = self.patch_embed(x)
        batch_size, seq_len, _ = x.size()

        cls_tokens = self.cls_token.expand(batch_size, -1, -1)  # stole cls_tokens impl from Phil Wang, thanks
        x = torch.cat((cls_tokens, x), dim=1)
        if self.pos_embed is not None:
            x = x + self.pos_embed
        x = self.pos_drop(x)

        # a patch_dropout of 0. would mean it is disabled and this function would do nothing but return what was passed in
        if os.getenv('RoPE') == '1':
            if self.training and not isinstance(self.patch_dropout, nn.Identity):
                x, patch_indices_keep = self.patch_dropout(x)
                self.rope.forward = partial(self.rope.forward, patch_indices_keep=patch_indices_keep)
            else:
                self.rope.forward = partial(self.rope.forward, patch_indices_keep=None)
                x = self.patch_dropout(x)
        else:
            x = self.patch_dropout(x)

        rel_pos_bias = None

        for blk in self.blocks:
            if self.grad_checkpointing:
                x = checkpoint(blk, x, (rel_pos_bias,))
            else:
                x = blk(x, rel_pos_bias=rel_pos_bias)

        return x

    def forward(self, x):

        """
        :return:
            forward_features function returns raw features of ViT,
            forward with return_all_features returns normalized features of ViT
        :param x:
        :param return_all_features:
        """

        features = self.forward_features(x)  # [B, n_patch, C]

        return features