import math
from functools import partial
import numpy as np

import torch
import torch.nn as nn

import warnings

def _no_grad_trunc_normal_(tensor, mean, std, a, b):
    def norm_cdf(x):
        return (1. + math.erf(x / math.sqrt(2.))) / 2.

    if (mean < a - 2 * std) or (mean > b + 2 * std):
        warnings.warn("mean is more than 2 std from [a, b] in nn.init.trunc_normal_. "
                      "The distribution of values may be incorrect.",
                      stacklevel=2)

    with torch.no_grad():
        l = norm_cdf((a - mean) / std)
        u = norm_cdf((b - mean) / std)

        tensor.uniform_(2 * l - 1, 2 * u - 1)

        tensor.erfinv_()

        tensor.mul_(std * math.sqrt(2.))
        tensor.add_(mean)

        tensor.clamp_(min=a, max=b)
        return tensor


def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.):
    return _no_grad_trunc_normal_(tensor, mean, std, a, b)



def drop_path(x, drop_prob: float = 0., training: bool = False):
    if drop_prob == 0. or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output


class DropPath(nn.Module):
    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)


class Mlp(nn.Module):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
        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.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)
        x = self.fc2(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.):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** -0.5

        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)
        self.requires_attn = True

    def forward(self, x):
        B, N, C = x.shape
        qkv = self.qkv(x) # B, N, 3, self.num_heads x C // self.num_heads
        if self.requires_attn:
            qkv = qkv.reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
            q, k, v = qkv[0], qkv[1], qkv[2] # 1, B, self.num_heads, N, C // self.num_heads
            attn = (q @ k.transpose(-2, -1)) * self.scale
            attn = attn.softmax(dim=-1)
            attn = self.attn_drop(attn)

            x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        else:
            qkv = qkv.reshape(B, N, 3,C)
            x = qkv[:,:,2]
            attn = None
        x = self.proj(x)
        x = self.proj_drop(x)
        return x, attn


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., act_layer=nn.GELU, norm_layer=nn.LayerNorm):
        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)
        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)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)

    def forward(self, x, return_attention=False):
        y, attn = self.attn(self.norm1(x))
        if return_attention:
            return attn
        x = x + self.drop_path(y)
        x = x + self.drop_path(self.mlp(self.norm2(x)))
        return x


class PatchEmbed(nn.Module):
    def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768):
        super().__init__()
        num_patches = (img_size // patch_size) * (img_size // patch_size)
        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):
        B, C, H, W = x.shape
        x = self.proj(x).flatten(2).transpose(1, 2)
        return x


class VisionTransformer(nn.Module):
    def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=0, 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, head_type=2, **kwargs):
        super().__init__()
        self.num_features = self.embed_dim = embed_dim
        self.head_type = head_type
        if isinstance(img_size,list): img_size=img_size[0]
        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))
        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
        self.pos_drop = nn.Dropout(p=drop_rate)

        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]
        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)
            for i in range(depth)])
        self.norm = norm_layer(embed_dim)

        # Classifier head
        if self.head_type==2:
            self.head = nn.Linear(2*embed_dim, num_classes) if num_classes > 0 else nn.Identity()
        else:
            self.head = nn.Linear(embed_dim, num_classes) if num_classes > 0 else nn.Identity()


        trunc_normal_(self.pos_embed, std=.02)
        trunc_normal_(self.cls_token, std=.02)
        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    def interpolate_pos_encoding(self, x, w, h):
        npatch = x.shape[1] - 1
        N = self.pos_embed.shape[1] - 1
        if npatch == N and w == h:
            return self.pos_embed
        class_pos_embed = self.pos_embed[:, 0]
        patch_pos_embed = self.pos_embed[:, 1:]
        dim = x.shape[-1]
        w0 = w // self.patch_embed.patch_size
        h0 = h // self.patch_embed.patch_size
        w0, h0 = w0 + 0.1, h0 + 0.1
        patch_pos_embed = nn.functional.interpolate(
            patch_pos_embed.reshape(1, int(math.sqrt(N)), int(math.sqrt(N)), dim).permute(0, 3, 1, 2),
            scale_factor=(w0 / math.sqrt(N), h0 / math.sqrt(N)),
            mode='bicubic',
        )
        assert int(w0) == patch_pos_embed.shape[-2] and int(h0) == patch_pos_embed.shape[-1]
        patch_pos_embed = patch_pos_embed.permute(0, 2, 3, 1).view(1, -1, dim)
        return torch.cat((class_pos_embed.unsqueeze(0), patch_pos_embed), dim=1)


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

    @torch.jit.ignore
    def group_matcher(self, coarse=False):
        return dict(
            stem=r'^cls_token|pos_embed|patch_embed',  # stem and embed
            blocks=[(r'^blocks\.(\d+)', None), (r'^norm', (99999,))]
        )

    
    def prepare_tokens(self, x):
        B, nc, w, h = x.shape
        x = self.patch_embed(x)

        cls_tokens = self.cls_token.expand(B, -1, -1)
        x = torch.cat((cls_tokens, x), dim=1)

        x = x + self.interpolate_pos_encoding(x, w, h)

        return self.pos_drop(x)
    
    def forward_features(self, x):
        x = self.prepare_tokens(x)
        for blk in self.blocks:
            x = blk(x)
            
        x = self.norm(x)
        return x
        
    def forward(self, x):
        x = self.forward_features(x)
        if self.head_type==0:
            return self.head(x[:, 0])          
        elif self.head_type==1:
            return self.head(x[:, 1:].mean(1))
        elif self.head_type==2:
            return self.head( torch.cat( (x[:, 0], torch.mean(x[:, 1:], dim=1)), dim=1 ))
      
    def get_intermediate_layers(self, x, n=1):
        x = self.prepare_tokens(x)
        # we return the output tokens from the `n` last blocks
        output = []
        for i, blk in enumerate(self.blocks):
            x = blk(x)
            if len(self.blocks) - i <= n:
                output.append(self.norm(x))
        return output

def vit_tiny(patch_size=16, **kwargs):
    model = VisionTransformer(
        patch_size=patch_size, embed_dim=192, depth=12, num_heads=3, mlp_ratio=4,
        qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), **kwargs)
    return model


def vit_small(patch_size=16, **kwargs):
    model = VisionTransformer(
        patch_size=patch_size, embed_dim=384, depth=12, num_heads=6, mlp_ratio=4,
        qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), **kwargs)
    return model


def vit_base(patch_size=16, **kwargs):
    model = VisionTransformer(
        patch_size=patch_size, embed_dim=768, depth=12, num_heads=12, mlp_ratio=4,
        qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), **kwargs)
    return model


def vit_large(patch_size=16, **kwargs):
    model = VisionTransformer(
        patch_size=patch_size, embed_dim=1024, depth=24, num_heads=16, mlp_ratio=4,
        qkv_bias=True, **kwargs)
    return model