# Based on EVA, BEIT, timm and DeiT code bases
# https://github.com/baaivision/EVA
# https://github.com/rwightman/pytorch-image-models/tree/master/timm
# https://github.com/microsoft/unilm/tree/master/beit
# https://github.com/facebookresearch/deit/
# https://github.com/facebookresearch/dino
# --------------------------------------------------------'
import os
import math
import logging
from functools import partial
from collections import OrderedDict

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
from timm.models.layers import drop_path, to_2tuple, trunc_normal_
from timm.models.registry import register_model

from utils.misc import download_cached_file


def _cfg(url='', **kwargs):
    return {
        'url': url,
        'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None,
        'crop_pct': .9, 'interpolation': 'bicubic',
        'mean': (0.5, 0.5, 0.5), 'std': (0.5, 0.5, 0.5),
        **kwargs
    }


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):
        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, 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)
        # commit this for the orignal BERT implement 
        x = self.fc2(x)
        x = self.drop(x)
        return x


class Local_MHRA(nn.Module):
    def __init__(self, d_model, dw_reduction=1.5, pos_kernel_size=3):
        super().__init__() 

        padding = pos_kernel_size // 2
        re_d_model = int(d_model // dw_reduction)
        self.pos_embed = nn.Sequential(
            nn.BatchNorm3d(d_model),
            nn.Conv3d(d_model, re_d_model, kernel_size=1, stride=1, padding=0),
            nn.Conv3d(re_d_model, re_d_model, kernel_size=(pos_kernel_size, 1, 1), stride=(1, 1, 1), padding=(padding, 0, 0), groups=re_d_model),
            nn.Conv3d(re_d_model, d_model, kernel_size=1, stride=1, padding=0),
        )

        # init zero
        # print('Init zero for Conv in pos_emb')
        nn.init.constant_(self.pos_embed[3].weight, 0)
        nn.init.constant_(self.pos_embed[3].bias, 0)

    def forward(self, x):
        out = self.pos_embed(x)
        return out


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):
        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.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

        if window_size:
            self.window_size = window_size
            self.num_relative_distance = (2 * window_size[0] - 1) * (2 * window_size[1] - 1) + 3
            self.relative_position_bias_table = nn.Parameter(
                torch.zeros(self.num_relative_distance, num_heads))  # 2*Wh-1 * 2*Ww-1, nH
            # cls to token & token 2 cls & cls to cls

            # get pair-wise relative position index for each token inside the window
            coords_h = torch.arange(window_size[0])
            coords_w = torch.arange(window_size[1])
            coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
            coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
            relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
            relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
            relative_coords[:, :, 0] += window_size[0] - 1  # shift to start from 0
            relative_coords[:, :, 1] += window_size[1] - 1
            relative_coords[:, :, 0] *= 2 * window_size[1] - 1
            relative_position_index = \
                torch.zeros(size=(window_size[0] * window_size[1] + 1, ) * 2, dtype=relative_coords.dtype)
            relative_position_index[1:, 1:] = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
            relative_position_index[0, 0:] = self.num_relative_distance - 3
            relative_position_index[0:, 0] = self.num_relative_distance - 2
            relative_position_index[0, 0] = self.num_relative_distance - 1

            self.register_buffer("relative_position_index", relative_position_index)
        else:
            self.window_size = None
            self.relative_position_bias_table = None
            self.relative_position_index = None

        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(all_head_dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

    def forward(self, x, rel_pos_bias=None):
        B, N, C = x.shape
        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 = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        qkv = F.linear(input=x, weight=self.qkv.weight, bias=qkv_bias)
        qkv = qkv.reshape(B, N, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4)
        q, k, v = qkv[0], qkv[1], qkv[2]   # make torchscript happy (cannot use tensor as tuple)

        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)

        if rel_pos_bias is not None:
            attn = attn + rel_pos_bias
        
        attn = attn.softmax(dim=-1)
        attn = self.attn_drop(attn)

        x = (attn @ v).transpose(1, 2).reshape(B, N, -1)
        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,
                 no_lmhra=False, double_lmhra=True, lmhra_reduction=2.0, 
                 ):
        super().__init__()
        self.no_lmhra = no_lmhra
        self.double_lmhra = double_lmhra
        if not no_lmhra:
            self.lmhra1 = Local_MHRA(dim, dw_reduction=lmhra_reduction)
            if double_lmhra:
                self.lmhra2 = Local_MHRA(dim, dw_reduction=lmhra_reduction)

        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)
        # 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)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, 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

    def forward(self, x, rel_pos_bias=None, T=8):
        # Local MHRA
        if not self.no_lmhra:
            # x: BT, HW+1, C
            tmp_x = x[:, 1:, :]
            BT, N, C = tmp_x.shape
            B = BT // T
            H = W = int(N ** 0.5)
            tmp_x = tmp_x.view(B, T, H, W, C).permute(0, 4, 1, 2, 3).contiguous()
            tmp_x = tmp_x + self.drop_path(self.lmhra1(tmp_x))
            tmp_x = tmp_x.view(B, C, T, N).permute(0, 2, 3, 1).contiguous().view(BT, N, C)
            x = torch.cat([x[:, :1, :], tmp_x], dim=1)

        # MHSA
        if self.gamma_1 is None:
            x = x + self.drop_path(self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias))
        else:
            x = x + self.drop_path(self.gamma_1 * self.attn(self.norm1(x), rel_pos_bias=rel_pos_bias))

        # Local MHRA
        if not self.no_lmhra and self.double_lmhra:
            tmp_x = x[:, 1:, :]
            tmp_x = tmp_x.view(B, T, H, W, C).permute(0, 4, 1, 2, 3).contiguous()
            tmp_x = tmp_x + self.drop_path(self.lmhra2(tmp_x))
            tmp_x = tmp_x.view(B, C, T, N).permute(0, 2, 3, 1).contiguous().view(BT, N, C)
            x = torch.cat([x[:, :1, :], tmp_x], dim=1)

        # MLP
        if self.gamma_1 is None:
            x = x + self.drop_path(self.mlp(self.norm2(x)))
        else:
            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, temporal_downsample=False):
        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
        if temporal_downsample:
            self.proj = nn.Conv3d(
                in_chans, embed_dim, kernel_size=(3, patch_size[0], patch_size[1]), 
                stride=(2, patch_size[0], patch_size[1]), padding=(1, 0, 0)
            )
        else:
            self.proj = nn.Conv3d(
                in_chans, embed_dim, kernel_size=(1, patch_size[0], patch_size[1]), 
                stride=(1, patch_size[0], patch_size[1]), padding=(0, 0, 0)
            )

    def forward(self, x, **kwargs):
        B, C, T, 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)
        return x


class RelativePositionBias(nn.Module):
    def __init__(self, window_size, num_heads):
        super().__init__()
        self.window_size = window_size
        self.num_relative_distance = (2 * window_size[0] - 1) * (2 * window_size[1] - 1) + 3
        self.relative_position_bias_table = nn.Parameter(
            torch.zeros(self.num_relative_distance, num_heads))  # 2*Wh-1 * 2*Ww-1, nH
        # cls to token & token 2 cls & cls to cls

        # get pair-wise relative position index for each token inside the window
        coords_h = torch.arange(window_size[0])
        coords_w = torch.arange(window_size[1])
        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
        relative_coords[:, :, 0] += window_size[0] - 1  # shift to start from 0
        relative_coords[:, :, 1] += window_size[1] - 1
        relative_coords[:, :, 0] *= 2 * window_size[1] - 1
        relative_position_index = \
            torch.zeros(size=(window_size[0] * window_size[1] + 1,) * 2, dtype=relative_coords.dtype)
        relative_position_index[1:, 1:] = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
        relative_position_index[0, 0:] = self.num_relative_distance - 3
        relative_position_index[0:, 0] = self.num_relative_distance - 2
        relative_position_index[0, 0] = self.num_relative_distance - 1

        self.register_buffer("relative_position_index", relative_position_index)

        # trunc_normal_(self.relative_position_bias_table, std=.02)

    def forward(self):
        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
        return relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww


class Global_MHRA(nn.Module):
    def __init__(
            self, d_model, n_head, attn_mask=None,
            mlp_factor=4.0, drop_path=0., dropout=0.,
        ):
        super().__init__()
        print(f'Drop path rate: {drop_path}')
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()

        self.dpe = nn.Conv3d(d_model, d_model, kernel_size=3, stride=1, padding=1, bias=True, groups=d_model)
        nn.init.constant_(self.dpe.bias, 0.)

        self.attn = nn.MultiheadAttention(d_model, n_head)
        self.ln_1 = nn.LayerNorm(d_model)
        d_mlp = round(mlp_factor * d_model)
        self.mlp = nn.Sequential(OrderedDict([
            ("c_fc", nn.Linear(d_model, d_mlp)),
            ("gelu", nn.GELU()),
            ("dropout", nn.Dropout(dropout)),
            ("c_proj", nn.Linear(d_mlp, d_model))
        ]))
        self.ln_2 = nn.LayerNorm(d_model)
        self.ln_3 = nn.LayerNorm(d_model)
        self.attn_mask = attn_mask

        # zero init
        nn.init.xavier_uniform_(self.attn.in_proj_weight)
        nn.init.constant_(self.attn.out_proj.weight, 0.)
        nn.init.constant_(self.attn.out_proj.bias, 0.)
        nn.init.xavier_uniform_(self.mlp[0].weight)
        nn.init.constant_(self.mlp[-1].weight, 0.)
        nn.init.constant_(self.mlp[-1].bias, 0.)

    def attention(self, x, y, T):
        # x: 1, B, C
        # y: BT, HW+1, C
        BT, N, C = y.shape
        B = BT // T
        H = W = int(N ** 0.5)
        y = y.view(B, T, N, C)
        _, tmp_feats = y[:, :, :1], y[:, :, 1:]
        tmp_feats = tmp_feats.view(B, T, H, W, C).permute(0, 4, 1, 2, 3).contiguous()
        tmp_feats = self.dpe(tmp_feats.clone()).view(B, C, T, N - 1).permute(0, 2, 3, 1).contiguous()
        y[:, :, 1:] = y[:, :, 1:] + tmp_feats
        y = y.permute(1, 2, 0, 3).flatten(0, 1) # T(HW+1), B, C

        d_model = self.ln_1.weight.size(0)
        q = (x @ self.attn.in_proj_weight[:d_model].T) + self.attn.in_proj_bias[:d_model]

        k = (y @ self.attn.in_proj_weight[d_model:-d_model].T) + self.attn.in_proj_bias[d_model:-d_model]
        v = (y @ self.attn.in_proj_weight[-d_model:].T) + self.attn.in_proj_bias[-d_model:]
        Tx, Ty, N = q.size(0), k.size(0), q.size(1)
        q = q.view(Tx, N, self.attn.num_heads, self.attn.head_dim).permute(1, 2, 0, 3)
        k = k.view(Ty, N, self.attn.num_heads, self.attn.head_dim).permute(1, 2, 0, 3)
        v = v.view(Ty, N, self.attn.num_heads, self.attn.head_dim).permute(1, 2, 0, 3)
        aff = (q @ k.transpose(-2, -1) / (self.attn.head_dim ** 0.5))

        aff = aff.softmax(dim=-1)
        out = aff @ v
        out = out.permute(2, 0, 1, 3).flatten(2)
        out = self.attn.out_proj(out)
        return out

    def forward(self, x, y, T):
        x = x + self.drop_path(self.attention(self.ln_1(x), self.ln_3(y), T=T))
        x = x + self.drop_path(self.mlp(self.ln_2(x)))
        return x


class VisionTransformer(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,
                 use_abs_pos_emb=True, use_rel_pos_bias=False, use_shared_rel_pos_bias=False,
                 use_mean_pooling=True, init_scale=0.001, use_checkpoint=False,
                 temporal_downsample=True,
                 no_lmhra=False, double_lmhra=True, lmhra_reduction=1.5, 
                 gmhra_layers=4, gmhra_drop_path_rate=0., gmhra_dropout=0.5, 
                 ):
        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

        print(f"Temporal downsample: {temporal_downsample}")
        self.patch_embed = PatchEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim,
            temporal_downsample=temporal_downsample,
        )
        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)

        if use_shared_rel_pos_bias:
            self.rel_pos_bias = RelativePositionBias(window_size=self.patch_embed.patch_shape, num_heads=num_heads)
        else:
            self.rel_pos_bias = None
        self.use_checkpoint = use_checkpoint
        
        print(f'No L_MHRA: {no_lmhra}')
        print(f'Double L_MHRA: {double_lmhra}')
        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,
                no_lmhra=no_lmhra, double_lmhra=double_lmhra, lmhra_reduction=lmhra_reduction, 
            )
            for i in range(depth)])

        # global MHRA
        self.gmhra_layers = gmhra_layers
        self.gmhra_layer_idx = [(depth - 1 - idx) for idx in range(gmhra_layers)]
        print(f"GMHRA index: {self.gmhra_layer_idx}")
        print(f"GMHRA dropout: {gmhra_dropout}")
        if gmhra_layers > 0:
            self.gmhra_cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
        gmhra_dpr = [x.item() for x in torch.linspace(0, gmhra_drop_path_rate, gmhra_layers)]
        self.gmhra = nn.ModuleList([
            Global_MHRA(
                embed_dim, num_heads, mlp_factor=mlp_ratio, 
                drop_path=gmhra_dpr[i], dropout=gmhra_dropout,
            ) for i in range(gmhra_layers)
        ])

        if self.pos_embed is not None:
            trunc_normal_(self.pos_embed, std=.02)
        trunc_normal_(self.cls_token, std=.02)
        self.fix_init_weight()

    def fix_init_weight(self):
        def rescale(param, layer_id):
            param.div_(math.sqrt(2.0 * layer_id))

        for layer_id, layer in enumerate(self.blocks):
            rescale(layer.attn.proj.weight.data, layer_id + 1)
            rescale(layer.mlp.fc2.weight.data, layer_id + 1)

    def forward_features(self, x):
        x = self.patch_embed(x)
        B, C, T, H, W = x.shape
        x = x.permute(0, 2, 3, 4, 1).reshape(B * T, H * W, C)

        cls_tokens = self.cls_token.expand(B * T, -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)

        # the input of global MHRA should be (THW+1)xBx1
        if self.gmhra_layers > 0:
            gmhra_cls_token = self.gmhra_cls_token.repeat(1, B, 1)

        rel_pos_bias = self.rel_pos_bias() if self.rel_pos_bias is not None else None
        j = -1
        for idx, blk in enumerate(self.blocks):
            if self.use_checkpoint:
                x = checkpoint.checkpoint(blk, x, rel_pos_bias, T=T)
            else:
                x = blk(x, rel_pos_bias, T=T)
            if idx in self.gmhra_layer_idx:
                j += 1
                tmp_x = x.clone()
                gmhra_cls_token = self.gmhra[j](gmhra_cls_token, tmp_x, T=T)
        z = torch.cat([x.view(B, -1, C), gmhra_cls_token.permute(1, 0, 2)], dim=1)
        return z

    def forward(self, x):
        x = self.forward_features(x)
        return x
    
    
def interpolate_pos_embed(model, checkpoint_model):
    if 'pos_embed' in checkpoint_model:
        pos_embed_checkpoint = checkpoint_model['pos_embed'].float()
        embedding_size = pos_embed_checkpoint.shape[-1]
        num_patches = model.patch_embed.num_patches
        num_extra_tokens = model.pos_embed.shape[-2] - num_patches
        # height (== width) for the checkpoint position embedding
        orig_size = int((pos_embed_checkpoint.shape[-2] - num_extra_tokens) ** 0.5)
        # height (== width) for the new position embedding
        new_size = int(num_patches ** 0.5)
        # class_token and dist_token are kept unchanged
        if orig_size != new_size:
            print("Position interpolate from %dx%d to %dx%d" % (orig_size, orig_size, new_size, new_size))
            extra_tokens = pos_embed_checkpoint[:, :num_extra_tokens]
            # only the position tokens are interpolated
            pos_tokens = pos_embed_checkpoint[:, num_extra_tokens:]
            pos_tokens = pos_tokens.reshape(-1, orig_size, orig_size, embedding_size).permute(0, 3, 1, 2)
            pos_tokens = torch.nn.functional.interpolate(
                pos_tokens, size=(new_size, new_size), mode='bicubic', align_corners=False)
            pos_tokens = pos_tokens.permute(0, 2, 3, 1).flatten(1, 2)
            new_pos_embed = torch.cat((extra_tokens, pos_tokens), dim=1)
            checkpoint_model['pos_embed'] = new_pos_embed
            
            
def convert_weights_to_fp16(model: nn.Module):
    """Convert applicable model parameters to fp16"""
    def _convert_weights_to_fp16(l):
        if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Linear)):
            l.weight.data = l.weight.data.half()
            if l.bias is not None:
                l.bias.data = l.bias.data.half()
        if isinstance(l, (nn.MultiheadAttention, Attention)):
            for attr in [*[f"{s}_proj_weight" for s in ["in", "q", "k", "v"]], "in_proj_bias", "bias_k", "bias_v"]:
                tensor = getattr(l, attr)
                if tensor is not None:
                    tensor.data = tensor.data.half()
    model.apply(_convert_weights_to_fp16)
    

def inflate_weight(weight_2d, time_dim, center=True):
    print(f'Init center: {center}')
    if center:
        weight_3d = torch.zeros(*weight_2d.shape)
        weight_3d = weight_3d.unsqueeze(2).repeat(1, 1, time_dim, 1, 1)
        middle_idx = time_dim // 2
        weight_3d[:, :, middle_idx, :, :] = weight_2d
    else:
        weight_3d = weight_2d.unsqueeze(2).repeat(1, 1, time_dim, 1, 1)
        weight_3d = weight_3d / time_dim
    return weight_3d


def load_state_dict(model, state_dict, strict=True):
    state_dict_3d = model.state_dict()
    for k in state_dict.keys():
        if k in state_dict_3d.keys() and state_dict[k].shape != state_dict_3d[k].shape:
            if len(state_dict_3d[k].shape) <= 2:
                print(f'Ignore: {k}')
                continue
            print(f'Inflate: {k}, {state_dict[k].shape} => {state_dict_3d[k].shape}')
            time_dim = state_dict_3d[k].shape[2]
            state_dict[k] = inflate_weight(state_dict[k], time_dim)
    msg = model.load_state_dict(state_dict, strict=strict)
    return msg
    

def create_eva_vit_g(
        img_size=224, drop_path_rate=0.4, use_checkpoint=False,
        precision="fp16", vit_model_path=None,
        # UniFormerV2
        temporal_downsample=True,
        no_lmhra=False, 
        double_lmhra=False,
        lmhra_reduction=2.0, 
        gmhra_layers=8, 
        gmhra_drop_path_rate=0.,
        gmhra_dropout=0.5, 
    ):
    model = VisionTransformer(
        img_size=img_size,
        patch_size=14,
        use_mean_pooling=False,
        embed_dim=1408,
        depth=39,
        num_heads=1408//88,
        mlp_ratio=4.3637,
        qkv_bias=True,
        drop_path_rate=drop_path_rate,
        norm_layer=partial(nn.LayerNorm, eps=1e-6),
        use_checkpoint=use_checkpoint,
        temporal_downsample=temporal_downsample,
        no_lmhra=no_lmhra, 
        double_lmhra=double_lmhra,
        lmhra_reduction=lmhra_reduction, 
        gmhra_layers=gmhra_layers, 
        gmhra_drop_path_rate=gmhra_drop_path_rate,
        gmhra_dropout=gmhra_dropout, 
    )  
    if vit_model_path is not None and os.path.isfile(vit_model_path):
        cached_file = download_cached_file(
            vit_model_path, check_hash=False, progress=True
        )
        state_dict = torch.load(cached_file, map_location="cpu")    
        print(f"Load ViT model from: {vit_model_path}")
        interpolate_pos_embed(model, state_dict)
        msg = load_state_dict(model, state_dict, strict=False)
        print(msg)
    
    if precision == "fp16":
#         model.to("cuda") 
        convert_weights_to_fp16(model)
    return model


if __name__ == '__main__':
    import time
    from fvcore.nn import FlopCountAnalysis
    from fvcore.nn import flop_count_table
    import numpy as np

    seed = 4217
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    num_frames = 8

    model = create_eva_vit_g(
        img_size=224, drop_path_rate=0.4, use_checkpoint=False,
        precision="fp16", vit_model_path=None,
        temporal_downsample=True,
        no_lmhra=False, 
        double_lmhra=False,
        lmhra_reduction=2.0, 
        gmhra_layers=12,
        gmhra_drop_path_rate=0.,
        gmhra_dropout=0.5, 
    )
    video = torch.rand(1, 3, num_frames, 224, 224)
    flops = FlopCountAnalysis(model, video)
    s = time.time()
    print(flop_count_table(flops, max_depth=1))
    print(time.time()-s)