""" Vision Transformer (ViT) in PyTorch

A PyTorch implement of Vision Transformers as described in
'An Image Is Worth 16 x 16 Words: Transformers for Image Recognition at Scale' - https://arxiv.org/abs/2010.11929

The official jax code is released and available at https://github.com/google-research/vision_transformer

DeiT model defs and weights from https://github.com/facebookresearch/deit,
paper `DeiT: Data-efficient Image Transformers` - https://arxiv.org/abs/2012.12877

Acknowledgments:
* The paper authors for releasing code and weights, thanks!
* I fixed my class token impl based on Phil Wang's https://github.com/lucidrains/vit-pytorch ... check it out
for some einops/einsum fun
* Simple transformer style inspired by Andrej Karpathy's https://github.com/karpathy/minGPT
* Bert reference code checks against Huggingface Transformers and Tensorflow Bert

Hacked together by / Copyright 2020 Ross Wightman
"""
import math
import logging
from functools import partial
from collections import OrderedDict
from copy import deepcopy

import torch
import torch.nn as nn
import torch.nn.functional as F

from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from .helpers import build_model_with_cfg, overlay_external_default_cfg
from .layers import PatchEmbed, Mlp, DropPath, trunc_normal_, lecun_normal_
from .registry import register_model

_logger = logging.getLogger(__name__)


def _cfg(url='', **kwargs):
    return {
        'url': url,
        'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None,
        'crop_pct': .9, 'interpolation': 'bicubic', 'fixed_input_size': True,
        'mean': IMAGENET_DEFAULT_MEAN, 'std': IMAGENET_DEFAULT_STD,
        'first_conv': 'patch_embed.proj', 'classifier': 'head',
        **kwargs
    }


default_cfgs = {
    # patch models (my experiments)
    'vit_small_patch16_224': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/vit_small_p16_224-15ec54c9.pth',
    ),

    # patch models (weights ported from official Google JAX impl)
    'vit_base_patch16_224': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_224-80ecf9dd.pth',
        mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5),
    ),
    'vit_base_patch32_224': _cfg(
        url='',  # no official model weights for this combo, only for in21k
        mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
    'vit_base_patch16_384': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_384-83fb41ba.pth',
        input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),
    'vit_base_patch32_384': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p32_384-830016f5.pth',
        input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),
    'vit_large_patch16_224': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p16_224-4ee7a4dc.pth',
        mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
    'vit_large_patch32_224': _cfg(
        url='',  # no official model weights for this combo, only for in21k
        mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
    'vit_large_patch16_384': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p16_384-b3be5167.pth',
        input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),
    'vit_large_patch32_384': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p32_384-9b920ba8.pth',
        input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),

    # patch models, imagenet21k (weights ported from official Google JAX impl)
    'vit_base_patch16_224_in21k': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch16_224_in21k-e5005f0a.pth',
        num_classes=21843, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
    'vit_base_patch32_224_in21k': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch32_224_in21k-8db57226.pth',
        num_classes=21843, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
    'vit_large_patch16_224_in21k': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch16_224_in21k-606da67d.pth',
        num_classes=21843, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
    'vit_large_patch32_224_in21k': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch32_224_in21k-9046d2e7.pth',
        num_classes=21843, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
    'vit_huge_patch14_224_in21k': _cfg(
        hf_hub='timm/vit_huge_patch14_224_in21k',
        num_classes=21843, mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),

    # deit models (FB weights)
    'vit_deit_tiny_patch16_224': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_tiny_patch16_224-a1311bcf.pth'),
    'vit_deit_small_patch16_224': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_small_patch16_224-cd65a155.pth'),
    'vit_deit_base_patch16_224': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_base_patch16_224-b5f2ef4d.pth',),
    'vit_deit_base_patch16_384': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_base_patch16_384-8de9b5d1.pth',
        input_size=(3, 384, 384), crop_pct=1.0),
    'vit_deit_tiny_distilled_patch16_224': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_tiny_distilled_patch16_224-b40b3cf7.pth',
        classifier=('head', 'head_dist')),
    'vit_deit_small_distilled_patch16_224': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_small_distilled_patch16_224-649709d9.pth',
        classifier=('head', 'head_dist')),
    'vit_deit_base_distilled_patch16_224': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_224-df68dfff.pth',
        classifier=('head', 'head_dist')),
    'vit_deit_base_distilled_patch16_384': _cfg(
        url='https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_384-d0272ac0.pth',
        input_size=(3, 384, 384), crop_pct=1.0, classifier=('head', 'head_dist')),

    # ViT ImageNet-21K-P pretraining
    'vit_base_patch16_224_miil_in21k': _cfg(
        url='https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/ImageNet_21K_P/models/timm/vit_base_patch16_224_in21k_miil.pth',
        mean=(0, 0, 0), std=(1, 1, 1), crop_pct=0.875, interpolation='bilinear', num_classes=11221,
    ),
    'vit_base_patch16_224_miil': _cfg(
        url='https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/ImageNet_21K_P/models/timm'
            '/vit_base_patch16_224_1k_miil_84_4.pth',
        mean=(0, 0, 0), std=(1, 1, 1), crop_pct=0.875, interpolation='bilinear',
    ),
}


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)

    def forward(self, x):
        B, N, C = x.shape
        qkv = self.qkv(x).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]   # make torchscript happy (cannot use tensor as tuple)

        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)
        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., 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)
        # 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)

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


class VisionTransformer(nn.Module):
    """ Vision Transformer

    A PyTorch impl of : `An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale`
        - https://arxiv.org/abs/2010.11929

    Includes distillation token & head support for `DeiT: Data-efficient Image Transformers`
        - https://arxiv.org/abs/2012.12877
    """

    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=True, qk_scale=None, representation_size=None, distilled=False,
                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0., embed_layer=PatchEmbed, norm_layer=None,
                 act_layer=None, weight_init=''):
        """
        Args:
            img_size (int, tuple): input image size
            patch_size (int, tuple): patch size
            in_chans (int): number of input channels
            num_classes (int): number of classes for classification head
            embed_dim (int): embedding dimension
            depth (int): depth of transformer
            num_heads (int): number of attention heads
            mlp_ratio (int): ratio of mlp hidden dim to embedding dim
            qkv_bias (bool): enable bias for qkv if True
            qk_scale (float): override default qk scale of head_dim ** -0.5 if set
            representation_size (Optional[int]): enable and set representation layer (pre-logits) to this value if set
            distilled (bool): model includes a distillation token and head as in DeiT models
            drop_rate (float): dropout rate
            attn_drop_rate (float): attention dropout rate
            drop_path_rate (float): stochastic depth rate
            embed_layer (nn.Module): patch embedding layer
            norm_layer: (nn.Module): normalization layer
            weight_init: (str): weight init scheme
        """
        super().__init__()
        self.num_classes = num_classes
        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
        self.num_tokens = 2 if distilled else 1
        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
        act_layer = act_layer or nn.GELU

        self.patch_embed = embed_layer(
            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.dist_token = nn.Parameter(torch.zeros(1, 1, embed_dim)) if distilled else None
        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
        self.pos_drop = nn.Dropout(p=drop_rate)

        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]  # stochastic depth decay rule
        self.blocks = nn.Sequential(*[
            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, act_layer=act_layer)
            for i in range(depth)])
        self.norm = norm_layer(embed_dim)

        # Representation layer
        if representation_size and not distilled:
            self.num_features = representation_size
            self.pre_logits = nn.Sequential(OrderedDict([
                ('fc', nn.Linear(embed_dim, representation_size)),
                ('act', nn.Tanh())
            ]))
        else:
            self.pre_logits = nn.Identity()

        # Classifier head(s)
        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()
        self.head_dist = None
        if distilled:
            self.head_dist = nn.Linear(self.embed_dim, self.num_classes) if num_classes > 0 else nn.Identity()

        # Weight init
        assert weight_init in ('jax', 'jax_nlhb', 'nlhb', '')
        head_bias = -math.log(self.num_classes) if 'nlhb' in weight_init else 0.
        trunc_normal_(self.pos_embed, std=.02)
        if self.dist_token is not None:
            trunc_normal_(self.dist_token, std=.02)
        if weight_init.startswith('jax'):
            # leave cls token as zeros to match jax impl
            for n, m in self.named_modules():
                _init_vit_weights(m, n, head_bias=head_bias, jax_impl=True)
        else:
            trunc_normal_(self.cls_token, std=.02)
            self.apply(_init_vit_weights)

    def _init_weights(self, m):
        # this fn left here for compat with downstream users
        _init_vit_weights(m)

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

    def get_classifier(self):
        if self.dist_token is None:
            return self.head
        else:
            return self.head, self.head_dist

    def reset_classifier(self, num_classes, global_pool=''):
        self.num_classes = num_classes
        self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
        if self.num_tokens == 2:
            self.head_dist = nn.Linear(self.embed_dim, self.num_classes) if num_classes > 0 else nn.Identity()

    def forward_features(self, x):
        x = self.patch_embed(x)
        cls_token = self.cls_token.expand(x.shape[0], -1, -1)  # stole cls_tokens impl from Phil Wang, thanks
        if self.dist_token is None:
            x = torch.cat((cls_token, x), dim=1)
        else:
            x = torch.cat((cls_token, self.dist_token.expand(x.shape[0], -1, -1), x), dim=1)
        x = self.pos_drop(x + self.pos_embed)
        x = self.blocks(x)
        x = self.norm(x)
        if self.dist_token is None:
            return self.pre_logits(x[:, 0])
        else:
            return x[:, 0], x[:, 1]

    def forward(self, x):
        x = self.forward_features(x)
        if self.head_dist is not None:
            x, x_dist = self.head(x[0]), self.head_dist(x[1])  # x must be a tuple
            if self.training and not torch.jit.is_scripting():
                # during inference, return the average of both classifier predictions
                return x, x_dist
            else:
                return (x + x_dist) / 2
        else:
            x = self.head(x)
        return x


def _init_vit_weights(m, n: str = '', head_bias: float = 0., jax_impl: bool = False):
    """ ViT weight initialization
    * When called without n, head_bias, jax_impl args it will behave exactly the same
      as my original init for compatibility with prev hparam / downstream use cases (ie DeiT).
    * When called w/ valid n (module name) and jax_impl=True, will (hopefully) match JAX impl
    """
    if isinstance(m, nn.Linear):
        if n.startswith('head'):
            nn.init.zeros_(m.weight)
            nn.init.constant_(m.bias, head_bias)
        elif n.startswith('pre_logits'):
            lecun_normal_(m.weight)
            nn.init.zeros_(m.bias)
        else:
            if jax_impl:
                nn.init.xavier_uniform_(m.weight)
                if m.bias is not None:
                    if 'mlp' in n:
                        nn.init.normal_(m.bias, std=1e-6)
                    else:
                        nn.init.zeros_(m.bias)
            else:
                trunc_normal_(m.weight, std=.02)
                if m.bias is not None:
                    nn.init.zeros_(m.bias)
    elif jax_impl and isinstance(m, nn.Conv2d):
        # NOTE conv was left to pytorch default in my original init
        lecun_normal_(m.weight)
        if m.bias is not None:
            nn.init.zeros_(m.bias)
    elif isinstance(m, nn.LayerNorm):
        nn.init.zeros_(m.bias)
        nn.init.ones_(m.weight)


def resize_pos_embed(posemb, posemb_new, num_tokens=1, gs_new=()):
    # Rescale the grid of position embeddings when loading from state_dict. Adapted from
    # https://github.com/google-research/vision_transformer/blob/00883dd691c63a6830751563748663526e811cee/vit_jax/checkpoint.py#L224
    _logger.info('Resized position embedding: %s to %s', posemb.shape, posemb_new.shape)
    ntok_new = posemb_new.shape[1]
    if num_tokens:
        posemb_tok, posemb_grid = posemb[:, :num_tokens], posemb[0, num_tokens:]
        ntok_new -= num_tokens
    else:
        posemb_tok, posemb_grid = posemb[:, :0], posemb[0]
    gs_old = int(math.sqrt(len(posemb_grid)))
    if not len(gs_new):  # backwards compatibility
        gs_new = [int(math.sqrt(ntok_new))] * 2
    assert len(gs_new) >= 2
    _logger.info('Position embedding grid-size from %s to %s', [gs_old, gs_old], gs_new)
    posemb_grid = posemb_grid.reshape(1, gs_old, gs_old, -1).permute(0, 3, 1, 2)
    posemb_grid = F.interpolate(posemb_grid, size=gs_new, mode='bilinear')
    posemb_grid = posemb_grid.permute(0, 2, 3, 1).reshape(1, gs_new[0] * gs_new[1], -1)
    posemb = torch.cat([posemb_tok, posemb_grid], dim=1)
    return posemb


def checkpoint_filter_fn(state_dict, model):
    """ convert patch embedding weight from manual patchify + linear proj to conv"""
    out_dict = {}
    if 'model' in state_dict:
        # For deit models
        state_dict = state_dict['model']
    for k, v in state_dict.items():
        if 'patch_embed.proj.weight' in k and len(v.shape) < 4:
            # For old models that I trained prior to conv based patchification
            O, I, H, W = model.patch_embed.proj.weight.shape
            v = v.reshape(O, -1, H, W)
        elif k == 'pos_embed' and v.shape != model.pos_embed.shape:
            # To resize pos embedding when using model at different size from pretrained weights
            v = resize_pos_embed(
                v, model.pos_embed, getattr(model, 'num_tokens', 1), model.patch_embed.grid_size)
        out_dict[k] = v
    return out_dict


def _create_vision_transformer(variant, pretrained=False, default_cfg=None, **kwargs):
    default_cfg = default_cfg or default_cfgs[variant]
    if kwargs.get('features_only', None):
        raise RuntimeError('features_only not implemented for Vision Transformer models.')

    # NOTE this extra code to support handling of repr size for in21k pretrained models
    default_num_classes = default_cfg['num_classes']
    num_classes = kwargs.get('num_classes', default_num_classes)
    repr_size = kwargs.pop('representation_size', None)
    if repr_size is not None and num_classes != default_num_classes:
        # Remove representation layer if fine-tuning. This may not always be the desired action,
        # but I feel better than doing nothing by default for fine-tuning. Perhaps a better interface?
        _logger.warning("Removing representation layer for fine-tuning.")
        repr_size = None

    model = build_model_with_cfg(
        VisionTransformer, variant, pretrained,
        default_cfg=default_cfg,
        representation_size=repr_size,
        pretrained_filter_fn=checkpoint_filter_fn,
        **kwargs)
    return model


@register_model
def vit_small_patch16_224(pretrained=False, **kwargs):
    """ My custom 'small' ViT model. embed_dim=768, depth=8, num_heads=8, mlp_ratio=3.
    NOTE:
        * this differs from the DeiT based 'small' definitions with embed_dim=384, depth=12, num_heads=6
        * this model does not have a bias for QKV (unlike the official ViT and DeiT models)
    """
    model_kwargs = dict(
        patch_size=16, embed_dim=768, depth=8, num_heads=8, mlp_ratio=3.,
        qkv_bias=False, norm_layer=nn.LayerNorm, **kwargs)
    if pretrained:
        # NOTE my scale was wrong for original weights, leaving this here until I have better ones for this model
        model_kwargs.setdefault('qk_scale', 768 ** -0.5)
    model = _create_vision_transformer('vit_small_patch16_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_base_patch16_224(pretrained=False, **kwargs):
    """ ViT-Base (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights fine-tuned from in21k @ 224x224, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer('vit_base_patch16_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_base_patch32_224(pretrained=False, **kwargs):
    """ ViT-Base (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929). No pretrained weights.
    """
    model_kwargs = dict(patch_size=32, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer('vit_base_patch32_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_base_patch16_384(pretrained=False, **kwargs):
    """ ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer('vit_base_patch16_384', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_base_patch32_384(pretrained=False, **kwargs):
    """ ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(patch_size=32, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer('vit_base_patch32_384', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_large_patch16_224(pretrained=False, **kwargs):
    """ ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights fine-tuned from in21k @ 224x224, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(patch_size=16, embed_dim=1024, depth=24, num_heads=16, **kwargs)
    model = _create_vision_transformer('vit_large_patch16_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_large_patch32_224(pretrained=False, **kwargs):
    """ ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). No pretrained weights.
    """
    model_kwargs = dict(patch_size=32, embed_dim=1024, depth=24, num_heads=16, **kwargs)
    model = _create_vision_transformer('vit_large_patch32_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_large_patch16_384(pretrained=False, **kwargs):
    """ ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(patch_size=16, embed_dim=1024, depth=24, num_heads=16, **kwargs)
    model = _create_vision_transformer('vit_large_patch16_384', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_large_patch32_384(pretrained=False, **kwargs):
    """ ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(patch_size=32, embed_dim=1024, depth=24, num_heads=16, **kwargs)
    model = _create_vision_transformer('vit_large_patch32_384', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_base_patch16_224_in21k(pretrained=False, **kwargs):
    """ ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(
        patch_size=16, embed_dim=768, depth=12, num_heads=12, representation_size=768, **kwargs)
    model = _create_vision_transformer('vit_base_patch16_224_in21k', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_base_patch32_224_in21k(pretrained=False, **kwargs):
    """ ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(
        patch_size=32, embed_dim=768, depth=12, num_heads=12, representation_size=768, **kwargs)
    model = _create_vision_transformer('vit_base_patch32_224_in21k', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_large_patch16_224_in21k(pretrained=False, **kwargs):
    """ ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(
        patch_size=16, embed_dim=1024, depth=24, num_heads=16, representation_size=1024, **kwargs)
    model = _create_vision_transformer('vit_large_patch16_224_in21k', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_large_patch32_224_in21k(pretrained=False, **kwargs):
    """ ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    """
    model_kwargs = dict(
        patch_size=32, embed_dim=1024, depth=24, num_heads=16, representation_size=1024, **kwargs)
    model = _create_vision_transformer('vit_large_patch32_224_in21k', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_huge_patch14_224_in21k(pretrained=False, **kwargs):
    """ ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    NOTE: converted weights not currently available, too large for github release hosting.
    """
    model_kwargs = dict(
        patch_size=14, embed_dim=1280, depth=32, num_heads=16, representation_size=1280, **kwargs)
    model = _create_vision_transformer('vit_huge_patch14_224_in21k', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_deit_tiny_patch16_224(pretrained=False, **kwargs):
    """ DeiT-tiny model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=192, depth=12, num_heads=3, **kwargs)
    model = _create_vision_transformer('vit_deit_tiny_patch16_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_deit_small_patch16_224(pretrained=False, **kwargs):
    """ DeiT-small model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=384, depth=12, num_heads=6, **kwargs)
    model = _create_vision_transformer('vit_deit_small_patch16_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_deit_base_patch16_224(pretrained=False, **kwargs):
    """ DeiT base model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer('vit_deit_base_patch16_224', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_deit_base_patch16_384(pretrained=False, **kwargs):
    """ DeiT base model @ 384x384 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer('vit_deit_base_patch16_384', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_deit_tiny_distilled_patch16_224(pretrained=False, **kwargs):
    """ DeiT-tiny distilled model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=192, depth=12, num_heads=3, **kwargs)
    model = _create_vision_transformer(
        'vit_deit_tiny_distilled_patch16_224', pretrained=pretrained,  distilled=True, **model_kwargs)
    return model


@register_model
def vit_deit_small_distilled_patch16_224(pretrained=False, **kwargs):
    """ DeiT-small distilled model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=384, depth=12, num_heads=6, **kwargs)
    model = _create_vision_transformer(
        'vit_deit_small_distilled_patch16_224', pretrained=pretrained,  distilled=True, **model_kwargs)
    return model


@register_model
def vit_deit_base_distilled_patch16_224(pretrained=False, **kwargs):
    """ DeiT-base distilled model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer(
        'vit_deit_base_distilled_patch16_224', pretrained=pretrained,  distilled=True, **model_kwargs)
    return model


@register_model
def vit_deit_base_distilled_patch16_384(pretrained=False, **kwargs):
    """ DeiT-base distilled model @ 384x384 from paper (https://arxiv.org/abs/2012.12877).
    ImageNet-1k weights from https://github.com/facebookresearch/deit.
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
    model = _create_vision_transformer(
        'vit_deit_base_distilled_patch16_384', pretrained=pretrained, distilled=True, **model_kwargs)
    return model


@register_model
def vit_base_patch16_224_miil_in21k(pretrained=False, **kwargs):
    """ ViT-Base (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
    Weights taken from: https://github.com/Alibaba-MIIL/ImageNet21K
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, qkv_bias=False, **kwargs)
    model = _create_vision_transformer('vit_base_patch16_224_miil_in21k', pretrained=pretrained, **model_kwargs)
    return model


@register_model
def vit_base_patch16_224_miil(pretrained=False, **kwargs):
    """ ViT-Base (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
    Weights taken from: https://github.com/Alibaba-MIIL/ImageNet21K
    """
    model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, qkv_bias=False, **kwargs)
    model = _create_vision_transformer('vit_base_patch16_224_miil', pretrained=pretrained, **model_kwargs)
    return model