MAE.py

from collections import OrderedDict

import torch
import torch.nn as nn

from timm.models.layers import PatchEmbed, Mlp, DropPath, trunc_normal_, lecun_normal_

from functools import partial


# Standard Attention
class Attention(nn.Module):
    def __init__(self, dim, num_heads=8, qkv_bias=False, attn_drop=0., proj_drop=0.):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = 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

        # BNC -> BN(3C) ->BN3H(C//H) -> 3BHN(C//H)
        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        # BHN(C//H)
        q, k, v = qkv[0], qkv[1], qkv[2]   # make torchscript happy (cannot use tensor as tuple)

        # BHN(C//H) @ BH(C//H)N = BHNN
        attn = (q @ k.transpose(-2, -1)) * self.scale
        attn = attn.softmax(dim=-1)
        attn = self.attn_drop(attn)

        # BHNN @ BHN(C//H) = BHN(C//H) -> BNH(C//H) -> BNC
        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


# Standard ViT Block
class Block(nn.Module):

    def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, 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, 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):

    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, 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='', global_pool=False):

        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
        self.global_pool = global_pool
        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, 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)])
        if self.global_pool:
            self.fc_norm = norm_layer(embed_dim)
        else:
            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()

        self.init_weights(weight_init)

    def init_weights(self, mode=''):
        assert mode in ''
        trunc_normal_(self.pos_embed, std=.02)
        if self.dist_token is not None:
            trunc_normal_(self.dist_token, std=.02)
        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)
        if self.global_pool:
            x = x[:, 1:, :].mean(dim=1)  # global pool without cls token
            x = self.fc_norm(x)
        else:
            x = self.norm(x)
            x = x[:, 0]
        if self.dist_token is None:
            if self.global_pool:
                return self.pre_logits(x)
            else:
                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(module: nn.Module, name: str = '', head_bias: float = 0.):
    """ 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(module, nn.Linear):
        if name.startswith('head'):
            nn.init.zeros_(module.weight)
            nn.init.constant_(module.bias, head_bias)
        elif name.startswith('pre_logits'):
            lecun_normal_(module.weight)
            nn.init.zeros_(module.bias)
        else:
            trunc_normal_(module.weight, std=.02)
            if module.bias is not None:
                nn.init.zeros_(module.bias)
    elif isinstance(module, nn.LayerNorm):
        nn.init.zeros_(module.bias)
        nn.init.ones_(module.weight)