src/models/backbones/vit.py

# Copyright (c) OpenMMLab. All rights reserved.
from functools import partial

import torch
import torch.nn as nn
import torch.utils.checkpoint as checkpoint
from timm.models.layers import drop_path, to_2tuple, trunc_normal_


def vit(cfg):
    return ViT(
        img_size=(256, 192),
        patch_size=16,
        embed_dim=1280,
        depth=32,
        num_heads=16,
        ratio=1,
        use_checkpoint=False,
        mlp_ratio=4,
        qkv_bias=True,
        drop_path_rate=0.55,
    )


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=0.0,
    ):
        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.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=0.0,
        proj_drop=0.0,
        attn_head_dim=None,
    ):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.dim = dim

        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=qkv_bias)

        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):
        B, N, C = x.shape
        qkv = self.qkv(x)
        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)

        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=4.0,
        qkv_bias=False,
        qk_scale=None,
        drop=0.0,
        attn_drop=0.0,
        drop_path=0.0,
        act_layer=nn.GELU,
        norm_layer=nn.LayerNorm,
        attn_head_dim=None,
    ):
        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,
            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 > 0.0 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 PatchEmbed(nn.Module):
    """Image to Patch Embedding"""

    def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768, ratio=1):
        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]) * (ratio**2)
        self.patch_shape = (
            int(img_size[0] // patch_size[0] * ratio),
            int(img_size[1] // patch_size[1] * ratio),
        )
        self.origin_patch_shape = (
            int(img_size[0] // patch_size[0]),
            int(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[0] // ratio),
            padding=4 + 2 * (ratio // 2 - 1),
        )

    def forward(self, x, **kwargs):
        B, C, H, W = x.shape
        x = self.proj(x)
        Hp, Wp = x.shape[2], x.shape[3]

        x = x.flatten(2).transpose(1, 2)
        return x, (Hp, Wp)


class ViT(nn.Module):

    def __init__(
        self,
        img_size=224,
        patch_size=16,
        in_chans=3,
        num_classes=80,
        embed_dim=768,
        depth=12,
        num_heads=12,
        mlp_ratio=4.0,
        qkv_bias=False,
        qk_scale=None,
        drop_rate=0.0,
        attn_drop_rate=0.0,
        drop_path_rate=0.0,
        hybrid_backbone=None,
        norm_layer=None,
        use_checkpoint=False,
        frozen_stages=-1,
        ratio=1,
        last_norm=True,
        patch_padding="pad",
        freeze_attn=False,
        freeze_ffn=False,
    ):
        # Protect mutable default arguments
        super(ViT, self).__init__()
        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
        self.num_classes = num_classes
        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
        self.frozen_stages = frozen_stages
        self.use_checkpoint = use_checkpoint
        self.patch_padding = patch_padding
        self.freeze_attn = freeze_attn
        self.freeze_ffn = freeze_ffn
        self.depth = depth

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

        # since the pretraining model has class token
        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))

        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]  # stochastic depth decay rule

        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.last_norm = norm_layer(embed_dim) if last_norm else nn.Identity()

        if self.pos_embed is not None:
            trunc_normal_(self.pos_embed, std=0.02)

    def forward_features(self, x):
        B, C, H, W = x.shape
        x, (Hp, Wp) = self.patch_embed(x)

        if self.pos_embed is not None:
            # fit for multiple GPU training
            # since the first element for pos embed (sin-cos manner) is zero, it will cause no difference
            x = x + self.pos_embed[:, 1:] + self.pos_embed[:, :1]

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

        x = self.last_norm(x)

        xp = x.permute(0, 2, 1).reshape(B, -1, Hp, Wp).contiguous()

        return xp

    def forward(self, x):
        x = self.forward_features(x)
        return x