vit-pytorch.py

import torch
from torch import nn

from einops import rearrange, repeat
from einops.layers.torch import Rearrange

# helpers

def pair(t):
    return t if isinstance(t, tuple) else (t, t)

# classes

class PreNorm(nn.Module):
    """
        PreNorm对应框图中最下面的黄色的Norm层。其参数dim是维度，而fn则是预先要进行的处理函数，是以下的Attention、FeedForward之一
    """
    def __init__(self, dim, fn):
        super().__init__()
        self.norm = nn.LayerNorm(dim)
        self.fn = fn
    def forward(self, x, **kwargs):
        return self.fn(self.norm(x), **kwargs)

class FeedForward(nn.Module):
    def __init__(self, dim, hidden_dim, dropout = 0.):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(dim, hidden_dim),
            nn.GELU(),  # https://zhuanlan.zhihu.com/p/394465965
            nn.Dropout(dropout),
            nn.Linear(hidden_dim, dim),
            nn.Dropout(dropout)
        )
    def forward(self, x):
        return self.net(x)


class Attention(nn.Module):
    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
        super().__init__()
        inner_dim = dim_head *  heads
        project_out = not (heads == 1 and dim_head == dim)

        self.heads = heads
        self.scale = dim_head ** -0.5

        self.attend = nn.Softmax(dim = -1)
        self.dropout = nn.Dropout(dropout)

        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)

        self.to_out = nn.Sequential(
            nn.Linear(inner_dim, dim),
            nn.Dropout(dropout)
        ) if project_out else nn.Identity()

    def forward(self, x):  # https://zhuanlan.zhihu.com/p/442125846
        # 输入 x -> (batch, 197, 768)即(batch, num_patch + 1, hid_dims)
        # 按照最后一维（特征维度)分成3块，分别对应QKV
        # chunk后是一个tuple，即(q, k, v)
        qkv = self.to_qkv(x).chunk(3, dim = -1)
        # q, k, v都做维度变换，(batch, 197, 768) -> (batch, 12, 197, 768 / 12 = 64)
        # 12是head的数量，目的是做**多头**注意力机制
        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)

        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale

        attn = self.attend(dots)
        attn = self.dropout(attn)

        out = torch.matmul(attn, v)
        # 把多头拼回去 -> (batch, 197, 768)
        out = rearrange(out, 'b h n d -> b n (h d)')
        return self.to_out(out)


class Transformer(nn.Module):
    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
        super().__init__()
        self.layers = nn.ModuleList([])
        for _ in range(depth):
            self.layers.append(nn.ModuleList([
                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
            ]))
    def forward(self, x):
        for attn, ff in self.layers:
            x = attn(x) + x
            x = ff(x) + x
        return x

class ViT(nn.Module):
    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
        super().__init__()
        image_height, image_width = pair(image_size)
        patch_height, patch_width = pair(patch_size)

        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'

        num_patches = (image_height // patch_height) * (image_width // patch_width)
        patch_dim = channels * patch_height * patch_width
        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'

        self.to_patch_embedding = nn.Sequential(
            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
            nn.Linear(patch_dim, dim),
        )

        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
        self.dropout = nn.Dropout(emb_dropout)

        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)

        self.pool = pool
        self.to_latent = nn.Identity()

        self.mlp_head = nn.Sequential(
            nn.LayerNorm(dim),
            nn.Linear(dim, num_classes)
        )

    def forward(self, img):     # https://blog.csdn.net/weixin_44966641/article/details/118733341
        x = self.to_patch_embedding(img)         # b c (h p1) (w p2) -> b (h w) (p1 p2 c) -> b (h w) dim
        b, n, _ = x.shape       # b表示batchSize, n表示每个块的空间分辨率, _表示一个块内有多少个值

        cls_tokens = repeat(self.cls_token, '1 1 d -> b 1 d', b = b)    # self.cls_token: (1, 1, dim) -> cls_tokens: (batchSize, 1, dim)
        x = torch.cat((cls_tokens, x), dim=1)   # 将cls_token拼接到patch token中去       (b, 65, dim)
        x += self.pos_embedding[:, :(n + 1)]    # 加位置嵌入（直接加）      (b, 65, dim)
        x = self.dropout(x)

        x = self.transformer(x)

        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]     # (b, dim)  默认不进行池化，即x[:, 0]只取第一个token（cls_token）。

        x = self.to_latent(x)
        return self.mlp_head(x)


if __name__ == "__main__":
    model_vit = ViT(
            image_size = 256,
            patch_size = 32,
            num_classes = 1000,
            dim = 1024,
            depth = 6,
            heads = 16,
            mlp_dim = 2048,
            dropout = 0.1,
            emb_dropout = 0.1
        )

    img = torch.randn(16, 3, 256, 256)

    preds = model_vit(img)

    print(preds.shape)  # (16, 1000)