mirror of
https://github.com/lucidrains/vit-pytorch.git
synced 2025-12-30 08:02:29 +00:00
131 lines
4.2 KiB
Python
131 lines
4.2 KiB
Python
import torch
|
|
from torch import nn, einsum
|
|
import torch.nn.functional as F
|
|
|
|
from einops import rearrange, repeat
|
|
from einops.layers.torch import Rearrange
|
|
|
|
class FeedForward(nn.Module):
|
|
def __init__(self, dim, hidden_dim, dropout = 0.):
|
|
super().__init__()
|
|
self.net = nn.Sequential(
|
|
nn.LayerNorm(dim),
|
|
nn.Linear(dim, hidden_dim),
|
|
nn.GELU(),
|
|
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
|
|
self.heads = heads
|
|
self.scale = dim_head ** -0.5
|
|
|
|
self.norm = nn.LayerNorm(dim)
|
|
self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
|
|
|
|
self.dropout = nn.Dropout(dropout)
|
|
|
|
self.reattn_weights = nn.Parameter(torch.randn(heads, heads))
|
|
|
|
self.reattn_norm = nn.Sequential(
|
|
Rearrange('b h i j -> b i j h'),
|
|
nn.LayerNorm(heads),
|
|
Rearrange('b i j h -> b h i j')
|
|
)
|
|
|
|
self.to_out = nn.Sequential(
|
|
nn.Linear(inner_dim, dim),
|
|
nn.Dropout(dropout)
|
|
)
|
|
|
|
def forward(self, x):
|
|
b, n, _, h = *x.shape, self.heads
|
|
x = self.norm(x)
|
|
|
|
qkv = self.to_qkv(x).chunk(3, dim = -1)
|
|
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
|
|
|
|
# attention
|
|
|
|
dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
|
|
attn = dots.softmax(dim=-1)
|
|
attn = self.dropout(attn)
|
|
|
|
# re-attention
|
|
|
|
attn = einsum('b h i j, h g -> b g i j', attn, self.reattn_weights)
|
|
attn = self.reattn_norm(attn)
|
|
|
|
# aggregate and out
|
|
|
|
out = einsum('b h i j, b h j d -> b h i d', attn, v)
|
|
out = rearrange(out, 'b h n d -> b n (h d)')
|
|
out = self.to_out(out)
|
|
return 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([
|
|
Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout),
|
|
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 DeepViT(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__()
|
|
assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
|
|
num_patches = (image_size // patch_size) ** 2
|
|
patch_dim = channels * patch_size ** 2
|
|
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_size, p2 = patch_size),
|
|
nn.LayerNorm(patch_dim),
|
|
nn.Linear(patch_dim, dim),
|
|
nn.LayerNorm(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):
|
|
x = self.to_patch_embedding(img)
|
|
b, n, _ = x.shape
|
|
|
|
cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
|
|
x = torch.cat((cls_tokens, x), dim=1)
|
|
x += self.pos_embedding[:, :(n + 1)]
|
|
x = self.dropout(x)
|
|
|
|
x = self.transformer(x)
|
|
|
|
x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
|
|
|
|
x = self.to_latent(x)
|
|
return self.mlp_head(x)
|