1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72

class Residual(nn.Module):
    def __init__(self, fn):
        super().__init__()
        self.fn = fn

    def forward(self, x, **kwargs):
        return self.fn(x, **kwargs) + x

class PreNorm(nn.Module):
    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(),
            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=512, num_heads=8):
        super(Attention, self).__init__()
        self.num_heads = num_heads
        self.scale = dim ** -0.5
        assert dim % self.num_heads == 0
        self.qkv = nn.Linear(dim, dim * 3, bias=False)
        self.fc = nn.Sequential(
            nn.Linear(512, 512),
            nn.Dropout(0.1),
        )

    def forward(self, x):
        qkv = self.qkv(x).chunk(3, dim=-1)
        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h=self.num_heads), qkv)

        attn = torch.einsum('bhid,bhjd->bhij', q, k) * self.scale
        attn = attn.softmax(dim=-1)

        out = torch.einsum('bhij,bhjd->bhid', attn, v)
        out = rearrange(out, 'b h n d -> b n (h d)')
        out = self.fc(out)
        return out

class Transformer(nn.Module):
    def __init__(self, dim, depth, heads, mlp_dim, dropout):
        super(Transformer, self).__init__()
        self.layers = nn.ModuleList([])
        for _ in range(depth):
            self.layers.append(nn.ModuleList([
                Residual(PreNorm(dim, Attention(dim, num_heads=heads, dropout=dropout))),
                Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout=dropout)))
            ]))

    def forward(self, x):
        for attn, ff in self.layers:
            x = attn(x)
            x = ff(x)
        return x

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40

class ViT(nn.Module):
    def __init__(self, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, 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 num_patches > MIN_NUM_PATCHES, f'your number of patches ({num_patches}) is way too small for attention to be effective (at least 16). Try decreasing your patch size'

        self.patch_size = patch_size

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

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

        self.to_cls_token = nn.Identity()

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

    def forward(self, img, mask = None):
        p = self.patch_size

        x = rearrange(img, 'b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = p, p2 = p)
        x = self.patch_to_embedding(x)
        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
        x = self.dropout(x)

        x = self.transformer(x, mask)

        x = self.to_cls_token(x[:, 0])
        return self.mlp_head(x)