File size: 9,665 Bytes
c4b2b37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
""" Vision Transformer (ViT) in PyTorch
Hacked together by / Copyright 2020 Ross Wightman
"""
from functools import partial

import torch
import torch.nn as nn
from baselines.ViT.helpers import load_pretrained
from baselines.ViT.layer_helpers import to_2tuple
from baselines.ViT.weight_init import trunc_normal_
from einops import rearrange


def _cfg(url="", **kwargs):
    return {
        "url": url,
        "num_classes": 1000,
        "input_size": (3, 224, 224),
        "pool_size": None,
        "crop_pct": 0.9,
        "interpolation": "bicubic",
        "first_conv": "patch_embed.proj",
        "classifier": "head",
        **kwargs,
    }


default_cfgs = {
    # patch models
    "vit_small_patch16_224": _cfg(
        url="https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/vit_small_p16_224-15ec54c9.pth",
    ),
    "vit_base_patch16_224": _cfg(
        url="https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_224-80ecf9dd.pth",
        mean=(0.5, 0.5, 0.5),
        std=(0.5, 0.5, 0.5),
    ),
    "vit_large_patch16_224": _cfg(
        url="https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p16_224-4ee7a4dc.pth",
        mean=(0.5, 0.5, 0.5),
        std=(0.5, 0.5, 0.5),
    ),
}


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.drop(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, attn_drop=0.0, proj_drop=0.0):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        # NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
        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)

        self.attn_gradients = None
        self.attention_map = None

    def save_attn_gradients(self, attn_gradients):
        self.attn_gradients = attn_gradients

    def get_attn_gradients(self):
        return self.attn_gradients

    def save_attention_map(self, attention_map):
        self.attention_map = attention_map

    def get_attention_map(self):
        return self.attention_map

    def forward(self, x, register_hook=False):
        b, n, _, h = *x.shape, self.num_heads

        # self.save_output(x)
        # x.register_hook(self.save_output_grad)

        qkv = self.qkv(x)
        q, k, v = rearrange(qkv, "b n (qkv h d) -> qkv b h n d", qkv=3, h=h)

        dots = torch.einsum("bhid,bhjd->bhij", q, k) * self.scale

        attn = dots.softmax(dim=-1)
        attn = self.attn_drop(attn)

        out = torch.einsum("bhij,bhjd->bhid", attn, v)

        self.save_attention_map(attn)
        if register_hook:
            attn.register_hook(self.save_attn_gradients)

        out = rearrange(out, "b h n d -> b n (h d)")
        out = self.proj(out)
        out = self.proj_drop(out)
        return out


class Block(nn.Module):
    def __init__(
        self,
        dim,
        num_heads,
        mlp_ratio=4.0,
        qkv_bias=False,
        drop=0.0,
        attn_drop=0.0,
        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,
        )
        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, register_hook=False):
        x = x + self.attn(self.norm1(x), register_hook=register_hook)
        x = x + 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):
        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])
        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
        )

    def forward(self, x):
        B, C, H, W = x.shape
        # FIXME look at relaxing size constraints
        assert (
            H == self.img_size[0] and W == self.img_size[1]
        ), f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
        x = self.proj(x).flatten(2).transpose(1, 2)
        return x


class VisionTransformer(nn.Module):
    """Vision Transformer"""

    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=4.0,
        qkv_bias=False,
        drop_rate=0.0,
        attn_drop_rate=0.0,
        norm_layer=nn.LayerNorm,
    ):
        super().__init__()
        self.num_classes = num_classes
        self.num_features = (
            self.embed_dim
        ) = embed_dim  # num_features for consistency with other models
        self.patch_embed = PatchEmbed(
            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.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
        self.pos_drop = nn.Dropout(p=drop_rate)

        self.blocks = nn.ModuleList(
            [
                Block(
                    dim=embed_dim,
                    num_heads=num_heads,
                    mlp_ratio=mlp_ratio,
                    qkv_bias=qkv_bias,
                    drop=drop_rate,
                    attn_drop=attn_drop_rate,
                    norm_layer=norm_layer,
                )
                for i in range(depth)
            ]
        )
        self.norm = norm_layer(embed_dim)

        # Classifier head
        self.head = (
            nn.Linear(embed_dim, num_classes) if num_classes > 0 else nn.Identity()
        )

        trunc_normal_(self.pos_embed, std=0.02)
        trunc_normal_(self.cls_token, std=0.02)
        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=0.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    @torch.jit.ignore
    def no_weight_decay(self):
        return {"pos_embed", "cls_token"}

    def forward(self, x, register_hook=False):
        B = x.shape[0]
        x = self.patch_embed(x)

        cls_tokens = self.cls_token.expand(
            B, -1, -1
        )  # stole cls_tokens impl from Phil Wang, thanks
        x = torch.cat((cls_tokens, x), dim=1)
        x = x + self.pos_embed
        x = self.pos_drop(x)

        for blk in self.blocks:
            x = blk(x, register_hook=register_hook)

        x = self.norm(x)
        x = x[:, 0]
        x = self.head(x)
        return x


def _conv_filter(state_dict, patch_size=16):
    """convert patch embedding weight from manual patchify + linear proj to conv"""
    out_dict = {}
    for k, v in state_dict.items():
        if "patch_embed.proj.weight" in k:
            v = v.reshape((v.shape[0], 3, patch_size, patch_size))
        out_dict[k] = v
    return out_dict


def vit_base_patch16_224(pretrained=False, **kwargs):
    model = VisionTransformer(
        patch_size=16,
        embed_dim=768,
        depth=12,
        num_heads=12,
        mlp_ratio=4,
        qkv_bias=True,
        norm_layer=partial(nn.LayerNorm, eps=1e-6),
        **kwargs,
    )
    model.default_cfg = default_cfgs["vit_base_patch16_224"]
    if pretrained:
        load_pretrained(
            model,
            num_classes=model.num_classes,
            in_chans=kwargs.get("in_chans", 3),
            filter_fn=_conv_filter,
        )
    return model


def vit_large_patch16_224(pretrained=False, **kwargs):
    model = VisionTransformer(
        patch_size=16,
        embed_dim=1024,
        depth=24,
        num_heads=16,
        mlp_ratio=4,
        qkv_bias=True,
        norm_layer=partial(nn.LayerNorm, eps=1e-6),
        **kwargs,
    )
    model.default_cfg = default_cfgs["vit_large_patch16_224"]
    if pretrained:
        load_pretrained(
            model, num_classes=model.num_classes, in_chans=kwargs.get("in_chans", 3)
        )
    return model