vision_transformer.py 10.0 KB
Newer Older
jm_12138's avatar
jm_12138 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14
# copyright (c) 2021 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

jm_12138's avatar
jm_12138 已提交
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
import paddle
import paddle.nn as nn
from paddle.nn.initializer import TruncatedNormal, Constant


__all__ = [
    "VisionTransformer",
    "ViT_small_patch16_224",
    "ViT_base_patch16_224", "ViT_base_patch16_384", "ViT_base_patch32_384",
    "ViT_large_patch16_224", "ViT_large_patch16_384", "ViT_large_patch32_384",
    "ViT_huge_patch16_224", "ViT_huge_patch32_384"
]


trunc_normal_ = TruncatedNormal(std=.02)
zeros_ = Constant(value=0.)
ones_ = Constant(value=1.)


def to_2tuple(x):
    return tuple([x] * 2)


def drop_path(x, drop_prob=0., training=False):
    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ...
    """
    if drop_prob == 0. or not training:
        return x
jm_12138's avatar
jm_12138 已提交
45
    keep_prob = paddle.to_tensor(1 - drop_prob)
jm_12138's avatar
jm_12138 已提交
46 47
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)
    random_tensor = keep_prob + paddle.rand(shape, dtype=x.dtype)
jm_12138's avatar
jm_12138 已提交
48 49
    random_tensor = paddle.floor(random_tensor) # binarize
    output = x.divide(keep_prob) * random_tensor
jm_12138's avatar
jm_12138 已提交
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
    return output

class DropPath(nn.Layer):
    """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)


class Identity(nn.Layer):
    def __init__(self):
        super(Identity, self).__init__()

    def forward(self, input):
        return input


class Mlp(nn.Layer):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=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.Layer):
    def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** -0.5

        self.qkv = nn.Linear(dim, dim * 3, bias_attr=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

    def forward(self, x):
        B, N, C = x.shape
        qkv = self.qkv(x).reshape((B, N, 3, self.num_heads, C //
                                   self.num_heads)).transpose((2, 0, 3, 1, 4))
        q, k, v = qkv[0], qkv[1], qkv[2]

        attn = (q.matmul(k.transpose((0, 1, 3, 2)))) * self.scale
        attn = nn.functional.softmax(attn, axis=-1)
        attn = self.attn_drop(attn)

        x = (attn.matmul(v)).transpose((0, 2, 1, 3)).reshape((B, N, C))
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


class Block(nn.Layer):

    def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., act_layer=nn.GELU, norm_layer='nn.LayerNorm', epsilon=1e-5):
        super().__init__()
        self.norm1 = eval(norm_layer)(dim, epsilon=epsilon)
        self.attn = Attention(
            dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
        # 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. else Identity()
        self.norm2 = eval(norm_layer)(dim, epsilon=epsilon)
        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.Layer):
    """ 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
        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((0, 2, 1))
        return x


class VisionTransformer(nn.Layer):
    """ Vision Transformer with support for patch input
    """

    def __init__(self, img_size=224, patch_size=16, in_chans=3, class_dim=1000, embed_dim=768, depth=12,
                 num_heads=12, mlp_ratio=4, qkv_bias=False, qk_scale=None, drop_rate=0., attn_drop_rate=0.,
                 drop_path_rate=0., norm_layer='nn.LayerNorm', epsilon=1e-5, **args):
        super().__init__()
        self.class_dim = class_dim

        self.num_features = self.embed_dim = embed_dim

        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.pos_embed = self.create_parameter(
            shape=(1, num_patches + 1, embed_dim), default_initializer=zeros_)
        self.add_parameter("pos_embed", self.pos_embed)
        self.cls_token = self.create_parameter(
            shape=(1, 1, embed_dim), default_initializer=zeros_)
        self.add_parameter("cls_token", self.cls_token)
        self.pos_drop = nn.Dropout(p=drop_rate)

        dpr = [x for x in paddle.linspace(0, drop_path_rate, depth)]

        self.blocks = nn.LayerList([
            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, epsilon=epsilon)
            for i in range(depth)])

        self.norm = eval(norm_layer)(embed_dim, epsilon=epsilon)

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

        trunc_normal_(self.pos_embed)
        trunc_normal_(self.cls_token)
        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight)
            if isinstance(m, nn.Linear) and m.bias is not None:
                zeros_(m.bias)
        elif isinstance(m, nn.LayerNorm):
            zeros_(m.bias)
            ones_(m.weight)

    def forward_features(self, x):
        B = x.shape[0]
        x = self.patch_embed(x)
        cls_tokens = self.cls_token.expand((B, -1, -1))
        x = paddle.concat((cls_tokens, x), axis=1)
        x = x + self.pos_embed
        x = self.pos_drop(x)
        for blk in self.blocks:
            x = blk(x)
        x = self.norm(x)
        return x[:, 0]

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


def ViT_small_patch16_224(**kwargs):
    model = VisionTransformer(
        patch_size=16, embed_dim=768, depth=8, num_heads=8, mlp_ratio=3, qk_scale=768**-0.5, **kwargs)
    return model


def ViT_base_patch16_224(**kwargs):
    model = VisionTransformer(
        patch_size=16, embed_dim=768, depth=12, num_heads=12, mlp_ratio=4, qkv_bias=True,
        epsilon=1e-6, **kwargs)
    return model


def ViT_base_patch16_384(**kwargs):
    model = VisionTransformer(
        img_size=384, patch_size=16, embed_dim=768, depth=12, num_heads=12, mlp_ratio=4,
        qkv_bias=True, epsilon=1e-6, **kwargs)
    return model


def ViT_base_patch32_384(**kwargs):
    model = VisionTransformer(
        img_size=384, patch_size=32, embed_dim=768, depth=12, num_heads=12, mlp_ratio=4,
        qkv_bias=True, epsilon=1e-6, **kwargs)
    return model


def ViT_large_patch16_224(**kwargs):
    model = VisionTransformer(
        patch_size=16, embed_dim=1024, depth=24, num_heads=16, mlp_ratio=4, qkv_bias=True,
        epsilon=1e-6, **kwargs)
    return model


def ViT_large_patch16_384(**kwargs):
    model = VisionTransformer(
        img_size=384, patch_size=16, embed_dim=1024, depth=24, num_heads=16, mlp_ratio=4,
        qkv_bias=True, epsilon=1e-6, **kwargs)
    return model


def ViT_large_patch32_384(**kwargs):
    model = VisionTransformer(
        img_size=384, patch_size=32, embed_dim=1024, depth=24, num_heads=16, mlp_ratio=4,
        qkv_bias=True, epsilon=1e-6, **kwargs)
    return model


def ViT_huge_patch16_224(**kwargs):
    model = VisionTransformer(
        patch_size=16, embed_dim=1280, depth=32, num_heads=16, mlp_ratio=4, **kwargs)
    return model


def ViT_huge_patch32_384(**kwargs):
    model = VisionTransformer(
        img_size=384, patch_size=32, embed_dim=1280, depth=32, num_heads=16, mlp_ratio=4, **kwargs)
    return model