Spaces:
Sleeping
Sleeping
File size: 47,621 Bytes
b4d6f1e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 |
""" Vision Transformer (ViT) in PyTorch
A PyTorch implement of Vision Transformers as described in:
'An Image Is Worth 16 x 16 Words: Transformers for Image Recognition at Scale'
- https://arxiv.org/abs/2010.11929
`How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers`
- https://arxiv.org/abs/2106.10270
The official jax code is released and available at https://github.com/google-research/vision_transformer
DeiT model defs and weights from https://github.com/facebookresearch/deit,
paper `DeiT: Data-efficient Image Transformers` - https://arxiv.org/abs/2012.12877
Acknowledgments:
* The paper authors for releasing code and weights, thanks!
* I fixed my class token impl based on Phil Wang's https://github.com/lucidrains/vit-pytorch ... check it out
for some einops/einsum fun
* Simple transformer style inspired by Andrej Karpathy's https://github.com/karpathy/minGPT
* Bert reference code checks against Huggingface Transformers and Tensorflow Bert
Hacked together by / Copyright 2021 Ross Wightman
"""
import math
import logging
from functools import partial
from collections import OrderedDict
from copy import deepcopy
import torch
import torch.nn as nn
import torch.nn.functional as F
from .layers import PatchEmbed, Mlp, DropPath, to_2tuple, trunc_normal_
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD, IMAGENET_INCEPTION_MEAN, IMAGENET_INCEPTION_STD
from .helpers import build_model_with_cfg, named_apply, adapt_input_conv
from .layers import PatchEmbed, Mlp, DropPath, trunc_normal_, lecun_normal_
from .registry import register_model
_logger = logging.getLogger(__name__)
def _cfg(url='', **kwargs):
return {
'url': url,
'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None,
'crop_pct': .9, 'interpolation': 'bicubic', 'fixed_input_size': True,
'mean': IMAGENET_INCEPTION_MEAN, 'std': IMAGENET_INCEPTION_STD,
'first_conv': 'patch_embed.proj', 'classifier': 'head',
**kwargs
}
default_cfgs = {
# patch models (weights from official Google JAX impl)
'vit_tiny_patch16_224': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'Ti_16-i21k-300ep-lr_0.001-aug_none-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_224.npz'),
'vit_tiny_patch16_384': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'Ti_16-i21k-300ep-lr_0.001-aug_none-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz',
input_size=(3, 384, 384), crop_pct=1.0),
'vit_small_patch32_224': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'S_32-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_224.npz'),
'vit_small_patch32_384': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'S_32-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz',
input_size=(3, 384, 384), crop_pct=1.0),
'vit_small_patch16_224': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'S_16-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_224.npz'),
'vit_small_patch16_384': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'S_16-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz',
input_size=(3, 384, 384), crop_pct=1.0),
'vit_base_patch32_224': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'B_32-i21k-300ep-lr_0.001-aug_medium1-wd_0.03-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_224.npz'),
'vit_base_patch32_384': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'B_32-i21k-300ep-lr_0.001-aug_light1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz',
input_size=(3, 384, 384), crop_pct=1.0),
'vit_base_patch16_224': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_224.npz'),
'vit_base_patch16_384': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_384.npz',
input_size=(3, 384, 384), crop_pct=1.0),
'vit_large_patch32_224': _cfg(
url='', # no official model weights for this combo, only for in21k
),
'vit_large_patch32_384': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p32_384-9b920ba8.pth',
input_size=(3, 384, 384), crop_pct=1.0),
'vit_large_patch16_224': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'L_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.1-sd_0.1--imagenet2012-steps_20k-lr_0.01-res_224.npz'),
'vit_large_patch16_384': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/'
'L_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.1-sd_0.1--imagenet2012-steps_20k-lr_0.01-res_384.npz',
input_size=(3, 384, 384), crop_pct=1.0),
# patch models, imagenet21k (weights from official Google JAX impl)
'vit_tiny_patch16_224_in21k': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/Ti_16-i21k-300ep-lr_0.001-aug_none-wd_0.03-do_0.0-sd_0.0.npz',
num_classes=21843),
'vit_small_patch32_224_in21k': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/S_32-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0.npz',
num_classes=21843),
'vit_small_patch16_224_in21k': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/S_16-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0.npz',
num_classes=21843),
'vit_base_patch32_224_in21k': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/B_32-i21k-300ep-lr_0.001-aug_medium1-wd_0.03-do_0.0-sd_0.0.npz',
num_classes=21843),
'vit_base_patch16_224_in21k': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0.npz',
num_classes=21843),
'vit_large_patch32_224_in21k': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch32_224_in21k-9046d2e7.pth',
num_classes=21843),
'vit_large_patch16_224_in21k': _cfg(
url='https://storage.googleapis.com/vit_models/augreg/L_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.1-sd_0.1.npz',
num_classes=21843),
'vit_huge_patch14_224_in21k': _cfg(
url='https://storage.googleapis.com/vit_models/imagenet21k/ViT-H_14.npz',
hf_hub='timm/vit_huge_patch14_224_in21k',
num_classes=21843),
# deit models (FB weights)
'deit_tiny_patch16_224': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_tiny_patch16_224-a1311bcf.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD),
'deit_small_patch16_224': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_small_patch16_224-cd65a155.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD),
'deit_base_patch16_224': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_base_patch16_224-b5f2ef4d.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD),
'deit_base_patch16_384': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_base_patch16_384-8de9b5d1.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD, input_size=(3, 384, 384), crop_pct=1.0),
'deit_tiny_distilled_patch16_224': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_tiny_distilled_patch16_224-b40b3cf7.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD, classifier=('head', 'head_dist')),
'deit_small_distilled_patch16_224': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_small_distilled_patch16_224-649709d9.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD, classifier=('head', 'head_dist')),
'deit_base_distilled_patch16_224': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_224-df68dfff.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD, classifier=('head', 'head_dist')),
'deit_base_distilled_patch16_384': _cfg(
url='https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_384-d0272ac0.pth',
mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEFAULT_STD, input_size=(3, 384, 384), crop_pct=1.0,
classifier=('head', 'head_dist')),
# ViT ImageNet-21K-P pretraining by MILL
'vit_base_patch16_224_miil_in21k': _cfg(
url='https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/ImageNet_21K_P/models/timm/vit_base_patch16_224_in21k_miil.pth',
mean=(0, 0, 0), std=(1, 1, 1), crop_pct=0.875, interpolation='bilinear', num_classes=11221,
),
'vit_base_patch16_224_miil': _cfg(
url='https://miil-public-eu.oss-eu-central-1.aliyuncs.com/model-zoo/ImageNet_21K_P/models/timm'
'/vit_base_patch16_224_1k_miil_84_4.pth',
mean=(0, 0, 0), std=(1, 1, 1), crop_pct=0.875, interpolation='bilinear',
),
}
class CrossAttention(nn.Module):
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 #这行多了个qk_scale #0.125
self.wq = nn.Linear(dim, dim, bias=qkv_bias)
self.wk = nn.Linear(dim, dim, bias=qkv_bias)
self.wv = nn.Linear(dim, dim, bias=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 #2 512 768
q = self.wq(x[:, 0:int(N/2), ...]).reshape(B, int(N/2), self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)#2 12 256 64
k = self.wk(x[:, (int(N/2)):, ...]).reshape(B, int(N/2), self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
v = self.wv(x[:, (int(N/2)):, ...]).reshape(B, int(N/2), self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
attn = (q @ k.transpose(-2, -1)) * self.scale
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B, int(N/2), C) #变成了B/2 2 256 768
x = self.proj(x)
x = self.proj_drop(x)
return x
class Attention(nn.Module):
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=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, data):
b,c,h = data.shape
x,atten_mask = data[:,0:int(c/2),...],data[:,int(c/2):,...]
B, N, C = x.shape
qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
q, k, v = qkv[0], qkv[1], qkv[2] #2,12,49,64 # make torchscript happy (cannot use tensor as tuple)
attn = (q @ k.transpose(-2, -1)) * self.scale #2,12,49,49 #mask 2,1,49,49
if atten_mask.sum() != 0:
atten_mask = atten_mask.unsqueeze(1) # 2,1,49,49
attn = attn + atten_mask
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class Attention_ori(nn.Module):
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=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).permute(2, 0, 3, 1, 4)
q, k, v = qkv[0], qkv[1], qkv[2] #2,12,49,64 # make torchscript happy (cannot use tensor as tuple)
attn = (q @ k.transpose(-2, -1)) * self.scale #2,12,49,49 #mask 2,1,49,49
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class Block(nn.Module):
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, drop=0., attn_drop=0.,
drop_path=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)
# 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 nn.Identity()
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, data):
b,c,h = data.shape
x,mask = data[:,0:int(c/2),...],data[:,int(c/2):,...]
x = x + self.drop_path(self.attn(torch.cat([self.norm1(x),mask],dim=1)))
x = x + self.drop_path(self.mlp(self.norm2(x)))
return torch.cat([x,mask],dim=1)
class mask_PatchEmbed(nn.Module):
def __init__(self, img_size=224, patch_size=16, in_chans=3, norm_layer=None, flatten=True):
super().__init__()
img_size = to_2tuple(img_size)
patch_size = to_2tuple(patch_size)
self.img_size = img_size
self.patch_size = patch_size
self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
self.flatten = flatten
self.num_patches = self.grid_size[0] * self.grid_size[1]
self.proj = nn.Conv2d(in_chans, 1, kernel_size=patch_size, stride=patch_size).requires_grad_(False)
nn.init.ones_(self.proj.weight)
nn.init.zeros_(self.proj.bias)
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)
if self.flatten:
x = x.flatten(2).transpose(1, 2) # BCHW -> BNC
return x
class VisionTransformer(nn.Module):
""" Vision Transformer
A PyTorch impl of : `An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale`
- https://arxiv.org/abs/2010.11929
Includes distillation token & head support for `DeiT: Data-efficient Image Transformers`
- https://arxiv.org/abs/2012.12877
"""
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., qkv_bias=True, representation_size=None, distilled=False,
drop_rate=0., attn_drop_rate=0., drop_path_rate=0., embed_layer=PatchEmbed, norm_layer=None,
act_layer=None,as_backbone=True, weight_init=''):
"""
Args:
img_size (int, tuple): input image size
patch_size (int, tuple): patch size
in_chans (int): number of input channels
num_classes (int): number of classes for classification head
embed_dim (int): embedding dimension
depth (int): depth of transformer
num_heads (int): number of attention heads
mlp_ratio (int): ratio of mlp hidden dim to embedding dim
qkv_bias (bool): enable bias for qkv if True
representation_size (Optional[int]): enable and set representation layer (pre-logits) to this value if set
distilled (bool): model includes a distillation token and head as in DeiT models
drop_rate (float): dropout rate
attn_drop_rate (float): attention dropout rate
drop_path_rate (float): stochastic depth rate
embed_layer (nn.Module): patch embedding layer
norm_layer: (nn.Module): normalization layer
weight_init: (str): weight init scheme
"""
super().__init__()
self.num_classes = num_classes
self.num_features = self.embed_dim = embed_dim # num_features for consistency with other models
self.num_tokens = 2 if distilled else 1
self.num_heads = num_heads
norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
act_layer = act_layer or nn.GELU
self.as_backbone = as_backbone #是否分类任务,如果不是,class不加上去
self.patch_embed = embed_layer(
img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim)
self.mask_embed = mask_PatchEmbed(img_size=img_size, patch_size=patch_size, in_chans=in_chans)
num_patches = self.patch_embed.num_patches
self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
self.dist_token = nn.Parameter(torch.zeros(1, 1, embed_dim)) if distilled else None
if not self.as_backbone:
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
else:
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim))
self.pos_drop = nn.Dropout(p=drop_rate)
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)] # stochastic depth decay rule
self.blocks = nn.Sequential(*[
Block(
dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, drop=drop_rate,
attn_drop=attn_drop_rate, drop_path=dpr[i], norm_layer=norm_layer, act_layer=act_layer)
for i in range(depth)])
self.norm = norm_layer(embed_dim)
# Representation layer
if representation_size and not distilled:
self.num_features = representation_size
self.pre_logits = nn.Sequential(OrderedDict([
('fc', nn.Linear(embed_dim, representation_size)),
('act', nn.Tanh())
]))
else:
self.pre_logits = nn.Identity()
if not self.as_backbone:
self.avgpool = nn.AdaptiveAvgPool1d(1)
# Classifier head(s)
self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()
self.head_dist = None
if distilled:
self.head_dist = nn.Linear(self.embed_dim, self.num_classes) if num_classes > 0 else nn.Identity()
self.init_weights(weight_init)
def init_weights(self, mode=''):
assert mode in ('jax', 'jax_nlhb', 'nlhb', '')
head_bias = -math.log(self.num_classes) if 'nlhb' in mode else 0.
trunc_normal_(self.pos_embed, std=.02)
if self.dist_token is not None:
trunc_normal_(self.dist_token, std=.02)
if mode.startswith('jax'):
# leave cls token as zeros to match jax impl
named_apply(partial(_init_vit_weights, head_bias=head_bias, jax_impl=True), self)
else:
trunc_normal_(self.cls_token, std=.02)
self.apply(_init_vit_weights)
def _init_weights(self, m):
# this fn left here for compat with downstream users
_init_vit_weights(m)
@torch.jit.ignore()
def load_pretrained(self, checkpoint_path, prefix=''):
_load_weights(self, checkpoint_path, prefix)
@torch.jit.ignore
def no_weight_decay(self):
return {'pos_embed', 'cls_token', 'dist_token'}
def get_classifier(self):
if self.dist_token is None:
return self.head
else:
return self.head, self.head_dist
def reset_classifier(self, num_classes, global_pool=''):
self.num_classes = num_classes
self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
if self.num_tokens == 2:
self.head_dist = nn.Linear(self.embed_dim, self.num_classes) if num_classes > 0 else nn.Identity()
def forward_features(self, data):
x,mask = data[:,0,:,:].unsqueeze(1),data[:,1,:,:].unsqueeze(1)
x = self.patch_embed(x)#B N C
atten_mask = torch.zeros_like(x) # 2 49 768
if mask.sum() != 0:
mask = self.mask_embed(mask) ###
mask.squeeze_(dim=2)
mask[mask != 0] = 1 ### H W数目token C编码长度
k1 = mask[:, None, :]
k2 = torch.ones_like(mask)[:, :, None]
k3 = k1 * k2
atten_mask = (1.0 - k3) * (-1e6)
atten_mask.requires_grad_(True)
self.atten_mask = atten_mask
cls_token = self.cls_token.expand(x.shape[0], -1, -1) # stole cls_tokens impl from Phil Wang, thanks
if not self.as_backbone:
if self.dist_token is None:
x = torch.cat((cls_token, x), dim=1)
else:
x = torch.cat((cls_token, self.dist_token.expand(x.shape[0], -1, -1), x), dim=1)
x = self.pos_drop(x + self.pos_embed) #2 49 768
x = self.blocks(torch.cat([x,atten_mask],dim=1))
b,c,h = x.shape
x = x[:,0:int(c/2),...]
x = self.norm(x)
if self.as_backbone:
# x = self.avgpool(x.transpose(1, 2)) # B C 1
# x = torch.flatten(x, 1)
return x
if self.dist_token is None:
return self.pre_logits(x[:, 0])
else:
return x[:, 0], x[:, 1]
def forward(self, data):
x = self.forward_features(data) #2 49 768
if self.as_backbone:
return x
else:
if self.head_dist is not None:
x, x_dist = self.head(x[0]), self.head_dist(x[1]) # x must be a tuple
if self.training and not torch.jit.is_scripting():
# during inference, return the average of both classifier predictions
return x, x_dist
else:
return (x + x_dist) / 2
else:
x = self.head(x)
return x
def _init_vit_weights(module: nn.Module, name: str = '', head_bias: float = 0., jax_impl: bool = False):
""" ViT weight initialization
* When called without n, head_bias, jax_impl args it will behave exactly the same
as my original init for compatibility with prev hparam / downstream use cases (ie DeiT).
* When called w/ valid n (module name) and jax_impl=True, will (hopefully) match JAX impl
"""
if isinstance(module, nn.Linear):
if name.startswith('head'):
nn.init.zeros_(module.weight)
nn.init.constant_(module.bias, head_bias)
elif name.startswith('pre_logits'):
lecun_normal_(module.weight)
nn.init.zeros_(module.bias)
else:
if jax_impl:
nn.init.xavier_uniform_(module.weight)
if module.bias is not None:
if 'mlp' in name:
nn.init.normal_(module.bias, std=1e-6)
else:
nn.init.zeros_(module.bias)
else:
trunc_normal_(module.weight, std=.02)
if module.bias is not None:
nn.init.zeros_(module.bias)
elif jax_impl and isinstance(module, nn.Conv2d):
# NOTE conv was left to pytorch default in my original init
lecun_normal_(module.weight)
if module.bias is not None:
nn.init.zeros_(module.bias)
elif isinstance(module, (nn.LayerNorm, nn.GroupNorm, nn.BatchNorm2d)):
nn.init.zeros_(module.bias)
nn.init.ones_(module.weight)
@torch.no_grad()
def _load_weights(model: VisionTransformer, checkpoint_path: str, prefix: str = ''):
""" Load weights from .npz checkpoints for official Google Brain Flax implementation
"""
import numpy as np
def _n2p(w, t=True):
if w.ndim == 4 and w.shape[0] == w.shape[1] == w.shape[2] == 1:
w = w.flatten()
if t:
if w.ndim == 4:
w = w.transpose([3, 2, 0, 1])
elif w.ndim == 3:
w = w.transpose([2, 0, 1])
elif w.ndim == 2:
w = w.transpose([1, 0])
return torch.from_numpy(w)
w = np.load(checkpoint_path)
if not prefix and 'opt/target/embedding/kernel' in w:
prefix = 'opt/target/'
if hasattr(model.patch_embed, 'backbone'):
# hybrid
backbone = model.patch_embed.backbone
stem_only = not hasattr(backbone, 'stem')
stem = backbone if stem_only else backbone.stem
stem.conv.weight.copy_(adapt_input_conv(stem.conv.weight.shape[1], _n2p(w[f'{prefix}conv_root/kernel'])))
stem.norm.weight.copy_(_n2p(w[f'{prefix}gn_root/scale']))
stem.norm.bias.copy_(_n2p(w[f'{prefix}gn_root/bias']))
if not stem_only:
for i, stage in enumerate(backbone.stages):
for j, block in enumerate(stage.blocks):
bp = f'{prefix}block{i + 1}/unit{j + 1}/'
for r in range(3):
getattr(block, f'conv{r + 1}').weight.copy_(_n2p(w[f'{bp}conv{r + 1}/kernel']))
getattr(block, f'norm{r + 1}').weight.copy_(_n2p(w[f'{bp}gn{r + 1}/scale']))
getattr(block, f'norm{r + 1}').bias.copy_(_n2p(w[f'{bp}gn{r + 1}/bias']))
if block.downsample is not None:
block.downsample.conv.weight.copy_(_n2p(w[f'{bp}conv_proj/kernel']))
block.downsample.norm.weight.copy_(_n2p(w[f'{bp}gn_proj/scale']))
block.downsample.norm.bias.copy_(_n2p(w[f'{bp}gn_proj/bias']))
embed_conv_w = _n2p(w[f'{prefix}embedding/kernel'])
else:
embed_conv_w = adapt_input_conv(
model.patch_embed.proj.weight.shape[1], _n2p(w[f'{prefix}embedding/kernel']))
model.patch_embed.proj.weight.copy_(embed_conv_w)
model.patch_embed.proj.bias.copy_(_n2p(w[f'{prefix}embedding/bias']))
model.cls_token.copy_(_n2p(w[f'{prefix}cls'], t=False))
pos_embed_w = _n2p(w[f'{prefix}Transformer/posembed_input/pos_embedding'], t=False)
if pos_embed_w.shape != model.pos_embed.shape:
pos_embed_w = resize_pos_embed( # resize pos embedding when different size from pretrained weights
pos_embed_w, model.pos_embed, getattr(model, 'num_tokens', 1), model.patch_embed.grid_size)
model.pos_embed.copy_(pos_embed_w)
model.norm.weight.copy_(_n2p(w[f'{prefix}Transformer/encoder_norm/scale']))
model.norm.bias.copy_(_n2p(w[f'{prefix}Transformer/encoder_norm/bias']))
if isinstance(model.head, nn.Linear) and model.head.bias.shape[0] == w[f'{prefix}head/bias'].shape[-1]:
model.head.weight.copy_(_n2p(w[f'{prefix}head/kernel']))
model.head.bias.copy_(_n2p(w[f'{prefix}head/bias']))
if isinstance(getattr(model.pre_logits, 'fc', None), nn.Linear) and f'{prefix}pre_logits/bias' in w:
model.pre_logits.fc.weight.copy_(_n2p(w[f'{prefix}pre_logits/kernel']))
model.pre_logits.fc.bias.copy_(_n2p(w[f'{prefix}pre_logits/bias']))
for i, block in enumerate(model.blocks.children()):
block_prefix = f'{prefix}Transformer/encoderblock_{i}/'
mha_prefix = block_prefix + 'MultiHeadDotProductAttention_1/'
block.norm1.weight.copy_(_n2p(w[f'{block_prefix}LayerNorm_0/scale']))
block.norm1.bias.copy_(_n2p(w[f'{block_prefix}LayerNorm_0/bias']))
block.attn.qkv.weight.copy_(torch.cat([
_n2p(w[f'{mha_prefix}{n}/kernel'], t=False).flatten(1).T for n in ('query', 'key', 'value')]))
block.attn.qkv.bias.copy_(torch.cat([
_n2p(w[f'{mha_prefix}{n}/bias'], t=False).reshape(-1) for n in ('query', 'key', 'value')]))
block.attn.proj.weight.copy_(_n2p(w[f'{mha_prefix}out/kernel']).flatten(1))
block.attn.proj.bias.copy_(_n2p(w[f'{mha_prefix}out/bias']))
for r in range(2):
getattr(block.mlp, f'fc{r + 1}').weight.copy_(_n2p(w[f'{block_prefix}MlpBlock_3/Dense_{r}/kernel']))
getattr(block.mlp, f'fc{r + 1}').bias.copy_(_n2p(w[f'{block_prefix}MlpBlock_3/Dense_{r}/bias']))
block.norm2.weight.copy_(_n2p(w[f'{block_prefix}LayerNorm_2/scale']))
block.norm2.bias.copy_(_n2p(w[f'{block_prefix}LayerNorm_2/bias']))
def resize_pos_embed(posemb, posemb_new, num_tokens=1, gs_new=()):
# Rescale the grid of position embeddings when loading from state_dict. Adapted from
# https://github.com/google-research/vision_transformer/blob/00883dd691c63a6830751563748663526e811cee/vit_jax/checkpoint.py#L224
_logger.info('Resized position embedding: %s to %s', posemb.shape, posemb_new.shape)
ntok_new = posemb_new.shape[1]
if num_tokens:
posemb_tok, posemb_grid = posemb[:, :num_tokens], posemb[0, num_tokens:]
ntok_new -= num_tokens
else:
posemb_tok, posemb_grid = posemb[:, :0], posemb[0]
gs_old = int(math.sqrt(len(posemb_grid)))
if not len(gs_new): # backwards compatibility
gs_new = [int(math.sqrt(ntok_new))] * 2
assert len(gs_new) >= 2
_logger.info('Position embedding grid-size from %s to %s', [gs_old, gs_old], gs_new)
posemb_grid = posemb_grid.reshape(1, gs_old, gs_old, -1).permute(0, 3, 1, 2)
posemb_grid = F.interpolate(posemb_grid, size=gs_new, mode='bilinear')
posemb_grid = posemb_grid.permute(0, 2, 3, 1).reshape(1, gs_new[0] * gs_new[1], -1)
posemb = torch.cat([posemb_tok, posemb_grid], dim=1)
return posemb
def checkpoint_filter_fn(state_dict, model):
""" convert patch embedding weight from manual patchify + linear proj to conv"""
out_dict = {}
if 'model' in state_dict:
# For deit models
state_dict = state_dict['model']
for k, v in state_dict.items():
if 'patch_embed.proj.weight' in k and len(v.shape) < 4:
# For old models that I trained prior to conv based patchification
O, I, H, W = model.patch_embed.proj.weight.shape
v = v.reshape(O, -1, H, W)
elif k == 'pos_embed' and v.shape != model.pos_embed.shape:
# To resize pos embedding when using model at different size from pretrained weights
v = resize_pos_embed(
v, model.pos_embed, getattr(model, 'num_tokens', 1), model.patch_embed.grid_size)
out_dict[k] = v
return out_dict
def _create_vision_transformer(variant, pretrained=False, default_cfg=None, **kwargs):
default_cfg = default_cfg or default_cfgs[variant]
if kwargs.get('features_only', None):
raise RuntimeError('features_only not implemented for Vision Transformer models.')
# NOTE this extra code to support handling of repr size for in21k pretrained models
default_num_classes = default_cfg['num_classes']
num_classes = kwargs.get('num_classes', default_num_classes)
repr_size = kwargs.pop('representation_size', None)
if repr_size is not None and num_classes != default_num_classes:
# Remove representation layer if fine-tuning. This may not always be the desired action,
# but I feel better than doing nothing by default for fine-tuning. Perhaps a better interface?
_logger.warning("Removing representation layer for fine-tuning.")
repr_size = None
model = build_model_with_cfg(
VisionTransformer, variant, pretrained,
default_cfg=default_cfg,
representation_size=repr_size,
pretrained_filter_fn=checkpoint_filter_fn,
pretrained_custom_load='npz' in default_cfg['url'],
**kwargs)
return model
@register_model
def vit_tiny_patch16_224(pretrained=False, **kwargs):
""" ViT-Tiny (Vit-Ti/16)
"""
model_kwargs = dict(patch_size=16, embed_dim=192, depth=12, num_heads=3, **kwargs)
model = _create_vision_transformer('vit_tiny_patch16_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_tiny_patch16_384(pretrained=False, **kwargs):
""" ViT-Tiny (Vit-Ti/16) @ 384x384.
"""
model_kwargs = dict(patch_size=16, embed_dim=192, depth=12, num_heads=3, **kwargs)
model = _create_vision_transformer('vit_tiny_patch16_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_small_patch32_224(pretrained=False, **kwargs):
""" ViT-Small (ViT-S/32)
"""
model_kwargs = dict(patch_size=32, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer('vit_small_patch32_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_small_patch32_384(pretrained=False, **kwargs):
""" ViT-Small (ViT-S/32) at 384x384.
"""
model_kwargs = dict(patch_size=32, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer('vit_small_patch32_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_small_patch16_224(pretrained=False, **kwargs):
""" ViT-Small (ViT-S/16)
NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper
"""
model_kwargs = dict(patch_size=16, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer('vit_small_patch16_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_small_patch16_384(pretrained=False, **kwargs):
""" ViT-Small (ViT-S/16)
NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper
"""
model_kwargs = dict(patch_size=16, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer('vit_small_patch16_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_base_patch32_224(pretrained=False, **kwargs):
""" ViT-Base (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929). No pretrained weights.
"""
model_kwargs = dict(patch_size=32, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('vit_base_patch32_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_base_patch32_384(pretrained=False, **kwargs):
""" ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
"""
model_kwargs = dict(patch_size=32, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('vit_base_patch32_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_base_patch16_224(pretrained=False, **kwargs):
""" ViT-Base (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights fine-tuned from in21k @ 224x224, source https://github.com/google-research/vision_transformer.
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('vit_base_patch16_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_base_patch16_384(pretrained=False, **kwargs):
""" ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('vit_base_patch16_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_large_patch32_224(pretrained=False, **kwargs):
""" ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). No pretrained weights.
"""
model_kwargs = dict(patch_size=32, embed_dim=1024, depth=24, num_heads=16, **kwargs)
model = _create_vision_transformer('vit_large_patch32_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_large_patch32_384(pretrained=False, **kwargs):
""" ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
"""
model_kwargs = dict(patch_size=32, embed_dim=1024, depth=24, num_heads=16, **kwargs)
model = _create_vision_transformer('vit_large_patch32_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_large_patch16_224(pretrained=False, **kwargs):
""" ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights fine-tuned from in21k @ 224x224, source https://github.com/google-research/vision_transformer.
"""
model_kwargs = dict(patch_size=16, embed_dim=1024, depth=24, num_heads=16, **kwargs)
model = _create_vision_transformer('vit_large_patch16_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_large_patch16_384(pretrained=False, **kwargs):
""" ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights fine-tuned from in21k @ 384x384, source https://github.com/google-research/vision_transformer.
"""
model_kwargs = dict(patch_size=16, embed_dim=1024, depth=24, num_heads=16, **kwargs)
model = _create_vision_transformer('vit_large_patch16_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_tiny_patch16_224_in21k(pretrained=False, **kwargs):
""" ViT-Tiny (Vit-Ti/16).
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has valid 21k classifier head and no representation (pre-logits) layer
"""
model_kwargs = dict(patch_size=16, embed_dim=192, depth=12, num_heads=3, **kwargs)
model = _create_vision_transformer('vit_tiny_patch16_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_small_patch32_224_in21k(pretrained=False, **kwargs):
""" ViT-Small (ViT-S/16)
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has valid 21k classifier head and no representation (pre-logits) layer
"""
model_kwargs = dict(patch_size=32, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer('vit_small_patch32_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_small_patch16_224_in21k(pretrained=False, **kwargs):
""" ViT-Small (ViT-S/16)
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has valid 21k classifier head and no representation (pre-logits) layer
"""
model_kwargs = dict(patch_size=16, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer('vit_small_patch16_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_base_patch32_224_in21k(pretrained=False, **kwargs):
""" ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has valid 21k classifier head and no representation (pre-logits) layer
"""
model_kwargs = dict(
patch_size=32, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('vit_base_patch32_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_base_patch16_224_in21k(pretrained=False, **kwargs):
""" ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has valid 21k classifier head and no representation (pre-logits) layer
"""
model_kwargs = dict(
patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('vit_base_patch16_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_large_patch32_224_in21k(pretrained=False, **kwargs):
""" ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has a representation layer but the 21k classifier head is zero'd out in original weights
"""
model_kwargs = dict(
patch_size=32, embed_dim=1024, depth=24, num_heads=16, representation_size=1024, **kwargs)
model = _create_vision_transformer('vit_large_patch32_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_large_patch16_224_in21k(pretrained=False, **kwargs):
""" ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has valid 21k classifier head and no representation (pre-logits) layer
"""
model_kwargs = dict(
patch_size=16, embed_dim=1024, depth=24, num_heads=16, **kwargs)
model = _create_vision_transformer('vit_large_patch16_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_huge_patch14_224_in21k(pretrained=False, **kwargs):
""" ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
NOTE: this model has a representation layer but the 21k classifier head is zero'd out in original weights
"""
model_kwargs = dict(
patch_size=14, embed_dim=1280, depth=32, num_heads=16, representation_size=1280, **kwargs)
model = _create_vision_transformer('vit_huge_patch14_224_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def deit_tiny_patch16_224(pretrained=False, **kwargs):
""" DeiT-tiny model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=192, depth=12, num_heads=3, **kwargs)
model = _create_vision_transformer('deit_tiny_patch16_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def deit_small_patch16_224(pretrained=False, **kwargs):
""" DeiT-small model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer('deit_small_patch16_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def deit_base_patch16_224(pretrained=False, **kwargs):
""" DeiT base model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('deit_base_patch16_224', pretrained=pretrained, **model_kwargs)
return model
@register_model
def deit_base_patch16_384(pretrained=False, **kwargs):
""" DeiT base model @ 384x384 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer('deit_base_patch16_384', pretrained=pretrained, **model_kwargs)
return model
@register_model
def deit_tiny_distilled_patch16_224(pretrained=False, **kwargs):
""" DeiT-tiny distilled model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=192, depth=12, num_heads=3, **kwargs)
model = _create_vision_transformer(
'deit_tiny_distilled_patch16_224', pretrained=pretrained, distilled=True, **model_kwargs)
return model
@register_model
def deit_small_distilled_patch16_224(pretrained=False, **kwargs):
""" DeiT-small distilled model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=384, depth=12, num_heads=6, **kwargs)
model = _create_vision_transformer(
'deit_small_distilled_patch16_224', pretrained=pretrained, distilled=True, **model_kwargs)
return model
@register_model
def deit_base_distilled_patch16_224(pretrained=False, **kwargs):
""" DeiT-base distilled model @ 224x224 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer(
'deit_base_distilled_patch16_224', pretrained=pretrained, distilled=True, **model_kwargs)
return model
@register_model
def deit_base_distilled_patch16_384(pretrained=False, **kwargs):
""" DeiT-base distilled model @ 384x384 from paper (https://arxiv.org/abs/2012.12877).
ImageNet-1k weights from https://github.com/facebookresearch/deit.
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer(
'deit_base_distilled_patch16_384', pretrained=pretrained, distilled=True, **model_kwargs)
return model
@register_model
def vit_base_patch16_224_miil_in21k(pretrained=False, **kwargs):
""" ViT-Base (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
Weights taken from: https://github.com/Alibaba-MIIL/ImageNet21K
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, qkv_bias=False, **kwargs)
model = _create_vision_transformer('vit_base_patch16_224_miil_in21k', pretrained=pretrained, **model_kwargs)
return model
@register_model
def vit_base_patch16_224_miil(pretrained=False, **kwargs):
""" ViT-Base (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
Weights taken from: https://github.com/Alibaba-MIIL/ImageNet21K
"""
model_kwargs = dict(patch_size=16, embed_dim=768, depth=12, num_heads=12, qkv_bias=False, **kwargs)
model = _create_vision_transformer('vit_base_patch16_224_miil', pretrained=pretrained, **model_kwargs)
return model
|