File size: 32,804 Bytes
18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce 499f0dc 18a9dce |
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 |
"""
original code from rwightman:
https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py
"""
from functools import partial
from collections import OrderedDict
import torch
import torch.nn as nn
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.hub
from functools import partial
# import mat
# from vision_transformer.ir50 import Backbone
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.hub
from functools import partial
import math
from timm.layers import DropPath, to_2tuple, trunc_normal_
from timm.models import register_model
from timm.models.vision_transformer import _cfg, Mlp, Block
from .ir50 import Backbone
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
"""3x3 convolution with padding"""
return nn.Conv2d(
in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=dilation,
groups=groups,
bias=False,
dilation=dilation,
)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
def drop_path(x, drop_prob: float = 0.0, training: bool = False):
"""
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
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 ... I've opted for
changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
'survival rate' as the argument.
"""
if drop_prob == 0.0 or not training:
return x
keep_prob = 1 - drop_prob
shape = (x.shape[0],) + (1,) * (
x.ndim - 1
) # work with diff dim tensors, not just 2D ConvNets
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
random_tensor.floor_() # binarize
output = x.div(keep_prob) * random_tensor
return output
class BasicBlock(nn.Module):
__constants__ = ["downsample"]
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
norm_layer = nn.BatchNorm2d
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class DropPath(nn.Module):
"""
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 PatchEmbed(nn.Module):
"""
2D Image to Patch Embedding
"""
def __init__(
self, img_size=14, patch_size=16, in_c=256, embed_dim=768, norm_layer=None
):
super().__init__()
img_size = (img_size, img_size)
patch_size = (patch_size, 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.num_patches = self.grid_size[0] * self.grid_size[1]
self.proj = nn.Conv2d(256, 768, kernel_size=1)
self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
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]})."
# print(x.shape)
# flatten: [B, C, H, W] -> [B, C, HW]
# transpose: [B, C, HW] -> [B, HW, C]
x = self.proj(x).flatten(2).transpose(1, 2)
x = self.norm(x)
return x
class Attention(nn.Module):
def __init__(
self,
dim,
in_chans, # 输入token的dim
num_heads=8,
qkv_bias=False,
qk_scale=None,
attn_drop_ratio=0.0,
proj_drop_ratio=0.0,
):
super(Attention, self).__init__()
self.num_heads = 8
self.img_chanel = in_chans + 1
head_dim = dim // num_heads
self.scale = head_dim**-0.5
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
self.attn_drop = nn.Dropout(attn_drop_ratio)
self.proj = nn.Linear(dim, dim)
self.proj_drop = nn.Dropout(proj_drop_ratio)
def forward(self, x):
x_img = x[:, : self.img_chanel, :]
# [batch_size, num_patches + 1, total_embed_dim]
B, N, C = x_img.shape
# print(C)
qkv = (
self.qkv(x_img)
.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]
# k, v = kv.unbind(0) # make torchscript happy (cannot use tensor as tuple)
# q = x_img.reshape(B, -1, 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_img = (attn @ v).transpose(1, 2).reshape(B, N, C)
x_img = self.proj(x_img)
x_img = self.proj_drop(x_img)
#
#
# # qkv(): -> [batch_size, num_patches + 1, 3 * total_embed_dim]
# # reshape: -> [batch_size, num_patches + 1, 3, num_heads, embed_dim_per_head]
# # permute: -> [3, batch_size, num_heads, num_patches + 1, embed_dim_per_head]
# qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
# # [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
# q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)
#
# # transpose: -> [batch_size, num_heads, embed_dim_per_head, num_patches + 1]
# # @: multiply -> [batch_size, num_heads, num_patches + 1, num_patches + 1]
# attn = (q @ k.transpose(-2, -1)) * self.scale
# attn = attn.softmax(dim=-1)
# attn = self.attn_drop(attn)
#
# # @: multiply -> [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
# # transpose: -> [batch_size, num_patches + 1, num_heads, embed_dim_per_head]
# # reshape: -> [batch_size, num_patches + 1, total_embed_dim]
# x = (attn @ v).transpose(1, 2).reshape(B, N, C)
# x = self.proj(x)
# x = self.proj_drop(x)
return x_img
class AttentionBlock(nn.Module):
__constants__ = ["downsample"]
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(AttentionBlock, self).__init__()
norm_layer = nn.BatchNorm2d
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
# self.cbam = CBAM(planes, 16)
self.inplanes = inplanes
self.eca_block = eca_block()
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
inplanes = self.inplanes
out = self.eca_block(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class Mlp(nn.Module):
"""
MLP as used in Vision Transformer, MLP-Mixer and related networks
"""
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 Block(nn.Module):
def __init__(
self,
dim,
in_chans,
num_heads,
mlp_ratio=4.0,
qkv_bias=False,
qk_scale=None,
drop_ratio=0.0,
attn_drop_ratio=0.0,
drop_path_ratio=0.0,
act_layer=nn.GELU,
norm_layer=nn.LayerNorm,
):
super(Block, self).__init__()
self.norm1 = norm_layer(dim)
self.img_chanel = in_chans + 1
self.conv = nn.Conv1d(self.img_chanel, self.img_chanel, 1)
self.attn = Attention(
dim,
in_chans=in_chans,
num_heads=num_heads,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
attn_drop_ratio=attn_drop_ratio,
proj_drop_ratio=drop_ratio,
)
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
self.drop_path = (
DropPath(drop_path_ratio) if drop_path_ratio > 0.0 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_ratio,
)
def forward(self, x):
# x = x + self.drop_path(self.attn(self.norm1(x)))
# x = x + self.drop_path(self.mlp(self.norm2(x)))
x_img = x
# [:, :self.img_chanel, :]
# x_lm = x[:, self.img_chanel:, :]
x_img = x_img + self.drop_path(self.attn(self.norm1(x)))
x = x_img + self.drop_path(self.mlp(self.norm2(x_img)))
#
# x_lm = x_lm + self.drop_path(self.attn_lm(self.norm3(x)))
# x_lm = x_lm + self.drop_path(self.mlp2(self.norm4(x_lm)))
# x = torch.cat((x_img, x_lm), dim=1)
# x = self.conv(x)
return x
class ClassificationHead(nn.Module):
def __init__(self, input_dim: int, target_dim: int):
super().__init__()
self.linear = torch.nn.Linear(input_dim, target_dim)
def forward(self, x):
x = x.view(x.size(0), -1)
y_hat = self.linear(x)
return y_hat
def load_pretrained_weights(model, checkpoint):
import collections
if "state_dict" in checkpoint:
state_dict = checkpoint["state_dict"]
else:
state_dict = checkpoint
model_dict = model.state_dict()
new_state_dict = collections.OrderedDict()
matched_layers, discarded_layers = [], []
for k, v in state_dict.items():
# If the pretrained state_dict was saved as nn.DataParallel,
# keys would contain "module.", which should be ignored.
if k.startswith("module."):
k = k[7:]
if k in model_dict and model_dict[k].size() == v.size():
new_state_dict[k] = v
matched_layers.append(k)
else:
discarded_layers.append(k)
# new_state_dict.requires_grad = False
model_dict.update(new_state_dict)
model.load_state_dict(model_dict)
print("load_weight", len(matched_layers))
return model
class eca_block(nn.Module):
def __init__(self, channel=128, b=1, gamma=2):
super(eca_block, self).__init__()
kernel_size = int(abs((math.log(channel, 2) + b) / gamma))
kernel_size = kernel_size if kernel_size % 2 else kernel_size + 1
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.conv = nn.Conv1d(
1, 1, kernel_size=kernel_size, padding=(kernel_size - 1) // 2, bias=False
)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
y = self.avg_pool(x)
y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)
y = self.sigmoid(y)
return x * y.expand_as(x)
#
#
# class IR20(nn.Module):
# def __init__(self, img_size_=112, num_classes=7, layers=[2, 2, 2, 2]):
# super().__init__()
# norm_layer = nn.BatchNorm2d
# self.img_size = img_size_
# self._norm_layer = norm_layer
# self.num_classes = num_classes
# self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
# self.bn1 = norm_layer(64)
# self.relu = nn.ReLU(inplace=True)
# self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
# # self.face_landback = MobileFaceNet([112, 112],136)
# # face_landback_checkpoint = torch.load('./models/pretrain/mobilefacenet_model_best.pth.tar', map_location=lambda storage, loc: storage)
# # self.face_landback.load_state_dict(face_landback_checkpoint['state_dict'])
# self.layer1 = self._make_layer(BasicBlock, 64, 64, layers[0])
# self.layer2 = self._make_layer(BasicBlock, 64, 128, layers[1], stride=2)
# self.layer3 = self._make_layer(AttentionBlock, 128, 256, layers[2], stride=2)
# self.layer4 = self._make_layer(AttentionBlock, 256, 256, layers[3], stride=1)
# self.ir_back = Backbone(50, 51, 52, 0.0, 'ir')
# self.ir_layer = nn.Linear(1024, 512)
# # ir_checkpoint = torch.load(r'F:\0815crossvit\vision_transformer\models\pretrain\Pretrained_on_MSCeleb.pth.tar',
# # map_location=lambda storage, loc: storage)
# # ir_checkpoint = ir_checkpoint['state_dict']
# # self.face_landback.load_state_dict(face_landback_checkpoint['state_dict'])
# # checkpoint = torch.load('./checkpoint/Pretrained_on_MSCeleb.pth.tar')
# # pre_trained_dict = checkpoint['state_dict']
# # IR20.load_state_dict(ir_checkpoint, strict=False)
# # self.IR = load_pretrained_weights(IR, ir_checkpoint)
#
# def _make_layer(self, block, inplanes, planes, blocks, stride=1):
# norm_layer = self._norm_layer
# downsample = None
# if stride != 1 or inplanes != planes:
# downsample = nn.Sequential(conv1x1(inplanes, planes, stride), norm_layer(planes))
# layers = []
# layers.append(block(inplanes, planes, stride, downsample))
# inplanes = planes
# for _ in range(1, blocks):
# layers.append(block(inplanes, planes))
# return nn.Sequential(*layers)
#
# def forward(self, x):
# x_ir = self.ir_back(x)
# # x_ir = self.ir_layer(x_ir)
# # print(x_ir.shape)
# # x = F.interpolate(x, size=112)
# # x = self.conv1(x)
# # x = self.bn1(x)
# # x = self.relu(x)
# # x = self.maxpool(x)
# #
# # x = self.layer1(x)
# # x = self.layer2(x)
# # x = self.layer3(x)
# # x = self.layer4(x)
# # print(x.shape)
# # print(x)
# out = x_ir
#
# return out
#
#
# class IR(nn.Module):
# def __init__(self, img_size_=112, num_classes=7):
# super().__init__()
# depth = 8
# # if type == "small":
# # depth = 4
# # if type == "base":
# # depth = 6
# # if type == "large":
# # depth = 8
#
# self.img_size = img_size_
# self.num_classes = num_classes
# self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
# # self.bn1 = norm_layer(64)
# self.relu = nn.ReLU(inplace=True)
# self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
# # self.face_landback = MobileFaceNet([112, 112],136)
# # face_landback_checkpoint = torch.load('./models/pretrain/mobilefacenet_model_best.pth.tar', map_location=lambda storage, loc: storage)
# # self.face_landback.load_state_dict(face_landback_checkpoint['state_dict'])
#
# # for param in self.face_landback.parameters():
# # param.requires_grad = False
#
# ###########################################################################333
#
# self.ir_back = IR20()
#
# # ir_checkpoint = torch.load(r'F:\0815crossvit\vision_transformer\models\pretrain\ir50.pth',
# # map_location=lambda storage, loc: storage)
# # # ir_checkpoint = ir_checkpoint["model"]
# # self.ir_back = load_pretrained_weights(self.ir_back, ir_checkpoint)
# # load_state_dict(checkpoint_model, strict=False)
# # self.ir_layer = nn.Linear(1024,512)
#
# #############################################################3
# #
# # self.pyramid_fuse = HyVisionTransformer(in_chans=49, q_chanel = 49, embed_dim=512,
# # depth=depth, num_heads=8, mlp_ratio=2.,
# # drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1)
#
# # self.se_block = SE_block(input_dim=512)
# self.head = ClassificationHead(input_dim=768, target_dim=self.num_classes)
#
# def forward(self, x):
# B_ = x.shape[0]
# # x_face = F.interpolate(x, size=112)
# # _, x_face = self.face_landback(x_face)
# # x_face = x_face.view(B_, -1, 49).transpose(1,2)
# ############### landmark x_face ([B, 49, 512])
# x_ir = self.ir_back(x)
# # print(x_ir.shape)
# # x_ir = self.ir_layer(x_ir)
# # print(x_ir.shape)
# ############### image x_ir ([B, 49, 512])
#
# # y_hat = self.pyramid_fuse(x_ir, x_face)
# # y_hat = self.se_block(y_hat)
# # y_feat = y_hat
#
# # out = self.head(x_ir)
#
# out = x_ir
# return out
class eca_block(nn.Module):
def __init__(self, channel=196, b=1, gamma=2):
super(eca_block, self).__init__()
kernel_size = int(abs((math.log(channel, 2) + b) / gamma))
kernel_size = kernel_size if kernel_size % 2 else kernel_size + 1
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.conv = nn.Conv1d(
1, 1, kernel_size=kernel_size, padding=(kernel_size - 1) // 2, bias=False
)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
y = self.avg_pool(x)
y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)
y = self.sigmoid(y)
return x * y.expand_as(x)
class SE_block(nn.Module):
def __init__(self, input_dim: int):
super().__init__()
self.linear1 = torch.nn.Linear(input_dim, input_dim)
self.relu = nn.ReLU()
self.linear2 = torch.nn.Linear(input_dim, input_dim)
self.sigmod = nn.Sigmoid()
def forward(self, x):
x1 = self.linear1(x)
x1 = self.relu(x1)
x1 = self.linear2(x1)
x1 = self.sigmod(x1)
x = x * x1
return x
class VisionTransformer(nn.Module):
def __init__(
self,
img_size=14,
patch_size=14,
in_c=147,
num_classes=8,
embed_dim=768,
depth=6,
num_heads=8,
mlp_ratio=4.0,
qkv_bias=True,
qk_scale=None,
representation_size=None,
distilled=False,
drop_ratio=0.0,
attn_drop_ratio=0.0,
drop_path_ratio=0.0,
embed_layer=PatchEmbed,
norm_layer=None,
act_layer=None,
):
"""
Args:
img_size (int, tuple): input image size
patch_size (int, tuple): patch size
in_c (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
qk_scale (float): override default qk scale of head_dim ** -0.5 if set
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_ratio (float): dropout rate
attn_drop_ratio (float): attention dropout rate
drop_path_ratio (float): stochastic depth rate
embed_layer (nn.Module): patch embedding layer
norm_layer: (nn.Module): normalization layer
"""
super(VisionTransformer, self).__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
norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
act_layer = act_layer or nn.GELU
self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
self.pos_embed = nn.Parameter(torch.zeros(1, in_c + 1, embed_dim))
self.pos_drop = nn.Dropout(p=drop_ratio)
self.se_block = SE_block(input_dim=embed_dim)
self.patch_embed = embed_layer(
img_size=img_size, patch_size=patch_size, in_c=256, embed_dim=768
)
num_patches = self.patch_embed.num_patches
self.head = ClassificationHead(input_dim=embed_dim, target_dim=self.num_classes)
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
)
# self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
self.pos_drop = nn.Dropout(p=drop_ratio)
# self.IR = IR()
self.eca_block = eca_block()
# self.ir_back = Backbone(50, 0.0, 'ir')
# ir_checkpoint = torch.load('./models/pretrain/ir50.pth', map_location=lambda storage, loc: storage)
# # ir_checkpoint = ir_checkpoint["model"]
# self.ir_back = load_pretrained_weights(self.ir_back, ir_checkpoint)
self.CON1 = nn.Conv2d(256, 768, kernel_size=1, stride=1, bias=False)
self.IRLinear1 = nn.Linear(1024, 768)
self.IRLinear2 = nn.Linear(768, 512)
self.eca_block = eca_block()
dpr = [
x.item() for x in torch.linspace(0, drop_path_ratio, depth)
] # stochastic depth decay rule
self.blocks = nn.Sequential(
*[
Block(
dim=embed_dim,
in_chans=in_c,
num_heads=num_heads,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
drop_ratio=drop_ratio,
attn_drop_ratio=attn_drop_ratio,
drop_path_ratio=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.has_logits = True
self.num_features = representation_size
self.pre_logits = nn.Sequential(
OrderedDict(
[
("fc", nn.Linear(embed_dim, representation_size)),
("act", nn.Tanh()),
]
)
)
else:
self.has_logits = False
self.pre_logits = nn.Identity()
# 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()
)
# Weight init
nn.init.trunc_normal_(self.pos_embed, std=0.02)
if self.dist_token is not None:
nn.init.trunc_normal_(self.dist_token, std=0.02)
nn.init.trunc_normal_(self.cls_token, std=0.02)
self.apply(_init_vit_weights)
def forward_features(self, x):
# [B, C, H, W] -> [B, num_patches, embed_dim]
# x = self.patch_embed(x) # [B, 196, 768]
# [1, 1, 768] -> [B, 1, 768]
# print(x.shape)
cls_token = self.cls_token.expand(x.shape[0], -1, -1)
if self.dist_token is None:
x = torch.cat((cls_token, x), dim=1) # [B, 197, 768]
else:
x = torch.cat(
(cls_token, self.dist_token.expand(x.shape[0], -1, -1), x), dim=1
)
# print(x.shape)
x = self.pos_drop(x + self.pos_embed)
x = self.blocks(x)
x = self.norm(x)
if self.dist_token is None:
return self.pre_logits(x[:, 0])
else:
return x[:, 0], x[:, 1]
def forward(self, x):
# B = x.shape[0]
# print(x)
# x = self.eca_block(x)
# x = self.IR(x)
# x = eca_block(x)
# x = self.ir_back(x)
# print(x.shape)
# x = self.CON1(x)
# x = x.view(-1, 196, 768)
#
# # print(x.shape)
# # x = self.IRLinear1(x)
# # print(x)
# x_cls = torch.mean(x, 1).view(B, 1, -1)
# x = torch.cat((x_cls, x), dim=1)
# # print(x.shape)
# x = self.pos_drop(x + self.pos_embed)
# # print(x.shape)
# x = self.blocks(x)
# # print(x)
# x = self.norm(x)
# # print(x)
# # x1 = self.IRLinear2(x)
# x1 = x[:, 0, :]
# print(x1)
# print(x1.shape)
x = self.forward_features(x)
# # print(x.shape)
# if self.head_dist is not None:
# x, x_dist = self.head(x[0]), self.head_dist(x[1])
# 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:
# print(x.shape)
x = self.se_block(x)
x1 = self.head(x)
return x1
def _init_vit_weights(m):
"""
ViT weight initialization
:param m: module
"""
if isinstance(m, nn.Linear):
nn.init.trunc_normal_(m.weight, std=0.01)
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out")
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, nn.LayerNorm):
nn.init.zeros_(m.bias)
nn.init.ones_(m.weight)
def vit_base_patch16_224(num_classes: int = 7):
"""
ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights @ 224x224, source https://github.com/google-research/vision_transformer.
weights ported from official Google JAX impl:
链接: https://pan.baidu.com/s/1zqb08naP0RPqqfSXfkB2EA 密码: eu9f
"""
model = VisionTransformer(
img_size=224,
patch_size=16,
embed_dim=768,
depth=12,
num_heads=12,
representation_size=None,
num_classes=num_classes,
)
return model
def vit_base_patch16_224_in21k(num_classes: int = 21843, has_logits: bool = True):
"""
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.
weights ported from official Google JAX impl:
https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch16_224_in21k-e5005f0a.pth
"""
model = VisionTransformer(
img_size=224,
patch_size=16,
embed_dim=768,
depth=12,
num_heads=12,
representation_size=768 if has_logits else None,
num_classes=num_classes,
)
return model
def vit_base_patch32_224(num_classes: int = 1000):
"""
ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights @ 224x224, source https://github.com/google-research/vision_transformer.
weights ported from official Google JAX impl:
链接: https://pan.baidu.com/s/1hCv0U8pQomwAtHBYc4hmZg 密码: s5hl
"""
model = VisionTransformer(
img_size=224,
patch_size=32,
embed_dim=768,
depth=12,
num_heads=12,
representation_size=None,
num_classes=num_classes,
)
return model
def vit_base_patch32_224_in21k(num_classes: int = 21843, has_logits: bool = True):
"""
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.
weights ported from official Google JAX impl:
https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch32_224_in21k-8db57226.pth
"""
model = VisionTransformer(
img_size=224,
patch_size=32,
embed_dim=768,
depth=12,
num_heads=12,
representation_size=768 if has_logits else None,
num_classes=num_classes,
)
return model
def vit_large_patch16_224(num_classes: int = 1000):
"""
ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
ImageNet-1k weights @ 224x224, source https://github.com/google-research/vision_transformer.
weights ported from official Google JAX impl:
链接: https://pan.baidu.com/s/1cxBgZJJ6qUWPSBNcE4TdRQ 密码: qqt8
"""
model = VisionTransformer(
img_size=224,
patch_size=16,
embed_dim=1024,
depth=24,
num_heads=16,
representation_size=None,
num_classes=num_classes,
)
return model
def vit_large_patch16_224_in21k(num_classes: int = 21843, has_logits: bool = True):
"""
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.
weights ported from official Google JAX impl:
https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch16_224_in21k-606da67d.pth
"""
model = VisionTransformer(
img_size=224,
patch_size=16,
embed_dim=1024,
depth=24,
num_heads=16,
representation_size=1024 if has_logits else None,
num_classes=num_classes,
)
return model
def vit_large_patch32_224_in21k(num_classes: int = 21843, has_logits: bool = True):
"""
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.
weights ported from official Google JAX impl:
https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch32_224_in21k-9046d2e7.pth
"""
model = VisionTransformer(
img_size=224,
patch_size=32,
embed_dim=1024,
depth=24,
num_heads=16,
representation_size=1024 if has_logits else None,
num_classes=num_classes,
)
return model
def vit_huge_patch14_224_in21k(num_classes: int = 21843, has_logits: bool = True):
"""
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: converted weights not currently available, too large for github release hosting.
"""
model = VisionTransformer(
img_size=224,
patch_size=14,
embed_dim=1280,
depth=32,
num_heads=16,
representation_size=1280 if has_logits else None,
num_classes=num_classes,
)
return model
|