import torch import torch.nn as nn from functools import partial import math from itertools import repeat # from torch._six import container_abcs import collections.abc as container_abcs #pytorch 1.9以后的版本 import warnings from taihuyuan_pv.compared_experiment.mySETR.model.helpers import load_pretrained # from .layers import DropPath, to_2tuple, trunc_normal_ def _cfg(url='', **kwargs): return { 'url': url, 'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None, 'crop_pct': .9, 'interpolation': 'bicubic', 'mean': (0.485, 0.456, 0.406), 'std': (0.229, 0.224, 0.225), 'first_conv': '', '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-weights/vit_base_p16_224-4e355ebd.pth', ), 'vit_base_patch16_384': _cfg( url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_384-83fb41ba.pth', input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0), 'vit_base_patch32_384': _cfg( url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p32_384-830016f5.pth', input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0), 'vit_large_patch16_224': _cfg(), 'vit_large_patch16_384': _cfg( url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p16_384-b3be5167.pth', input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0, ), '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), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0), 'vit_huge_patch16_224': _cfg(), 'vit_huge_patch32_384': _cfg(input_size=(3, 384, 384)), # hybrid models 'vit_small_resnet26d_224': _cfg(), 'vit_small_resnet50d_s3_224': _cfg(), 'vit_base_resnet26d_224': _cfg(), 'vit_base_resnet50d_224': _cfg(), 'deit_base_distilled_path16_384': _cfg( url='https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_384-d0272ac0.pth', input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0, checkpoint=True, ), } def to_2tuple(x): if isinstance(x, container_abcs.Iterable): return x return tuple(repeat(x, 2)) 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): if self.drop_prob == 0. or not self.training: return x keep_prob = 1 - self.drop_prob # work with diff dim tensors, not just 2D ConvNets shape = (x.shape[0],) + (1,) * (x.ndim - 1) 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 def _no_grad_trunc_normal_(tensor, mean, std, a, b): # Cut & paste from PyTorch official master until it's in a few official releases - RW # Method based on https://people.sc.fsu.edu/~jburkardt/presentations/truncated_normal.pdf def norm_cdf(x): # Computes standard normal cumulative distribution function return (1. + math.erf(x / math.sqrt(2.))) / 2. if (mean < a - 2 * std) or (mean > b + 2 * std): warnings.warn("mean is more than 2 std from [a, b] in nn.init.trunc_normal_. " "The distribution of values may be incorrect.", stacklevel=2) with torch.no_grad(): # Values are generated by using a truncated uniform distribution and # then using the inverse CDF for the normal distribution. # Get upper and lower cdf values l = norm_cdf((a - mean) / std) u = norm_cdf((b - mean) / std) # Uniformly fill tensor with values from [l, u], then translate to # [2l-1, 2u-1]. tensor.uniform_(2 * l - 1, 2 * u - 1) # Use inverse cdf transform for normal distribution to get truncated # standard normal tensor.erfinv_() # Transform to proper mean, std tensor.mul_(std * math.sqrt(2.)) tensor.add_(mean) # Clamp to ensure it's in the proper range tensor.clamp_(min=a, max=b) return tensor def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.): # type: (Tensor, float, float, float, float) -> Tensor r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distribution :math:`\mathcal{N}(\text{mean}, \text{std}^2)` with values outside :math:`[a, b]` redrawn until they are within the bounds. The method used for generating the random values works best when :math:`a \leq \text{mean} \leq b`. Args: tensor: an n-dimensional `torch.Tensor` mean: the mean of the normal distribution std: the standard deviation of the normal distribution a: the minimum cutoff value b: the maximum cutoff value Examples: >>> w = torch.empty(3, 5) >>> nn.init.trunc_normal_(w) """ return _no_grad_trunc_normal_(tensor, mean, std, a, b) class Mlp(nn.Module): 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.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 # NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights 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 q, k, v = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4) 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, 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, qk_scale=None, 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, 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 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, 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.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 = F.interpolate(x, size=2*x.shape[-1], mode='bilinear', align_corners=True) x = self.proj(x) return x class HybridEmbed(nn.Module): """ CNN Feature Map Embedding Extract feature map from CNN, flatten, project to embedding dim. """ def __init__(self, backbone, img_size=224, feature_size=None, in_chans=3, embed_dim=768): super().__init__() assert isinstance(backbone, nn.Module) img_size = to_2tuple(img_size) self.img_size = img_size self.backbone = backbone if feature_size is None: with torch.no_grad(): # FIXME this is hacky, but most reliable way of determining the exact dim of the output feature # map for all networks, the feature metadata has reliable channel and stride info, but using # stride to calc feature dim requires info about padding of each stage that isn't captured. training = backbone.training if training: backbone.eval() o = self.backbone(torch.zeros( 1, in_chans, img_size[0], img_size[1]))[-1] feature_size = o.shape[-2:] feature_dim = o.shape[1] backbone.train(training) else: feature_size = to_2tuple(feature_size) feature_dim = self.backbone.feature_info.channels()[-1] self.num_patches = feature_size[0] * feature_size[1] self.proj = nn.Linear(feature_dim, embed_dim) def forward(self, x): x = self.backbone(x)[-1] x = x.flatten(2).transpose(1, 2) x = self.proj(x) return x class VisionTransformer(nn.Module): """ Vision Transformer with support for patch or hybrid CNN input stage """ def __init__(self, model_name='vit_large_patch16_384', img_size=384, patch_size=16, in_chans=3, embed_dim=1024, depth=24, num_heads=16, num_classes=19, mlp_ratio=4., qkv_bias=True, qk_scale=None, drop_rate=0.1, attn_drop_rate=0., drop_path_rate=0., hybrid_backbone=None, norm_layer=partial(nn.LayerNorm, eps=1e-6), norm_cfg=None, pos_embed_interp=False, random_init=False, align_corners=False, **kwargs): super(VisionTransformer, self).__init__(**kwargs) self.model_name = model_name self.img_size = img_size self.patch_size = patch_size self.in_chans = in_chans self.embed_dim = embed_dim self.depth = depth self.num_heads = num_heads self.num_classes = num_classes self.mlp_ratio = mlp_ratio self.qkv_bias = qkv_bias self.qk_scale = qk_scale self.drop_rate = drop_rate self.attn_drop_rate = attn_drop_rate self.drop_path_rate = drop_path_rate self.hybrid_backbone = hybrid_backbone self.norm_layer = norm_layer self.norm_cfg = norm_cfg self.pos_embed_interp = pos_embed_interp self.random_init = random_init self.align_corners = align_corners self.num_stages = self.depth self.out_indices = tuple(range(self.num_stages)) if self.hybrid_backbone is not None: self.patch_embed = HybridEmbed( self.hybrid_backbone, img_size=self.img_size, in_chans=self.in_chans, embed_dim=self.embed_dim) else: self.patch_embed = PatchEmbed( img_size=self.img_size, patch_size=self.patch_size, in_chans=self.in_chans, embed_dim=self.embed_dim) self.num_patches = self.patch_embed.num_patches self.cls_token = nn.Parameter(torch.zeros(1, 1, self.embed_dim)) self.pos_embed = nn.Parameter(torch.zeros( 1, self.num_patches + 1, self.embed_dim)) self.pos_drop = nn.Dropout(p=self.drop_rate) dpr = [x.item() for x in torch.linspace(0, self.drop_path_rate, self.depth)] # stochastic depth decay rule self.blocks = nn.ModuleList([ Block( dim=self.embed_dim, num_heads=self.num_heads, mlp_ratio=self.mlp_ratio, qkv_bias=self.qkv_bias, qk_scale=self.qk_scale, drop=self.drop_rate, attn_drop=self.attn_drop_rate, drop_path=dpr[i], norm_layer=self.norm_layer) for i in range(self.depth)]) # NOTE as per official impl, we could have a pre-logits representation dense layer + tanh here # self.repr = nn.Linear(embed_dim, representation_size) # self.repr_act = nn.Tanh() trunc_normal_(self.pos_embed, std=.02) trunc_normal_(self.cls_token, std=.02) # self.apply(self._init_weights) def init_weights(self, pretrained=None): # nn.init.normal_(self.pos_embed, std=0.02) # nn.init.zeros_(self.cls_token) for m in self.modules(): if isinstance(m, nn.Linear): trunc_normal_(m.weight, std=.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) if not self.random_init: # self.default_cfg = default_cfgs[self.model_name] cfg = { 'pretrained_finetune': pretrained, "num_classes": self.num_classes, 'classifier': 'head', 'input_size': (3, 224, 224), 'pool_size': None, 'crop_pct': .9, 'interpolation': 'bicubic', 'first_conv': '', } if self.model_name in ['vit_small_patch16_224', 'vit_base_patch16_224']: load_pretrained(self, cfg=cfg,num_classes=self.num_classes, in_chans=self.in_chans, pos_embed_interp=self.pos_embed_interp, num_patches=self.patch_embed.num_patches, align_corners=self.align_corners, filter_fn=self._conv_filter) else: load_pretrained(self, num_classes=self.num_classes, in_chans=self.in_chans, pos_embed_interp=self.pos_embed_interp, num_patches=self.patch_embed.num_patches, align_corners=self.align_corners) else: print('Initialize weight randomly') @property def no_weight_decay(self): return {'pos_embed', 'cls_token'} def _conv_filter(self, 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 to_2D(self, x): n, hw, c = x.shape h = w = int(math.sqrt(hw)) x = x.transpose(1, 2).reshape(n, c, h, w) return x def to_1D(self, x): n, c, h, w = x.shape x = x.reshape(n, c, -1).transpose(1, 2) return x def forward(self, x): B = x.shape[0] x = self.patch_embed(x) #就是一个卷积 p16 base： 768*32*32 x = x.flatten(2).transpose(1, 2) #1024*768 # stole cls_tokens impl from Phil Wang, thanks cls_tokens = self.cls_token.expand(B, -1, -1) x = torch.cat((cls_tokens, x), dim=1) #1025*768 #加了一个cls x = x + self.pos_embed #位置编码 x = self.pos_drop(x) ##1025*768 outs = [] for i, blk in enumerate(self.blocks): #base 是12层 x = blk(x) if i in self.out_indices: outs.append(x) return tuple(outs) #把每一层block的输出都拿出来