Spaces:
Sleeping
Sleeping
| import math | |
| import warnings | |
| from itertools import repeat | |
| import collections.abc | |
| import torch | |
| from functools import partial | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| import torch.utils.checkpoint as checkpoint | |
| from torch import Tensor | |
| # from timm.models.layers import drop_path, to_2tuple, trunc_normal_ | |
| # from .base_backbone import BaseBackbone | |
| def drop_path(x, drop_prob: float = 0., training: bool = False, scale_by_keep: bool = True): | |
| """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. 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 = x.new_empty(shape).bernoulli_(keep_prob) | |
| if keep_prob > 0.0 and scale_by_keep: | |
| random_tensor.div_(keep_prob) | |
| return x * random_tensor | |
| def _ntuple(n): | |
| def parse(x): | |
| if isinstance(x, collections.abc.Iterable) and not isinstance(x, str): | |
| return x | |
| return tuple(repeat(x, n)) | |
| return parse | |
| to_1tuple = _ntuple(1) | |
| to_2tuple = _ntuple(2) | |
| to_3tuple = _ntuple(3) | |
| to_4tuple = _ntuple(4) | |
| to_ntuple = _ntuple | |
| def _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) | |
| # 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`. | |
| NOTE: this impl is similar to the PyTorch trunc_normal_, the bounds [a, b] are | |
| applied while sampling the normal with mean/std applied, therefore a, b args | |
| should be adjusted to match the range of mean, std args. | |
| 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) | |
| """ | |
| with torch.no_grad(): | |
| return _trunc_normal_(tensor, mean, std, a, b) | |
| 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) | |
| def extra_repr(self): | |
| return 'p={}'.format(self.drop_prob) | |
| 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.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., attn_head_dim=None,): | |
| super().__init__() | |
| self.num_heads = num_heads | |
| head_dim = dim // num_heads | |
| self.dim = dim | |
| if attn_head_dim is not None: | |
| head_dim = attn_head_dim | |
| all_head_dim = head_dim * self.num_heads | |
| self.scale = qk_scale or head_dim ** -0.5 | |
| self.qkv = nn.Linear(dim, all_head_dim * 3, bias=qkv_bias) | |
| self.attn_drop = nn.Dropout(attn_drop) | |
| self.proj = nn.Linear(all_head_dim, dim) | |
| self.proj_drop = nn.Dropout(proj_drop) | |
| def forward(self, x): | |
| B, N, C = x.shape | |
| qkv = self.qkv(x) | |
| qkv = qkv.reshape(B, N, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4) | |
| q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple) | |
| q = q * self.scale | |
| attn = (q @ k.transpose(-2, -1)) | |
| attn = attn.softmax(dim=-1) | |
| attn = self.attn_drop(attn) | |
| x = (attn @ v).transpose(1, 2).reshape(B, N, -1) | |
| 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, attn_head_dim=None | |
| ): | |
| 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, attn_head_dim=attn_head_dim | |
| ) | |
| # 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, ratio=1): | |
| 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]) * (ratio ** 2) | |
| self.patch_shape = (int(img_size[0] // patch_size[0] * ratio), int(img_size[1] // patch_size[1] * ratio)) | |
| self.origin_patch_shape = (int(img_size[0] // patch_size[0]), int(img_size[1] // patch_size[1])) | |
| 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[0] // ratio), padding=4 + 2 * (ratio//2-1)) | |
| def forward(self, x): | |
| x = self.proj(x) | |
| B, C, Hp, Wp = x.shape | |
| x = x.view(B, C, Hp * Wp).transpose(1, 2) | |
| return x, (Hp, Wp) | |
| 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(): | |
| 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 ViT(nn.Module): | |
| def __init__(self, | |
| img_size=224, patch_size=16, in_chans=3, num_classes=80, 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., hybrid_backbone=None, norm_layer=None, use_checkpoint=False, | |
| frozen_stages=-1, ratio=1, last_norm=True, | |
| patch_padding='pad', freeze_attn=False, freeze_ffn=False, | |
| ): | |
| super(ViT, self).__init__() | |
| # Protect mutable default arguments | |
| norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6) | |
| self.num_classes = num_classes | |
| self.num_features = self.embed_dim = embed_dim # num_features for consistency with other models | |
| self.frozen_stages = frozen_stages | |
| self.use_checkpoint = use_checkpoint | |
| self.patch_padding = patch_padding | |
| self.freeze_attn = freeze_attn | |
| self.freeze_ffn = freeze_ffn | |
| self.depth = depth | |
| if hybrid_backbone is not None: | |
| self.patch_embed = HybridEmbed( | |
| hybrid_backbone, img_size=img_size, in_chans=in_chans, embed_dim=embed_dim) | |
| else: | |
| self.patch_embed = PatchEmbed( | |
| img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim, ratio=ratio) | |
| num_patches = self.patch_embed.num_patches | |
| # since the pretraining model has class token | |
| self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim)) | |
| dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)] # stochastic depth decay rule | |
| self.blocks = nn.ModuleList([ | |
| 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, | |
| ) | |
| for i in range(depth)]) | |
| self.last_norm = norm_layer(embed_dim) if last_norm else nn.Identity() | |
| if self.pos_embed is not None: | |
| trunc_normal_(self.pos_embed, std=.02) | |
| self._freeze_stages() | |
| def _freeze_stages(self): | |
| """Freeze parameters.""" | |
| if self.frozen_stages >= 0: | |
| self.patch_embed.eval() | |
| for param in self.patch_embed.parameters(): | |
| param.requires_grad = False | |
| for i in range(1, self.frozen_stages + 1): | |
| m = self.blocks[i] | |
| m.eval() | |
| for param in m.parameters(): | |
| param.requires_grad = False | |
| if self.freeze_attn: | |
| for i in range(0, self.depth): | |
| m = self.blocks[i] | |
| m.attn.eval() | |
| m.norm1.eval() | |
| for param in m.attn.parameters(): | |
| param.requires_grad = False | |
| for param in m.norm1.parameters(): | |
| param.requires_grad = False | |
| if self.freeze_ffn: | |
| self.pos_embed.requires_grad = False | |
| self.patch_embed.eval() | |
| for param in self.patch_embed.parameters(): | |
| param.requires_grad = False | |
| for i in range(0, self.depth): | |
| m = self.blocks[i] | |
| m.mlp.eval() | |
| m.norm2.eval() | |
| for param in m.mlp.parameters(): | |
| param.requires_grad = False | |
| for param in m.norm2.parameters(): | |
| param.requires_grad = False | |
| def init_weights(self, pretrained=None): | |
| """Initialize the weights in backbone. | |
| Args: | |
| pretrained (str, optional): Path to pre-trained weights. | |
| Defaults to None. | |
| """ | |
| super().init_weights(pretrained, patch_padding=self.patch_padding) | |
| if pretrained is None: | |
| def _init_weights(m): | |
| 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) | |
| self.apply(_init_weights) | |
| def get_num_layers(self): | |
| return len(self.blocks) | |
| def no_weight_decay(self): | |
| return {'pos_embed', 'cls_token'} | |
| def forward(self, x): | |
| B, C, H, W = x.shape | |
| x, (Hp, Wp) = self.patch_embed(x) | |
| if self.pos_embed is not None: | |
| # fit for multiple GPU training | |
| # since the first element for pos embed (sin-cos manner) is zero, it will cause no difference | |
| x = x + self.pos_embed[:, 1:] + self.pos_embed[:, :1] | |
| for blk in self.blocks: | |
| x = blk(x) | |
| x = self.last_norm(x) | |
| x = x.permute(0, 2, 1).view(B, -1, Hp, Wp).contiguous() | |
| return x | |
| def train(self, mode=True): | |
| """Convert the model into training mode.""" | |
| super().train(mode) | |
| self._freeze_stages() | |