424 lines
17 KiB
Python
424 lines
17 KiB
Python
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_roof.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
|