(ECCV 2024) HTB.py

# 论文：Restoring Images in Adverse Weather Conditions via Histogram Transformer (ECCV 2024)
# 论文地址：https://arxiv.org/pdf/2407.10172
# 微信公众号：AI缝合术
"""
2024年全网最全即插即用模块,全部免费!包含各种卷积变种、最新注意力机制、特征融合模块、上下采样模块，
适用于人工智能(AI)、深度学习、计算机视觉(CV)领域，适用于图像分类、目标检测、实例分割、语义分割、
单目标跟踪(SOT)、多目标跟踪(MOT)、红外与可见光图像融合跟踪(RGBT)、图像去噪、去雨、去雾、去模糊、超分等任务，
模块库持续更新中......
https://github.com/AIFengheshu/Plug-play-modules
"""
import numbers
import torch
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange
Conv2d = nn.Conv2d
##########################################################################
## Layer Norm
def to_2d(x):
    return rearrange(x, 'b c h w -> b (h w c)')

def to_3d(x):
#    return rearrange(x, 'b c h w -> b c (h w)')
    return rearrange(x, 'b c h w -> b (h w) c')

def to_4d(x,h,w):
#    return rearrange(x, 'b c (h w) -> b c h w',h=h,w=w)
    return rearrange(x, 'b (h w) c -> b c h w',h=h,w=w)


class BiasFree_LayerNorm(nn.Module):
    def __init__(self, normalized_shape):
        super(BiasFree_LayerNorm, self).__init__()
        if isinstance(normalized_shape, numbers.Integral):
            normalized_shape = (normalized_shape,)
        normalized_shape = torch.Size(normalized_shape)

        assert len(normalized_shape) == 1

        self.normalized_shape = normalized_shape

    def forward(self, x):
        sigma = x.var(-1, keepdim=True, unbiased=False)
        return x / torch.sqrt(sigma+1e-5) #* self.weight

class WithBias_LayerNorm(nn.Module):
    def __init__(self, normalized_shape):
        super(WithBias_LayerNorm, self).__init__()
        if isinstance(normalized_shape, numbers.Integral):
            normalized_shape = (normalized_shape,)
        normalized_shape = torch.Size(normalized_shape)

        assert len(normalized_shape) == 1

        self.normalized_shape = normalized_shape

    def forward(self, x):
        mu = x.mean(-1, keepdim=True)
        sigma = x.var(-1, keepdim=True, unbiased=False)
        return (x - mu) / torch.sqrt(sigma+1e-5) #* self.weight + self.bias


class LayerNorm(nn.Module):
    def __init__(self, dim, LayerNorm_type="WithBias"):
        super(LayerNorm, self).__init__()
        if LayerNorm_type =='BiasFree':
            self.body = BiasFree_LayerNorm(dim)
        else:
            self.body = WithBias_LayerNorm(dim)

    def forward(self, x):
        h, w = x.shape[-2:]
        return to_4d(self.body(to_3d(x)), h, w)
##########################################################################
## Dual-scale Gated Feed-Forward Network (DGFF)
class FeedForward(nn.Module):
    def __init__(self, dim, ffn_expansion_factor, bias):
        super(FeedForward, self).__init__()

        hidden_features = int(dim * ffn_expansion_factor)

        self.project_in = Conv2d(dim, hidden_features * 2, kernel_size=1, bias=bias)

        self.dwconv_5 = Conv2d(hidden_features // 4, hidden_features // 4, kernel_size=5, stride=1, padding=2,
                               groups=hidden_features // 4, bias=bias)
        self.dwconv_dilated2_1 = Conv2d(hidden_features // 4, hidden_features // 4, kernel_size=3, stride=1, padding=2,
                                        groups=hidden_features // 4, bias=bias, dilation=2)
        self.p_unshuffle = nn.PixelUnshuffle(2)
        self.p_shuffle = nn.PixelShuffle(2)

        self.project_out = Conv2d(hidden_features, dim, kernel_size=1, bias=bias)

    def forward(self, x):
        x = self.project_in(x)
        x = self.p_shuffle(x)
        x1, x2 = x.chunk(2, dim=1)
        x1 = self.dwconv_5(x1)
        x2 = self.dwconv_dilated2_1(x2)
        x = F.mish(x2) * x1
        x = self.p_unshuffle(x)
        x = self.project_out(x)
        return x

##########################################################################
##Dynamic-range Histogram Self-Attention (DHSA)
class Attention_histogram(nn.Module):
    def __init__(self, dim, num_heads=4, bias=False, ifBox=True):
        super(Attention_histogram, self).__init__()
        self.factor = num_heads
        self.ifBox = ifBox
        self.num_heads = num_heads
        self.temperature = nn.Parameter(torch.ones(num_heads, 1, 1))

        self.qkv = Conv2d(dim, dim * 5, kernel_size=1, bias=bias)
        self.qkv_dwconv = Conv2d(dim * 5, dim * 5, kernel_size=3, stride=1, padding=1, groups=dim * 5, bias=bias)
        self.project_out = Conv2d(dim, dim, kernel_size=1, bias=bias)

    def pad(self, x, factor):
        hw = x.shape[-1]
        t_pad = [0, 0] if hw % factor == 0 else [0, (hw // factor + 1) * factor - hw]
        x = F.pad(x, t_pad, 'constant', 0)
        return x, t_pad

    def unpad(self, x, t_pad):
        _, _, hw = x.shape
        return x[:, :, t_pad[0]:hw - t_pad[1]]

    def softmax_1(self, x, dim=-1):
        logit = x.exp()
        logit = logit / (logit.sum(dim, keepdim=True) + 1)
        return logit

    def normalize(self, x):
        mu = x.mean(-2, keepdim=True)
        sigma = x.var(-2, keepdim=True, unbiased=False)
        return (x - mu) / torch.sqrt(sigma + 1e-5)  # * self.weight + self.bias

    def reshape_attn(self, q, k, v, ifBox):
        b, c = q.shape[:2]
        q, t_pad = self.pad(q, self.factor)
        k, t_pad = self.pad(k, self.factor)
        v, t_pad = self.pad(v, self.factor)
        hw = q.shape[-1] // self.factor
        shape_ori = "b (head c) (factor hw)" if ifBox else "b (head c) (hw factor)"
        shape_tar = "b head (c factor) hw"
        q = rearrange(q, '{} -> {}'.format(shape_ori, shape_tar), factor=self.factor, hw=hw, head=self.num_heads)
        k = rearrange(k, '{} -> {}'.format(shape_ori, shape_tar), factor=self.factor, hw=hw, head=self.num_heads)
        v = rearrange(v, '{} -> {}'.format(shape_ori, shape_tar), factor=self.factor, hw=hw, head=self.num_heads)
        q = torch.nn.functional.normalize(q, dim=-1)
        k = torch.nn.functional.normalize(k, dim=-1)
        attn = (q @ k.transpose(-2, -1)) * self.temperature
        attn = self.softmax_1(attn, dim=-1)
        out = (attn @ v)
        out = rearrange(out, '{} -> {}'.format(shape_tar, shape_ori), factor=self.factor, hw=hw, b=b,
                        head=self.num_heads)
        out = self.unpad(out, t_pad)
        return out

    def forward(self, x):
        b, c, h, w = x.shape
        x_sort, idx_h = x[:, :c // 2].sort(-2)
        x_sort, idx_w = x_sort.sort(-1)
        x[:, :c // 2] = x_sort
        qkv = self.qkv_dwconv(self.qkv(x))
        q1, k1, q2, k2, v = qkv.chunk(5, dim=1)  # b,c,x,x

        v, idx = v.view(b, c, -1).sort(dim=-1)
        q1 = torch.gather(q1.view(b, c, -1), dim=2, index=idx)
        k1 = torch.gather(k1.view(b, c, -1), dim=2, index=idx)
        q2 = torch.gather(q2.view(b, c, -1), dim=2, index=idx)
        k2 = torch.gather(k2.view(b, c, -1), dim=2, index=idx)

        out1 = self.reshape_attn(q1, k1, v, True)
        out2 = self.reshape_attn(q2, k2, v, False)

        out1 = torch.scatter(out1, 2, idx, out1).view(b, c, h, w)
        out2 = torch.scatter(out2, 2, idx, out2).view(b, c, h, w)
        out = out1 * out2
        out = self.project_out(out)
        out_replace = out[:, :c // 2]
        out_replace = torch.scatter(out_replace, -1, idx_w, out_replace)
        out_replace = torch.scatter(out_replace, -2, idx_h, out_replace)
        out[:, :c // 2] = out_replace
        return out


##########################################################################
##Histogram Transformer Block (HTB)
class TransformerBlock(nn.Module):
    def __init__(self, dim, num_heads=4, ffn_expansion_factor=2.5, bias=False, LayerNorm_type='WithBias'):## Other option 'BiasFree'
        super(TransformerBlock, self).__init__()
        self.attn_g = Attention_histogram(dim, num_heads, bias, True)
        self.norm_g = LayerNorm(dim, LayerNorm_type)
        self.ffn = FeedForward(dim, ffn_expansion_factor, bias)

        self.norm_ff1 = LayerNorm(dim, LayerNorm_type)

    def forward(self, x):
        x = x + self.attn_g(self.norm_g(x))
        x_out = x + self.ffn(self.norm_ff1(x))

        return x_out


if __name__ == '__main__':

    input = torch.randn(1, 64, 128, 128)#输入 B C H W


    transformer_block = TransformerBlock(64)#输入C

    # 前向传播
    output = transformer_block(input)

    # 打印输入和输出的形状
    print(input.size())
    print(output.size())