common.py

import torch.nn as nn
import math
import torch
import torch.nn.functional as F


def default_conv(in_channels, out_channels, kernel_size, stride=1, bias=True, dilation=1):
    if dilation==1:
       return nn.Conv2d(
           in_channels, out_channels, kernel_size,
           padding=(kernel_size//2), bias=bias)
    elif dilation==2:
       return nn.Conv2d(
           in_channels, out_channels, kernel_size,
           padding=2, bias=bias, dilation=dilation)
    else:
       padding = int((kernel_size - 1) / 2) * dilation
       return nn.Conv2d(
           in_channels, out_channels, kernel_size,
           stride, padding=padding, bias=bias, dilation=dilation)


class CALayer(nn.Module):
    def __init__(self, channel, reduction=16):
        super(CALayer, self).__init__()
        # global average pooling: feature --> point
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        # feature channel downscale and upscale --> channel weight
        self.conv_du = nn.Sequential(
                nn.Conv2d(channel, channel // reduction, 1, padding=0, bias=True),
                nn.ReLU(inplace=True),
                nn.Conv2d(channel // reduction, channel, 1, padding=0, bias=True),
                nn.Sigmoid()
        )

    def forward(self, x):
        y = self.avg_pool(x)
        y = self.conv_du(y)
        return x * y


def mean_channels(F):
    assert(F.dim() == 4)
    spatial_sum = F.sum(3, keepdim=True).sum(2, keepdim=True)
    return spatial_sum / (F.size(2) * F.size(3))

def stdv_channels(F):
    assert(F.dim() == 4)
    F_mean = mean_channels(F)
    F_variance = (F - F_mean).pow(2).sum(3, keepdim=True).sum(2, keepdim=True) / (F.size(2) * F.size(3))
    return F_variance.pow(0.5)


class ResBlock(nn.Module):
    def __init__(self, conv, n_feats, kernel_size, bias=True, bn=False, act=nn.ReLU(True), res_scale=1):
        super(ResBlock, self).__init__()
        m = []
        for i in range(2):
            m.append(conv(n_feats, n_feats, kernel_size, bias=bias))
            if bn:
                m.append(nn.BatchNorm2d(n_feats))
            if i == 0:
                m.append(act)

        self.body = nn.Sequential(*m)
        self.res_scale = res_scale

    def forward(self, x):
        res = self.body(x).mul(self.res_scale)
        res += x

        return res



class ResAttentionBlock(nn.Module):
    def __init__(self, conv, n_feats, kernel_size, bias=True, bn=False, act=nn.ReLU(True), res_scale=1):
        super(ResAttentionBlock, self).__init__()
        m = []
        for i in range(2):
            m.append(conv(n_feats, n_feats, kernel_size, bias=bias))
            if bn:
                m.append(nn.BatchNorm2d(n_feats))
            if i == 0:
                m.append(act)

        m.append(CALayer(n_feats, 16))

        self.body = nn.Sequential(*m)
        self.res_scale = res_scale

    def forward(self, x):
        res = self.body(x).mul(self.res_scale)
        res += x
        return res


class Upsampler(nn.Sequential):
    def __init__(self, conv, scale, n_feats, bn=False, act=False, bias=True):
        m = []
        if (scale & (scale - 1)) == 0:    # Is scale = 2^n?
            for _ in range(int(math.log(scale, 2))):
                m.append(conv(n_feats, 4 * n_feats, 3, bias))
                m.append(nn.PixelShuffle(2))
                if bn:
                    m.append(nn.BatchNorm2d(n_feats))
                if act == 'relu':
                    m.append(nn.ReLU(True))
                elif act == 'prelu':
                    m.append(nn.PReLU(n_feats))

        elif scale == 3:
            m.append(conv(n_feats, 9 * n_feats, 3, bias))
            m.append(nn.PixelShuffle(3))
            if bn:
                m.append(nn.BatchNorm2d(n_feats))
            if act == 'relu':
                m.append(nn.ReLU(True))
            elif act == 'prelu':
                m.append(nn.PReLU(n_feats))
        else:
            raise NotImplementedError

        super(Upsampler, self).__init__(*m)


class DeformConv2d(nn.Module):
    def __init__(self, inc, outc, kernel_size=3, padding=1, stride=1, bias=None, modulation=False):
        """
        Args:
            modulation (bool, optional): If True, Modulated Defomable Convolution (Deformable ConvNets v2).
        """
        super(DeformConv2d, self).__init__()
        self.kernel_size = kernel_size
        self.padding = padding
        self.stride = stride
        self.zero_padding = nn.ZeroPad2d(padding)
        self.conv = nn.Conv2d(inc, outc, kernel_size=kernel_size, stride=kernel_size, bias=bias)

        self.p_conv = nn.Conv2d(inc, 2*kernel_size*kernel_size, kernel_size=3, padding=1, stride=stride)
        nn.init.constant_(self.p_conv.weight, 0)
        self.p_conv.register_backward_hook(self._set_lr)

        self.modulation = modulation
        if modulation:
            self.m_conv = nn.Conv2d(inc, kernel_size*kernel_size, kernel_size=3, padding=1, stride=stride)
            nn.init.constant_(self.m_conv.weight, 0)
            self.m_conv.register_backward_hook(self._set_lr)

    @staticmethod
    def _set_lr(module, grad_input, grad_output):
        grad_input = (grad_input[i] * 0.1 for i in range(len(grad_input)))
        grad_output = (grad_output[i] * 0.1 for i in range(len(grad_output)))

    def forward(self, x):
        offset = self.p_conv(x)
        if self.modulation:
            m = torch.sigmoid(self.m_conv(x))

        dtype = offset.data.type()
        ks = self.kernel_size
        N = offset.size(1) // 2

        if self.padding:
            x = self.zero_padding(x)

        # (b, 2N, h, w)
        p = self._get_p(offset, dtype)

        # (b, h, w, 2N)
        p = p.contiguous().permute(0, 2, 3, 1)
        q_lt = p.detach().floor()
        q_rb = q_lt + 1

        q_lt = torch.cat([torch.clamp(q_lt[..., :N], 0, x.size(2)-1), torch.clamp(q_lt[..., N:], 0, x.size(3)-1)], dim=-1).long()
        q_rb = torch.cat([torch.clamp(q_rb[..., :N], 0, x.size(2)-1), torch.clamp(q_rb[..., N:], 0, x.size(3)-1)], dim=-1).long()
        q_lb = torch.cat([q_lt[..., :N], q_rb[..., N:]], dim=-1)
        q_rt = torch.cat([q_rb[..., :N], q_lt[..., N:]], dim=-1)

        # clip p
        p = torch.cat([torch.clamp(p[..., :N], 0, x.size(2)-1), torch.clamp(p[..., N:], 0, x.size(3)-1)], dim=-1)

        # bilinear kernel (b, h, w, N)
        g_lt = (1 + (q_lt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_lt[..., N:].type_as(p) - p[..., N:]))
        g_rb = (1 - (q_rb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_rb[..., N:].type_as(p) - p[..., N:]))
        g_lb = (1 + (q_lb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_lb[..., N:].type_as(p) - p[..., N:]))
        g_rt = (1 - (q_rt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_rt[..., N:].type_as(p) - p[..., N:]))

        # (b, c, h, w, N)
        x_q_lt = self._get_x_q(x, q_lt, N)
        x_q_rb = self._get_x_q(x, q_rb, N)
        x_q_lb = self._get_x_q(x, q_lb, N)
        x_q_rt = self._get_x_q(x, q_rt, N)

        # (b, c, h, w, N)
        x_offset = g_lt.unsqueeze(dim=1) * x_q_lt + \
                   g_rb.unsqueeze(dim=1) * x_q_rb + \
                   g_lb.unsqueeze(dim=1) * x_q_lb + \
                   g_rt.unsqueeze(dim=1) * x_q_rt

        # modulation
        if self.modulation:
            m = m.contiguous().permute(0, 2, 3, 1)
            m = m.unsqueeze(dim=1)
            m = torch.cat([m for _ in range(x_offset.size(1))], dim=1)
            x_offset *= m

        x_offset = self._reshape_x_offset(x_offset, ks)
        out = self.conv(x_offset)

        return out

    def _get_p_n(self, N, dtype):
        p_n_x, p_n_y = torch.meshgrid(
            torch.arange(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1),
            torch.arange(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1))
        # (2N, 1)
        p_n = torch.cat([torch.flatten(p_n_x), torch.flatten(p_n_y)], 0)
        p_n = p_n.view(1, 2*N, 1, 1).type(dtype)

        return p_n

    def _get_p_0(self, h, w, N, dtype):
        p_0_x, p_0_y = torch.meshgrid(
            torch.arange(1, h*self.stride+1, self.stride),
            torch.arange(1, w*self.stride+1, self.stride))
        p_0_x = torch.flatten(p_0_x).view(1, 1, h, w).repeat(1, N, 1, 1)
        p_0_y = torch.flatten(p_0_y).view(1, 1, h, w).repeat(1, N, 1, 1)
        p_0 = torch.cat([p_0_x, p_0_y], 1).type(dtype)

        return p_0

    def _get_p(self, offset, dtype):
        N, h, w = offset.size(1)//2, offset.size(2), offset.size(3)

        # (1, 2N, 1, 1)
        p_n = self._get_p_n(N, dtype)
        # (1, 2N, h, w)
        p_0 = self._get_p_0(h, w, N, dtype)
        p = p_0 + p_n + offset
        return p

    def _get_x_q(self, x, q, N):
        b, h, w, _ = q.size()
        padded_w = x.size(3)
        c = x.size(1)
        # (b, c, h*w)
        x = x.contiguous().view(b, c, -1)

        # (b, h, w, N)
        index = q[..., :N]*padded_w + q[..., N:]  # offset_x*w + offset_y
        # (b, c, h*w*N)
        index = index.contiguous().unsqueeze(dim=1).expand(-1, c, -1, -1, -1).contiguous().view(b, c, -1)

        x_offset = x.gather(dim=-1, index=index).contiguous().view(b, c, h, w, N)

        return x_offset

    @staticmethod
    def _reshape_x_offset(x_offset, ks):
        b, c, h, w, N = x_offset.size()
        x_offset = torch.cat([x_offset[..., s:s+ks].contiguous().view(b, c, h, w*ks) for s in range(0, N, ks)], dim=-1)
        x_offset = x_offset.contiguous().view(b, c, h*ks, w*ks)

        return x_offset