module_util.py

import torch
import torch.nn as nn
import torch.nn.init as init
import torch.nn.functional as F


def print_network(net):
    num_params = 0
    for param in net.parameters():
        num_params += param.numel()
    print(net)
    print('Total number of parameters: %d' % num_params)

def initialize_weights(net_l, scale=1):
    if not isinstance(net_l, list):
        net_l = [net_l]
    for net in net_l:
        for m in net.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal_(m.weight, a=0, mode='fan_in')
                m.weight.data *= scale  # for residual block
                if m.bias is not None:
                    init.normal_(m.bias, 0.0001)
            elif isinstance(m, nn.Linear):
                init.kaiming_normal_(m.weight, a=0, mode='fan_in')
                m.weight.data *= scale
                if m.bias is not None:
                    init.normal_(m.bias, 0.0001)
            elif isinstance(m, nn.BatchNorm2d):
                try:
                    init.constant_(m.weight, 1)
                    init.normal_(m.bias, 0.0001)
                except:
                    print('This layer has no BN parameters:', m)

def make_layer(block, n_layers):
    layers = []
    for _ in range(n_layers):
        layers.append(block())
    return nn.Sequential(*layers)

class SELayer(nn.Module):
    def __init__(self, channel, reduction=16):
        super(SELayer, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
#       self.spatialpool = SpatialPool(channel)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction, bias=True),
            nn.ReLU(inplace=True),
            nn.Linear(channel // reduction, channel, bias=True),
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b,c,1)
        return y

# class ResidualBlock_noBN(nn.Module):
#     def __init__(self, nf=64, stride=1, downsample=None, reduction=4):
#         super(ResidualBlock_noBN, self).__init__()
#         self.conv1 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
#         self.relu = nn.ReLU(inplace=True)
#         self.conv2 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
#         self.se = SELayer(nf, reduction)
#         self.sigmoid = nn.Sigmoid()

#     def forward(self, x):
#         residual = x
#         out = self.relu(self.conv1(x))
#         out = self.conv2(out)
#         y = self.se(out)
#         y = self.sigmoid(y.view(y.size(0),-1))
#         y = y.view(y.size(0), y.size(1),1,1)
#         out = torch.mul(out, y)
#         out += residual
#         return out

class ResidualBlock_noBN(nn.Module):
    '''Residual block w/o BN
    ---Conv-ReLU-Conv-+-
     |________________|
    '''
    def __init__(self, nf=64):
        super(ResidualBlock_noBN, self).__init__()
        self.conv1 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
        self.conv2 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)

        # initialization
        initialize_weights([self.conv1, self.conv2], 0.1)

    def forward(self, x):
        identity = x
        out = F.relu(self.conv1(x), inplace=True)
        out = self.conv2(out)
        return identity + out


def flow_warp(x, flow, interp_mode='bilinear', padding_mode='zeros'):
    """Warp an image or feature map with optical flow
    Args:
        x (Tensor): size (N, C, H, W)
        flow (Tensor): size (N, H, W, 2), normal value
        interp_mode (str): 'nearest' or 'bilinear'
        padding_mode (str): 'zeros' or 'border' or 'reflection'

    Returns:
        Tensor: warped image or feature map
    """
    assert x.size()[-2:] == flow.size()[1:3]
    B, C, H, W = x.size()
    # mesh grid
    grid_y, grid_x = torch.meshgrid(torch.arange(0, H), torch.arange(0, W))
    grid = torch.stack((grid_x, grid_y), 2).float()  # W(x), H(y), 2
    grid.requires_grad = False
    grid = grid.type_as(x)
    vgrid = grid + flow
    # scale grid to [-1,1]
    vgrid_x = 2.0 * vgrid[:, :, :, 0] / max(W - 1, 1) - 1.0
    vgrid_y = 2.0 * vgrid[:, :, :, 1] / max(H - 1, 1) - 1.0
    vgrid_scaled = torch.stack((vgrid_x, vgrid_y), dim=3)
    output = F.grid_sample(x, vgrid_scaled, mode=interp_mode, padding_mode=padding_mode)
    return output