| import torch
|
| import torch.nn as nn
|
| from torchvision import models
|
| import torch.nn.functional as F
|
| import numpy as np
|
|
|
|
|
| class sobel_net(nn.Module):
|
| def __init__(self):
|
| super().__init__()
|
| self.conv_opx = nn.Conv2d(1, 1, 3, bias=False)
|
| self.conv_opy = nn.Conv2d(1, 1, 3, bias=False)
|
| sobel_kernelx = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]], dtype='float32').reshape((1, 1, 3, 3))
|
| sobel_kernely = np.array([[-1, -2, -1], [0, 0, 0], [1, 2, 1]], dtype='float32').reshape((1, 1, 3, 3))
|
| self.conv_opx.weight.data = torch.from_numpy(sobel_kernelx)
|
| self.conv_opy.weight.data = torch.from_numpy(sobel_kernely)
|
|
|
| for p in self.parameters():
|
| p.requires_grad = False
|
|
|
| def forward(self, im):
|
| x = (0.299 * im[:, 0, :, :] + 0.587 * im[:, 1, :, :] + 0.114 * im[:, 2, :, :]).unsqueeze(1)
|
| gradx = self.conv_opx(x)
|
| grady = self.conv_opy(x)
|
|
|
| x = (gradx ** 2 + grady ** 2) ** 0.5
|
| x = (x - x.min()) / (x.max() - x.min())
|
| x = F.pad(x, (1, 1, 1, 1))
|
|
|
| x = torch.cat([im, x], dim=1)
|
| return x
|
|
|
|
|
| class REBNCONV(nn.Module):
|
| def __init__(self, in_ch=3, out_ch=3, dirate=1):
|
| super(REBNCONV, self).__init__()
|
|
|
| self.conv_s1 = nn.Conv2d(in_ch, out_ch, 3, padding=1 * dirate, dilation=1 * dirate)
|
| self.bn_s1 = nn.BatchNorm2d(out_ch)
|
| self.relu_s1 = nn.ReLU(inplace=True)
|
|
|
| def forward(self, x):
|
| hx = x
|
| xout = self.relu_s1(self.bn_s1(self.conv_s1(hx)))
|
|
|
| return xout
|
|
|
|
|
|
|
| def _upsample_like(src, tar):
|
| src = F.interpolate(src, size=tar.shape[2:], mode='bilinear', align_corners=False)
|
| return src
|
|
|
|
|
|
|
| class RSU7(nn.Module):
|
|
|
| def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
| super(RSU7, self).__init__()
|
|
|
| self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
|
|
| self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
| self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool5 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
|
|
| self.rebnconv7 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
|
|
| self.rebnconv6d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
|
|
|
| def forward(self, x):
|
| hx = x
|
| hxin = self.rebnconvin(hx)
|
|
|
| hx1 = self.rebnconv1(hxin)
|
| hx = self.pool1(hx1)
|
|
|
| hx2 = self.rebnconv2(hx)
|
| hx = self.pool2(hx2)
|
|
|
| hx3 = self.rebnconv3(hx)
|
| hx = self.pool3(hx3)
|
|
|
| hx4 = self.rebnconv4(hx)
|
| hx = self.pool4(hx4)
|
|
|
| hx5 = self.rebnconv5(hx)
|
| hx = self.pool5(hx5)
|
|
|
| hx6 = self.rebnconv6(hx)
|
|
|
| hx7 = self.rebnconv7(hx6)
|
|
|
| hx6d = self.rebnconv6d(torch.cat((hx7, hx6), 1))
|
| hx6dup = _upsample_like(hx6d, hx5)
|
|
|
| hx5d = self.rebnconv5d(torch.cat((hx6dup, hx5), 1))
|
| hx5dup = _upsample_like(hx5d, hx4)
|
|
|
| hx4d = self.rebnconv4d(torch.cat((hx5dup, hx4), 1))
|
| hx4dup = _upsample_like(hx4d, hx3)
|
|
|
| hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
|
| hx3dup = _upsample_like(hx3d, hx2)
|
|
|
| hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
| hx2dup = _upsample_like(hx2d, hx1)
|
|
|
| hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
|
|
| return hx1d + hxin
|
|
|
|
|
|
|
| class RSU6(nn.Module):
|
|
|
| def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
| super(RSU6, self).__init__()
|
|
|
| self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
|
|
| self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
| self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
|
|
| self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
|
|
| self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
|
|
|
| def forward(self, x):
|
| hx = x
|
|
|
| hxin = self.rebnconvin(hx)
|
|
|
| hx1 = self.rebnconv1(hxin)
|
| hx = self.pool1(hx1)
|
|
|
| hx2 = self.rebnconv2(hx)
|
| hx = self.pool2(hx2)
|
|
|
| hx3 = self.rebnconv3(hx)
|
| hx = self.pool3(hx3)
|
|
|
| hx4 = self.rebnconv4(hx)
|
| hx = self.pool4(hx4)
|
|
|
| hx5 = self.rebnconv5(hx)
|
|
|
| hx6 = self.rebnconv6(hx5)
|
|
|
| hx5d = self.rebnconv5d(torch.cat((hx6, hx5), 1))
|
| hx5dup = _upsample_like(hx5d, hx4)
|
|
|
| hx4d = self.rebnconv4d(torch.cat((hx5dup, hx4), 1))
|
| hx4dup = _upsample_like(hx4d, hx3)
|
|
|
| hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
|
| hx3dup = _upsample_like(hx3d, hx2)
|
|
|
| hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
| hx2dup = _upsample_like(hx2d, hx1)
|
|
|
| hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
|
|
| return hx1d + hxin
|
|
|
|
|
|
|
| class RSU5(nn.Module):
|
|
|
| def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
| super(RSU5, self).__init__()
|
|
|
| self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
|
|
| self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
| self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
|
|
| self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
|
|
| self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
|
|
|
| def forward(self, x):
|
| hx = x
|
|
|
| hxin = self.rebnconvin(hx)
|
|
|
| hx1 = self.rebnconv1(hxin)
|
| hx = self.pool1(hx1)
|
|
|
| hx2 = self.rebnconv2(hx)
|
| hx = self.pool2(hx2)
|
|
|
| hx3 = self.rebnconv3(hx)
|
| hx = self.pool3(hx3)
|
|
|
| hx4 = self.rebnconv4(hx)
|
|
|
| hx5 = self.rebnconv5(hx4)
|
|
|
| hx4d = self.rebnconv4d(torch.cat((hx5, hx4), 1))
|
| hx4dup = _upsample_like(hx4d, hx3)
|
|
|
| hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
|
| hx3dup = _upsample_like(hx3d, hx2)
|
|
|
| hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
| hx2dup = _upsample_like(hx2d, hx1)
|
|
|
| hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
|
|
| return hx1d + hxin
|
|
|
|
|
|
|
| class RSU4(nn.Module):
|
|
|
| def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
| super(RSU4, self).__init__()
|
|
|
| self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
|
|
| self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
| self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
| self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
|
|
| self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
|
|
| self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
|
| self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
|
|
|
| def forward(self, x):
|
| hx = x
|
|
|
| hxin = self.rebnconvin(hx)
|
|
|
| hx1 = self.rebnconv1(hxin)
|
| hx = self.pool1(hx1)
|
|
|
| hx2 = self.rebnconv2(hx)
|
| hx = self.pool2(hx2)
|
|
|
| hx3 = self.rebnconv3(hx)
|
|
|
| hx4 = self.rebnconv4(hx3)
|
|
|
| hx3d = self.rebnconv3d(torch.cat((hx4, hx3), 1))
|
| hx3dup = _upsample_like(hx3d, hx2)
|
|
|
| hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
| hx2dup = _upsample_like(hx2d, hx1)
|
|
|
| hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
|
|
| return hx1d + hxin
|
|
|
|
|
|
|
| class RSU4F(nn.Module):
|
|
|
| def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
| super(RSU4F, self).__init__()
|
|
|
| self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
|
|
| self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
| self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
| self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=4)
|
|
|
| self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=8)
|
|
|
| self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=4)
|
| self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=2)
|
| self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
|
|
|
| def forward(self, x):
|
| hx = x
|
|
|
| hxin = self.rebnconvin(hx)
|
|
|
| hx1 = self.rebnconv1(hxin)
|
| hx2 = self.rebnconv2(hx1)
|
| hx3 = self.rebnconv3(hx2)
|
|
|
| hx4 = self.rebnconv4(hx3)
|
|
|
| hx3d = self.rebnconv3d(torch.cat((hx4, hx3), 1))
|
| hx2d = self.rebnconv2d(torch.cat((hx3d, hx2), 1))
|
| hx1d = self.rebnconv1d(torch.cat((hx2d, hx1), 1))
|
|
|
| return hx1d + hxin
|
|
|
|
|
|
|
| class U2NET(nn.Module):
|
| def __init__(self, in_ch=3, out_ch=1):
|
| super(U2NET, self).__init__()
|
| self.edge = sobel_net()
|
|
|
| self.stage1 = RSU7(in_ch, 32, 64)
|
| self.pool12 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage2 = RSU6(64, 32, 128)
|
| self.pool23 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage3 = RSU5(128, 64, 256)
|
| self.pool34 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage4 = RSU4(256, 128, 512)
|
| self.pool45 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage5 = RSU4F(512, 256, 512)
|
| self.pool56 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage6 = RSU4F(512, 256, 512)
|
|
|
|
|
| self.stage5d = RSU4F(1024, 256, 512)
|
| self.stage4d = RSU4(1024, 128, 256)
|
| self.stage3d = RSU5(512, 64, 128)
|
| self.stage2d = RSU6(256, 32, 64)
|
| self.stage1d = RSU7(128, 16, 64)
|
|
|
| self.side1 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side2 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side3 = nn.Conv2d(128, out_ch, 3, padding=1)
|
| self.side4 = nn.Conv2d(256, out_ch, 3, padding=1)
|
| self.side5 = nn.Conv2d(512, out_ch, 3, padding=1)
|
| self.side6 = nn.Conv2d(512, out_ch, 3, padding=1)
|
|
|
| self.outconv = nn.Conv2d(6, out_ch, 1)
|
|
|
| def forward(self, x):
|
| x = self.edge(x)
|
| hx = x
|
|
|
|
|
| hx1 = self.stage1(hx)
|
| hx = self.pool12(hx1)
|
|
|
|
|
| hx2 = self.stage2(hx)
|
| hx = self.pool23(hx2)
|
|
|
|
|
| hx3 = self.stage3(hx)
|
| hx = self.pool34(hx3)
|
|
|
|
|
| hx4 = self.stage4(hx)
|
| hx = self.pool45(hx4)
|
|
|
|
|
| hx5 = self.stage5(hx)
|
| hx = self.pool56(hx5)
|
|
|
|
|
| hx6 = self.stage6(hx)
|
| hx6up = _upsample_like(hx6, hx5)
|
|
|
|
|
| hx5d = self.stage5d(torch.cat((hx6up, hx5), 1))
|
| hx5dup = _upsample_like(hx5d, hx4)
|
|
|
| hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1))
|
| hx4dup = _upsample_like(hx4d, hx3)
|
|
|
| hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1))
|
| hx3dup = _upsample_like(hx3d, hx2)
|
|
|
| hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1))
|
| hx2dup = _upsample_like(hx2d, hx1)
|
|
|
| hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1))
|
|
|
|
|
| d1 = self.side1(hx1d)
|
|
|
| d2 = self.side2(hx2d)
|
| d2 = _upsample_like(d2, d1)
|
|
|
| d3 = self.side3(hx3d)
|
| d3 = _upsample_like(d3, d1)
|
|
|
| d4 = self.side4(hx4d)
|
| d4 = _upsample_like(d4, d1)
|
|
|
| d5 = self.side5(hx5d)
|
| d5 = _upsample_like(d5, d1)
|
|
|
| d6 = self.side6(hx6)
|
| d6 = _upsample_like(d6, d1)
|
|
|
| d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1))
|
|
|
| return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(
|
| d4), torch.sigmoid(d5), torch.sigmoid(d6)
|
|
|
|
|
| class U2NETP(nn.Module):
|
|
|
| def __init__(self, in_ch=3, out_ch=1):
|
| super(U2NETP, self).__init__()
|
|
|
| self.stage1 = RSU7(in_ch, 16, 64)
|
| self.pool12 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage2 = RSU6(64, 16, 64)
|
| self.pool23 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage3 = RSU5(64, 16, 64)
|
| self.pool34 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage4 = RSU4(64, 16, 64)
|
| self.pool45 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage5 = RSU4F(64, 16, 64)
|
| self.pool56 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage6 = RSU4F(64, 16, 64)
|
|
|
|
|
| self.stage5d = RSU4F(128, 16, 64)
|
| self.stage4d = RSU4(128, 16, 64)
|
| self.stage3d = RSU5(128, 16, 64)
|
| self.stage2d = RSU6(128, 16, 64)
|
| self.stage1d = RSU7(128, 16, 64)
|
|
|
| self.side1 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side2 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side3 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side4 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side5 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side6 = nn.Conv2d(64, out_ch, 3, padding=1)
|
|
|
| self.outconv = nn.Conv2d(6, out_ch, 1)
|
|
|
| def forward(self, x):
|
| hx = x
|
|
|
|
|
| hx1 = self.stage1(hx)
|
| hx = self.pool12(hx1)
|
|
|
|
|
| hx2 = self.stage2(hx)
|
| hx = self.pool23(hx2)
|
|
|
|
|
| hx3 = self.stage3(hx)
|
| hx = self.pool34(hx3)
|
|
|
|
|
| hx4 = self.stage4(hx)
|
| hx = self.pool45(hx4)
|
|
|
|
|
| hx5 = self.stage5(hx)
|
| hx = self.pool56(hx5)
|
|
|
|
|
| hx6 = self.stage6(hx)
|
| hx6up = _upsample_like(hx6, hx5)
|
|
|
|
|
| hx5d = self.stage5d(torch.cat((hx6up, hx5), 1))
|
| hx5dup = _upsample_like(hx5d, hx4)
|
|
|
| hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1))
|
| hx4dup = _upsample_like(hx4d, hx3)
|
|
|
| hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1))
|
| hx3dup = _upsample_like(hx3d, hx2)
|
|
|
| hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1))
|
| hx2dup = _upsample_like(hx2d, hx1)
|
|
|
| hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1))
|
|
|
|
|
| d1 = self.side1(hx1d)
|
|
|
| d2 = self.side2(hx2d)
|
| d2 = _upsample_like(d2, d1)
|
|
|
| d3 = self.side3(hx3d)
|
| d3 = _upsample_like(d3, d1)
|
|
|
| d4 = self.side4(hx4d)
|
| d4 = _upsample_like(d4, d1)
|
|
|
| d5 = self.side5(hx5d)
|
| d5 = _upsample_like(d5, d1)
|
|
|
| d6 = self.side6(hx6)
|
| d6 = _upsample_like(d6, d1)
|
|
|
| d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1))
|
|
|
| return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(
|
| d4), torch.sigmoid(d5), torch.sigmoid(d6)
|
|
|
| class ClassifierHead(nn.Module):
|
| def __init__(self, in_channels=64, channels=[512, 128], mode='avg_pool'):
|
| super(ClassifierHead, self).__init__()
|
| self.linears = nn.ModuleList()
|
| for i, c in enumerate(channels):
|
| if i == 0:
|
| self.linears.append(nn.Linear(in_channels, c))
|
| else:
|
| self.linears.append(nn.Linear(channels[i-1], c))
|
| self.cls = nn.Linear(channels[-1], 1)
|
| self.available_modes = ['avg_pool', 'max_pool', 'flatten']
|
| if mode not in self.available_modes:
|
| raise ValueError("Mode must be one of: {}".format(self.available_modes))
|
| self.mode = mode
|
|
|
| def forward(self, x):
|
| if self.mode == 'avg_pool':
|
| x = F.adaptive_avg_pool2d(x, (1, 1))
|
| elif self.mode == 'max_pool':
|
| x = F.adaptive_max_pool2d(x, (1, 1))
|
| elif self.mode == 'flatten':
|
| x = torch.flatten(x, 1)
|
| else:
|
| raise ValueError("Unsupported mode: {}".format(self.mode))
|
|
|
| x = x.view(x.size(0), -1)
|
| for linear in self.linears:
|
| x = F.relu(linear(x))
|
| x = self.cls(x)
|
| return x
|
|
|
| class U2NETP_v2(nn.Module):
|
|
|
| def __init__(self, in_ch=3, out_ch=1):
|
| super(U2NETP_v2, self).__init__()
|
|
|
| self.stage1 = RSU7(in_ch, 16, 64)
|
| self.pool12 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage2 = RSU6(64, 16, 64)
|
| self.pool23 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage3 = RSU5(64, 16, 64)
|
| self.pool34 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage4 = RSU4(64, 16, 64)
|
| self.pool45 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage5 = RSU4F(64, 16, 64)
|
| self.pool56 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
|
|
| self.stage6 = RSU4F(64, 16, 64)
|
|
|
|
|
| self.stage5d = RSU4F(128, 16, 64)
|
| self.stage4d = RSU4(128, 16, 64)
|
| self.stage3d = RSU5(128, 16, 64)
|
| self.stage2d = RSU6(128, 16, 64)
|
| self.stage1d = RSU7(128, 16, 64)
|
|
|
| self.side1 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side2 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side3 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side4 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side5 = nn.Conv2d(64, out_ch, 3, padding=1)
|
| self.side6 = nn.Conv2d(64, out_ch, 3, padding=1)
|
|
|
| self.outconv = nn.Conv2d(out_ch * 6, out_ch, 1)
|
|
|
| def forward(self, x):
|
| hx = x
|
|
|
|
|
| hx1 = self.stage1(hx)
|
| hx = self.pool12(hx1)
|
|
|
|
|
| hx2 = self.stage2(hx)
|
| hx = self.pool23(hx2)
|
|
|
|
|
| hx3 = self.stage3(hx)
|
| hx = self.pool34(hx3)
|
|
|
|
|
| hx4 = self.stage4(hx)
|
| hx = self.pool45(hx4)
|
|
|
|
|
| hx5 = self.stage5(hx)
|
| hx = self.pool56(hx5)
|
|
|
|
|
| hx6 = self.stage6(hx)
|
| hx6up = _upsample_like(hx6, hx5)
|
|
|
|
|
| hx5d = self.stage5d(torch.cat((hx6up, hx5), 1))
|
| hx5dup = _upsample_like(hx5d, hx4)
|
|
|
| hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1))
|
| hx4dup = _upsample_like(hx4d, hx3)
|
|
|
| hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1))
|
| hx3dup = _upsample_like(hx3d, hx2)
|
|
|
| hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1))
|
| hx2dup = _upsample_like(hx2d, hx1)
|
|
|
| hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1))
|
|
|
|
|
| d1 = self.side1(hx1d)
|
|
|
| d2 = self.side2(hx2d)
|
| d2 = _upsample_like(d2, d1)
|
|
|
| d3 = self.side3(hx3d)
|
| d3 = _upsample_like(d3, d1)
|
|
|
| d4 = self.side4(hx4d)
|
| d4 = _upsample_like(d4, d1)
|
|
|
| d5 = self.side5(hx5d)
|
| d5 = _upsample_like(d5, d1)
|
|
|
| d6 = self.side6(hx6)
|
| d6 = _upsample_like(d6, d1)
|
|
|
| d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1))
|
|
|
| return d0, hx6 |
