Spaces:
Running on Zero
Running on Zero
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| from refnet.util import default | |
| """ | |
| Source code: https://github.com/SkyTNT/anime-segmentation?tab=readme-ov-file | |
| Author: SkyTNT | |
| """ | |
| class REBNCONV(nn.Module): | |
| def __init__(self, in_ch=3, out_ch=3, dirate=1, stride=1): | |
| super(REBNCONV, self).__init__() | |
| self.conv_s1 = nn.Conv2d( | |
| in_ch, out_ch, 3, padding=1 * dirate, dilation=1 * dirate, stride=stride | |
| ) | |
| 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 | |
| ## upsample tensor 'src' to have the same spatial size with tensor 'tar' | |
| def _upsample_like(src, tar): | |
| src = F.interpolate(src, size=tar.shape[2:], mode="bilinear", align_corners=False) | |
| return src | |
| ### RSU-7 ### | |
| class RSU7(nn.Module): | |
| def __init__(self, in_ch=3, mid_ch=12, out_ch=3, img_size=512): | |
| super(RSU7, self).__init__() | |
| self.in_ch = in_ch | |
| self.mid_ch = mid_ch | |
| self.out_ch = out_ch | |
| self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) ## 1 -> 1/2 | |
| 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): | |
| b, c, h, w = x.shape | |
| 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 | |
| ### RSU-6 ### | |
| 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 | |
| ### RSU-5 ### | |
| 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 | |
| ### RSU-4 ### | |
| 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 | |
| ### RSU-4F ### | |
| 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 myrebnconv(nn.Module): | |
| def __init__( | |
| self, | |
| in_ch=3, | |
| out_ch=1, | |
| kernel_size=3, | |
| stride=1, | |
| padding=1, | |
| dilation=1, | |
| groups=1, | |
| ): | |
| super(myrebnconv, self).__init__() | |
| self.conv = nn.Conv2d( | |
| in_ch, | |
| out_ch, | |
| kernel_size=kernel_size, | |
| stride=stride, | |
| padding=padding, | |
| dilation=dilation, | |
| groups=groups, | |
| ) | |
| self.bn = nn.BatchNorm2d(out_ch) | |
| self.rl = nn.ReLU(inplace=True) | |
| def forward(self, x): | |
| return self.rl(self.bn(self.conv(x))) | |
| class ISNetDIS(nn.Module): | |
| def __init__(self, in_ch=3, out_ch=1): | |
| super(ISNetDIS, self).__init__() | |
| self.conv_in = nn.Conv2d(in_ch, 64, 3, stride=2, padding=1) | |
| self.pool_in = nn.MaxPool2d(2, stride=2, ceil_mode=True) | |
| self.stage1 = RSU7(64, 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) | |
| # decoder | |
| 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) | |
| def forward(self, x): | |
| hx = x | |
| hxin = self.conv_in(hx) | |
| hx = self.pool_in(hxin) | |
| # stage 1 | |
| hx1 = self.stage1(hxin) | |
| hx = self.pool12(hx1) | |
| # stage 2 | |
| hx2 = self.stage2(hx) | |
| hx = self.pool23(hx2) | |
| # stage 3 | |
| hx3 = self.stage3(hx) | |
| hx = self.pool34(hx3) | |
| # stage 4 | |
| hx4 = self.stage4(hx) | |
| hx = self.pool45(hx4) | |
| # stage 5 | |
| hx5 = self.stage5(hx) | |
| hx = self.pool56(hx5) | |
| # stage 6 | |
| hx6 = self.stage6(hx) | |
| hx6up = _upsample_like(hx6, hx5) | |
| # -------------------- decoder -------------------- | |
| 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)) | |
| # side output | |
| d1 = self.side1(hx1d) | |
| d1 = _upsample_like(d1, x) | |
| # d2 = self.side2(hx2d) | |
| # d2 = _upsample_like(d2, x) | |
| # | |
| # d3 = self.side3(hx3d) | |
| # d3 = _upsample_like(d3, x) | |
| # | |
| # d4 = self.side4(hx4d) | |
| # d4 = _upsample_like(d4, x) | |
| # | |
| # d5 = self.side5(hx5d) | |
| # d5 = _upsample_like(d5, x) | |
| # | |
| # d6 = self.side6(hx6) | |
| # d6 = _upsample_like(d6, x) | |
| # d0 = self.outconv(torch.cat((d1,d2,d3,d4,d5,d6),1)) | |
| # | |
| # return [torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(d4), torch.sigmoid(d5), torch.sigmoid(d6)], [hx1d, hx2d, hx3d, hx4d, hx5d, hx6] | |
| # return [d1, d2, d3, d4, d5, d6], [hx1d, hx2d, hx3d, hx4d, hx5d, hx6] | |
| return torch.sigmoid(d1) | |
| def proceed(self, x: torch.Tensor, th=None, tw=None, s=1024, dilate=False, crop=True, *args, **kwargs): | |
| b, c, h, w = x.shape | |
| if crop: | |
| th, tw = default(th, h), default(tw, w) | |
| scale = s / max(h, w) | |
| h, w = int(h * scale), int(w * scale) | |
| canvas = -torch.ones((b, c, s, s), dtype=x.dtype, device=x.device) | |
| ph, pw = (s - h) // 2, (s - w) // 2 | |
| x = F.interpolate(x, scale_factor=scale, mode="bicubic") | |
| canvas[:, :, ph: ph+h, pw: pw+w] = x | |
| canvas = 1 - (canvas + 1.) / 2. | |
| mask = self(canvas)[:, :, ph: ph+h, pw: pw+w] | |
| else: | |
| x = F.interpolate(x, size=(s, s), mode="bicubic") | |
| mask = self(x) | |
| mask = F.interpolate(mask, (th, tw), mode="bicubic").clamp(0, 1) | |
| if dilate: | |
| mask = F.max_pool2d(mask, kernel_size=21, stride=1, padding=10) | |
| # mask = mask_expansion(mask, 32, 20) | |
| return mask |