import torch import torch.nn as nn from backbones_unet.model.unet import Unet import torch.nn.functional as F from utils import * __all__ = ['UNext'] from timm.models.layers import DropPath, to_2tuple, trunc_normal_ import math class UNet(nn.Module): def __init__(self, in_channels = 3, out_channels = 1, init_features = 32, pretrained=True , back_bone=None): super().__init__() if back_bone is None: self.model = torch.hub.load( 'mateuszbuda/brain-segmentation-pytorch', 'unet', in_channels=in_channels, out_channels=out_channels, init_features=init_features, pretrained=pretrained ) else: self.model = UNet( in_channels= in_channels, out_channels= out_channels, backbone=back_bone ) self.soft = nn.Softmax(dim =1) def forward(self, x, text_dummy): return self.soft(self.model(x)),0 def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d: """1x1 convolution""" return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, bias=False) class shiftmlp(nn.Module): def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0., shift_size=5): super().__init__() out_features = out_features or in_features hidden_features = hidden_features or in_features self.dim = in_features self.fc1 = nn.Linear(in_features, hidden_features) self.dwconv = DWConv(hidden_features) self.act = act_layer() self.fc2 = nn.Linear(hidden_features, out_features) self.drop = nn.Dropout(drop) self.shift_size = shift_size self.pad = shift_size // 2 self.apply(self._init_weights) def _init_weights(self, m): if isinstance(m, nn.Linear): trunc_normal_(m.weight, std=.02) if isinstance(m, nn.Linear) and m.bias is not None: nn.init.constant_(m.bias, 0) elif isinstance(m, nn.LayerNorm): nn.init.constant_(m.bias, 0) nn.init.constant_(m.weight, 1.0) elif isinstance(m, nn.Conv2d): fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels fan_out //= m.groups m.weight.data.normal_(0, math.sqrt(2.0 / fan_out)) if m.bias is not None: m.bias.data.zero_() def forward(self, x, H, W): # pdb.set_trace() B, N, C = x.shape xn = x.transpose(1, 2).view(B, C, H, W).contiguous() xn = F.pad(xn, (self.pad, self.pad, self.pad, self.pad) , "constant", 0) xs = torch.chunk(xn, self.shift_size, 1) x_shift = [torch.roll(x_c, shift, 2) for x_c, shift in zip(xs, range(-self.pad, self.pad+1))] x_cat = torch.cat(x_shift, 1) x_cat = torch.narrow(x_cat, 2, self.pad, H) x_s = torch.narrow(x_cat, 3, self.pad, W) x_s = x_s.reshape(B,C,H*W).contiguous() x_shift_r = x_s.transpose(1,2) x = self.fc1(x_shift_r) x = self.dwconv(x, H, W) x = self.act(x) x = self.drop(x) xn = x.transpose(1, 2).view(B, C, H, W).contiguous() xn = F.pad(xn, (self.pad, self.pad, self.pad, self.pad) , "constant", 0) xs = torch.chunk(xn, self.shift_size, 1) x_shift = [torch.roll(x_c, shift, 3) for x_c, shift in zip(xs, range(-self.pad, self.pad+1))] x_cat = torch.cat(x_shift, 1) x_cat = torch.narrow(x_cat, 2, self.pad, H) x_s = torch.narrow(x_cat, 3, self.pad, W) x_s = x_s.reshape(B,C,H*W).contiguous() x_shift_c = x_s.transpose(1,2) x = self.fc2(x_shift_c) x = self.drop(x) return x class shiftedBlock(nn.Module): def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1): super().__init__() self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity() self.norm2 = norm_layer(dim) mlp_hidden_dim = int(dim * mlp_ratio) self.mlp = shiftmlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop) self.apply(self._init_weights) def _init_weights(self, m): if isinstance(m, nn.Linear): trunc_normal_(m.weight, std=.02) if isinstance(m, nn.Linear) and m.bias is not None: nn.init.constant_(m.bias, 0) elif isinstance(m, nn.LayerNorm): nn.init.constant_(m.bias, 0) nn.init.constant_(m.weight, 1.0) elif isinstance(m, nn.Conv2d): fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels fan_out //= m.groups m.weight.data.normal_(0, math.sqrt(2.0 / fan_out)) if m.bias is not None: m.bias.data.zero_() def forward(self, x, H, W): x = x + self.drop_path(self.mlp(self.norm2(x), H, W)) return x class DWConv(nn.Module): def __init__(self, dim=768): super(DWConv, self).__init__() self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim) def forward(self, x, H, W): B, N, C = x.shape x = x.transpose(1, 2).view(B, C, H, W) x = self.dwconv(x) x = x.flatten(2).transpose(1, 2) return x class OverlapPatchEmbed(nn.Module): """ Image to Patch Embedding """ def __init__(self, img_size=224, patch_size=7, stride=4, in_chans=3, embed_dim=768): super().__init__() img_size = to_2tuple(img_size) patch_size = to_2tuple(patch_size) self.img_size = img_size self.patch_size = patch_size self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1] self.num_patches = self.H * self.W self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=stride, padding=(patch_size[0] // 2, patch_size[1] // 2)) self.norm = nn.LayerNorm(embed_dim) self.apply(self._init_weights) def _init_weights(self, m): if isinstance(m, nn.Linear): trunc_normal_(m.weight, std=.02) if isinstance(m, nn.Linear) and m.bias is not None: nn.init.constant_(m.bias, 0) elif isinstance(m, nn.LayerNorm): nn.init.constant_(m.bias, 0) nn.init.constant_(m.weight, 1.0) elif isinstance(m, nn.Conv2d): fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels fan_out //= m.groups m.weight.data.normal_(0, math.sqrt(2.0 / fan_out)) if m.bias is not None: m.bias.data.zero_() def forward(self, x): x = self.proj(x) _, _, H, W = x.shape x = x.flatten(2).transpose(1, 2) x = self.norm(x) return x, H, W class UNext(nn.Module): ## Conv 3 + MLP 2 + shifted MLP def __init__(self, num_classes, input_channels=3, deep_supervision=False,img_size=256, patch_size=16, in_chans=3, embed_dims=[ 128, 160, 256], num_heads=[1, 2, 4, 8], mlp_ratios=[4, 4, 4, 4], qkv_bias=False, qk_scale=None, drop_rate=0., attn_drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm, depths=[1, 1, 1], sr_ratios=[8, 4, 2, 1], **kwargs): super().__init__() self.encoder1 = nn.Conv2d(3, 16, 3, stride=1, padding=1) self.encoder2 = nn.Conv2d(16, 32, 3, stride=1, padding=1) self.encoder3 = nn.Conv2d(32, 128, 3, stride=1, padding=1) self.ebn1 = nn.BatchNorm2d(16) self.ebn2 = nn.BatchNorm2d(32) self.ebn3 = nn.BatchNorm2d(128) self.norm3 = norm_layer(embed_dims[1]) self.norm4 = norm_layer(embed_dims[2]) self.dnorm3 = norm_layer(160) self.dnorm4 = norm_layer(128) dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] self.block1 = nn.ModuleList([shiftedBlock( dim=embed_dims[1], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[0], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.block2 = nn.ModuleList([shiftedBlock( dim=embed_dims[2], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[1], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.dblock1 = nn.ModuleList([shiftedBlock( dim=embed_dims[1], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[0], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.dblock2 = nn.ModuleList([shiftedBlock( dim=embed_dims[0], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[1], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.patch_embed3 = OverlapPatchEmbed(img_size=img_size // 4, patch_size=3, stride=2, in_chans=embed_dims[0], embed_dim=embed_dims[1]) self.patch_embed4 = OverlapPatchEmbed(img_size=img_size // 8, patch_size=3, stride=2, in_chans=embed_dims[1], embed_dim=embed_dims[2]) self.decoder1 = nn.Conv2d(256, 160, 3, stride=1,padding=1) self.decoder2 = nn.Conv2d(160, 128, 3, stride=1, padding=1) self.decoder3 = nn.Conv2d(128, 32, 3, stride=1, padding=1) self.decoder4 = nn.Conv2d(32, 16, 3, stride=1, padding=1) self.decoder5 = nn.Conv2d(16, 16, 3, stride=1, padding=1) self.dbn1 = nn.BatchNorm2d(160) self.dbn2 = nn.BatchNorm2d(128) self.dbn3 = nn.BatchNorm2d(32) self.dbn4 = nn.BatchNorm2d(16) self.final = nn.Conv2d(16, num_classes, kernel_size=1) self.soft = nn.Softmax(dim =1) def forward(self, x, text_dummy): B = x.shape[0] ### Encoder ### Conv Stage ### Stage 1 out = F.relu(F.max_pool2d(self.ebn1(self.encoder1(x)),2,2)) t1 = out ### Stage 2 out = F.relu(F.max_pool2d(self.ebn2(self.encoder2(out)),2,2)) t2 = out ### Stage 3 out = F.relu(F.max_pool2d(self.ebn3(self.encoder3(out)),2,2)) t3 = out ### Tokenized MLP Stage ### Stage 4 out,H,W = self.patch_embed3(out) for i, blk in enumerate(self.block1): out = blk(out, H, W) out = self.norm3(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() t4 = out ### Bottleneck out ,H,W= self.patch_embed4(out) for i, blk in enumerate(self.block2): out = blk(out, H, W) out = self.norm4(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() ### Stage 4 out = F.relu(F.interpolate(self.dbn1(self.decoder1(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t4) _,_,H,W = out.shape out = out.flatten(2).transpose(1,2) for i, blk in enumerate(self.dblock1): out = blk(out, H, W) ### Stage 3 out = self.dnorm3(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() out = F.relu(F.interpolate(self.dbn2(self.decoder2(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t3) _,_,H,W = out.shape out = out.flatten(2).transpose(1,2) for i, blk in enumerate(self.dblock2): out = blk(out, H, W) out = self.dnorm4(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() out = F.relu(F.interpolate(self.dbn3(self.decoder3(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t2) out = F.relu(F.interpolate(self.dbn4(self.decoder4(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t1) out = F.relu(F.interpolate(self.decoder5(out),scale_factor=(2,2),mode ='bilinear')) return self.soft(self.final(out)),0 class UNext_S(nn.Module): ## Conv 3 + MLP 2 + shifted MLP w less parameters def __init__(self, num_classes, input_channels=3, deep_supervision=False,img_size=256, patch_size=16, in_chans=3, embed_dims=[32, 64, 128, 512], num_heads=[1, 2, 4, 8], mlp_ratios=[4, 4, 4, 4], qkv_bias=False, qk_scale=None, drop_rate=0., attn_drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm, depths=[1, 1, 1], sr_ratios=[8, 4, 2, 1], **kwargs): super().__init__() self.encoder1 = nn.Conv2d(3, 8, 3, stride=1, padding=1) self.encoder2 = nn.Conv2d(8, 16, 3, stride=1, padding=1) self.encoder3 = nn.Conv2d(16, 32, 3, stride=1, padding=1) self.ebn1 = nn.BatchNorm2d(8) self.ebn2 = nn.BatchNorm2d(16) self.ebn3 = nn.BatchNorm2d(32) self.norm3 = norm_layer(embed_dims[1]) self.norm4 = norm_layer(embed_dims[2]) self.dnorm3 = norm_layer(64) self.dnorm4 = norm_layer(32) dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] self.block1 = nn.ModuleList([shiftedBlock( dim=embed_dims[1], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[0], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.block2 = nn.ModuleList([shiftedBlock( dim=embed_dims[2], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[1], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.dblock1 = nn.ModuleList([shiftedBlock( dim=embed_dims[1], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[0], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.dblock2 = nn.ModuleList([shiftedBlock( dim=embed_dims[0], num_heads=num_heads[0], mlp_ratio=1, qkv_bias=qkv_bias, qk_scale=qk_scale, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[1], norm_layer=norm_layer, sr_ratio=sr_ratios[0])]) self.patch_embed3 = OverlapPatchEmbed(img_size=img_size // 4, patch_size=3, stride=2, in_chans=embed_dims[0], embed_dim=embed_dims[1]) self.patch_embed4 = OverlapPatchEmbed(img_size=img_size // 8, patch_size=3, stride=2, in_chans=embed_dims[1], embed_dim=embed_dims[2]) self.decoder1 = nn.Conv2d(128, 64, 3, stride=1,padding=1) self.decoder2 = nn.Conv2d(64, 32, 3, stride=1, padding=1) self.decoder3 = nn.Conv2d(32, 16, 3, stride=1, padding=1) self.decoder4 = nn.Conv2d(16, 8, 3, stride=1, padding=1) self.decoder5 = nn.Conv2d(8, 8, 3, stride=1, padding=1) self.dbn1 = nn.BatchNorm2d(64) self.dbn2 = nn.BatchNorm2d(32) self.dbn3 = nn.BatchNorm2d(16) self.dbn4 = nn.BatchNorm2d(8) self.final = nn.Conv2d(8, num_classes, kernel_size=1) self.soft = nn.Softmax(dim =1) def forward(self, x, text_dummy): B = x.shape[0] ### Encoder ### Conv Stage ### Stage 1 out = F.relu(F.max_pool2d(self.ebn1(self.encoder1(x)),2,2)) t1 = out ### Stage 2 out = F.relu(F.max_pool2d(self.ebn2(self.encoder2(out)),2,2)) t2 = out ### Stage 3 out = F.relu(F.max_pool2d(self.ebn3(self.encoder3(out)),2,2)) t3 = out ### Tokenized MLP Stage ### Stage 4 out,H,W = self.patch_embed3(out) for i, blk in enumerate(self.block1): out = blk(out, H, W) out = self.norm3(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() t4 = out ### Bottleneck out ,H,W= self.patch_embed4(out) for i, blk in enumerate(self.block2): out = blk(out, H, W) out = self.norm4(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() ### Stage 4 out = F.relu(F.interpolate(self.dbn1(self.decoder1(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t4) _,_,H,W = out.shape out = out.flatten(2).transpose(1,2) for i, blk in enumerate(self.dblock1): out = blk(out, H, W) ### Stage 3 out = self.dnorm3(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() out = F.relu(F.interpolate(self.dbn2(self.decoder2(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t3) _,_,H,W = out.shape out = out.flatten(2).transpose(1,2) for i, blk in enumerate(self.dblock2): out = blk(out, H, W) out = self.dnorm4(out) out = out.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous() out = F.relu(F.interpolate(self.dbn3(self.decoder3(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t2) out = F.relu(F.interpolate(self.dbn4(self.decoder4(out)),scale_factor=(2,2),mode ='bilinear')) out = torch.add(out,t1) out = F.relu(F.interpolate(self.decoder5(out),scale_factor=(2,2),mode ='bilinear')) return self.final(out) class medt_net(nn.Module): def __init__(self, block, block_2, layers, num_classes=2, zero_init_residual=True, groups=8, width_per_group=64, replace_stride_with_dilation=None, norm_layer=None, s=0.125, img_size = 128,imgchan = 3): super(medt_net, self).__init__() if norm_layer is None: norm_layer = nn.BatchNorm2d self._norm_layer = norm_layer self.inplanes = int(64 * s) self.dilation = 1 if replace_stride_with_dilation is None: replace_stride_with_dilation = [False, False, False] if len(replace_stride_with_dilation) != 3: raise ValueError("replace_stride_with_dilation should be None " "or a 3-element tuple, got {}".format(replace_stride_with_dilation)) self.groups = groups self.base_width = width_per_group self.conv1 = nn.Conv2d(imgchan, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False) self.conv2 = nn.Conv2d(self.inplanes, 128, kernel_size=3, stride=1, padding=1, bias=False) self.conv3 = nn.Conv2d(128, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False) self.bn1 = norm_layer(self.inplanes) self.bn2 = norm_layer(128) self.bn3 = norm_layer(self.inplanes) self.bn1 = norm_layer(self.inplanes) self.relu = nn.ReLU(inplace=True) self.layer1 = self._make_layer(block, int(128 * s), layers[0], kernel_size= (img_size//2)) self.layer2 = self._make_layer(block, int(256 * s), layers[1], stride=2, kernel_size=(img_size//2), dilate=replace_stride_with_dilation[0]) self.decoder4 = nn.Conv2d(int(512*s) , int(256*s), kernel_size=3, stride=1, padding=1) self.decoder5 = nn.Conv2d(int(256*s) , int(128*s) , kernel_size=3, stride=1, padding=1) self.adjust = nn.Conv2d(int(128*s) , num_classes, kernel_size=1, stride=1, padding=0) self.soft = nn.Softmax(dim=1) self.conv1_p = nn.Conv2d(imgchan, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False) self.conv2_p = nn.Conv2d(self.inplanes,128, kernel_size=3, stride=1, padding=1, bias=False) self.conv3_p = nn.Conv2d(128, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False) self.bn1_p = norm_layer(self.inplanes) self.bn2_p = norm_layer(128) self.bn3_p = norm_layer(self.inplanes) self.relu_p = nn.ReLU(inplace=True) img_size_p = img_size // 4 self.layer1_p = self._make_layer(block_2, int(128 * s), layers[0], kernel_size= (img_size_p//2)) self.layer2_p = self._make_layer(block_2, int(256 * s), layers[1], stride=2, kernel_size=(img_size_p//2), dilate=replace_stride_with_dilation[0]) self.layer3_p = self._make_layer(block_2, int(512 * s), layers[2], stride=2, kernel_size=(img_size_p//4), dilate=replace_stride_with_dilation[1]) self.layer4_p = self._make_layer(block_2, int(1024 * s), layers[3], stride=2, kernel_size=(img_size_p//8), dilate=replace_stride_with_dilation[2]) # Decoder self.decoder1_p = nn.Conv2d(int(1024 *2*s) , int(1024*2*s), kernel_size=3, stride=2, padding=1) self.decoder2_p = nn.Conv2d(int(1024 *2*s) , int(1024*s), kernel_size=3, stride=1, padding=1) self.decoder3_p = nn.Conv2d(int(1024*s), int(512*s), kernel_size=3, stride=1, padding=1) self.decoder4_p = nn.Conv2d(int(512*s) , int(256*s), kernel_size=3, stride=1, padding=1) self.decoder5_p = nn.Conv2d(int(256*s) , int(128*s) , kernel_size=3, stride=1, padding=1) self.decoderf = nn.Conv2d(int(128*s) , int(128*s) , kernel_size=3, stride=1, padding=1) self.adjust_p = nn.Conv2d(int(128*s) , num_classes, kernel_size=1, stride=1, padding=0) self.soft_p = nn.Softmax(dim=1) def _make_layer(self, block, planes, blocks, kernel_size=56, stride=1, dilate=False): norm_layer = self._norm_layer downsample = None previous_dilation = self.dilation if dilate: self.dilation *= stride stride = 1 if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( conv1x1(self.inplanes, planes * block.expansion, stride), norm_layer(planes * block.expansion), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample, groups=self.groups, base_width=self.base_width, dilation=previous_dilation, norm_layer=norm_layer, kernel_size=kernel_size)) self.inplanes = planes * block.expansion if stride != 1: kernel_size = kernel_size // 2 for _ in range(1, blocks): layers.append(block(self.inplanes, planes, groups=self.groups, base_width=self.base_width, dilation=self.dilation, norm_layer=norm_layer, kernel_size=kernel_size)) return nn.Sequential(*layers) def _forward_impl(self, x): xin = x.clone() x = self.conv1(x) x = self.bn1(x) x = self.relu(x) x = self.conv2(x) x = self.bn2(x) x = self.relu(x) x = self.conv3(x) x = self.bn3(x) x = self.relu(x) x1 = self.layer1(x) x2 = self.layer2(x1) x = F.relu(F.interpolate(self.decoder4(x2) , scale_factor=(2,2), mode ='bilinear')) x = torch.add(x, x1) x = F.relu(F.interpolate(self.decoder5(x) , scale_factor=(2,2), mode ='bilinear')) # end of full image training x_loc = x.clone() #start for i in range(0,4): for j in range(0,4): x_p = xin[:,:,32*i:32*(i+1),32*j:32*(j+1)] # begin patch wise x_p = self.conv1_p(x_p) x_p = self.bn1_p(x_p) x_p = self.relu(x_p) x_p = self.conv2_p(x_p) x_p = self.bn2_p(x_p) x_p = self.relu(x_p) x_p = self.conv3_p(x_p) x_p = self.bn3_p(x_p) x_p = self.relu(x_p) x1_p = self.layer1_p(x_p) x2_p = self.layer2_p(x1_p) x3_p = self.layer3_p(x2_p) x4_p = self.layer4_p(x3_p) x_p = F.relu(F.interpolate(self.decoder1_p(x4_p), scale_factor=(2,2), mode ='bilinear')) x_p = torch.add(x_p, x4_p) x_p = F.relu(F.interpolate(self.decoder2_p(x_p) , scale_factor=(2,2), mode ='bilinear')) x_p = torch.add(x_p, x3_p) x_p = F.relu(F.interpolate(self.decoder3_p(x_p) , scale_factor=(2,2), mode ='bilinear')) x_p = torch.add(x_p, x2_p) x_p = F.relu(F.interpolate(self.decoder4_p(x_p) , scale_factor=(2,2), mode ='bilinear')) x_p = torch.add(x_p, x1_p) x_p = F.relu(F.interpolate(self.decoder5_p(x_p) , scale_factor=(2,2), mode ='bilinear')) x_loc[:,:,32*i:32*(i+1),32*j:32*(j+1)] = x_p x = torch.add(x,x_loc) x = F.relu(self.decoderf(x)) x = self.adjust(F.relu(x)) return x def forward(self, x, text_dummy): return self._forward_impl(x)