"""Local adjacent slices conditioned on three whole-volume OCT views.""" import torch from torch import nn from torch.nn import functional as F from src.models.context import ContextBoundaryNet from src.models.unet import Block class GlobalBoundaryNet(ContextBoundaryNet): def __init__(self, n_boundaries, base, prior_height): super().__init__(n_boundaries, base, prior_height) self.global_encoder = nn.Sequential( nn.Conv2d(3, base, 5, stride=2, padding=2, bias=False), nn.GroupNorm(min(8, base), base), nn.SiLU(), Block(base, base * 2), nn.AvgPool2d(2), Block(base * 2, base * 4), nn.AdaptiveAvgPool2d(1), nn.Flatten(), ) self.global_film = nn.Linear(base * 4, base * 12 * 2) nn.init.zeros_(self.global_film.weight) nn.init.zeros_(self.global_film.bias) def forward(self, image): if image.shape[1] != 6: raise ValueError("Expected local3 plus global3 OCT channels") global_image = F.interpolate( image[:, 3:], size=(96, 128), mode="bilinear", align_corners=False ) embedding = self.global_encoder(global_image) scale, bias = self.global_film(embedding).chunk(2, dim=1) x = image[:, :3].contiguous() skips = [] for index, layer in enumerate(self.down): if index: x = F.avg_pool2d(x, 2) x = layer(x) if index == len(self.down) - 1: x = x * (1 + scale[:, :, None, None]) + bias[:, :, None, None] skips.append(x) for index, layer in enumerate(self.up): skip = skips[-2 - index] x = F.interpolate( x, size=skip.shape[-2:], mode="bilinear", align_corners=False ) x = layer(torch.cat([x, skip], 1)) logits = self.head(x) prior = self.axial_prior if prior.shape[-2] != logits.shape[-2]: prior = F.interpolate( prior, size=(logits.shape[-2], 1), mode="bilinear", align_corners=False ) return logits + prior