rscd/models/decoderheads/lgpnet/SpatialPyramidModule.py

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

"""
This code refers to "Pyramid scene parsing network".
"""

class SPM(nn.Module):
    def __init__(self, features, out_features=1024, sizes=(1, 2, 3, 6)):
        super().__init__()
        self.stages = []
        self.stages = nn.ModuleList([self._make_stage(features, size) for size in sizes])
        self.bottleneck = nn.Conv2d(features * (len(sizes) + 1), out_features, kernel_size=1)
        self.relu = nn.ReLU()

    def _make_stage(self, features, size):
        prior = nn.AdaptiveAvgPool2d(output_size=(size, size))
        conv = nn.Conv2d(features, features, kernel_size=1, bias=False)
        return nn.Sequential(prior, conv)

    def forward(self, feats):
        h, w = feats.size(2), feats.size(3)
        priors = [F.interpolate(input=stage(feats), size=(h, w), mode='bilinear', align_corners=False) for stage in self.stages] + [feats]
        bottle = self.bottleneck(torch.cat(priors, 1))
        return self.relu(bottle)