preprocess/humanparsing/networks/context_encoding/aspp.py

#!/usr/bin/env python
# -*- encoding: utf-8 -*-

"""
@Author  :   Peike Li
@Contact :   [email protected]
@File    :   aspp.py
@Time    :   8/4/19 3:36 PM
@Desc    :   
@License :   This source code is licensed under the license found in the 
             LICENSE file in the root directory of this source tree.
"""

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

from modules import InPlaceABNSync


class ASPPModule(nn.Module):
    """
    Reference:
        Chen, Liang-Chieh, et al. *"Rethinking Atrous Convolution for Semantic Image Segmentation."*
    """
    def __init__(self, features, out_features=512, inner_features=256, dilations=(12, 24, 36)):
        super(ASPPModule, self).__init__()

        self.conv1 = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
                                   nn.Conv2d(features, inner_features, kernel_size=1, padding=0, dilation=1,
                                             bias=False),
                                   InPlaceABNSync(inner_features))
        self.conv2 = nn.Sequential(
            nn.Conv2d(features, inner_features, kernel_size=1, padding=0, dilation=1, bias=False),
            InPlaceABNSync(inner_features))
        self.conv3 = nn.Sequential(
            nn.Conv2d(features, inner_features, kernel_size=3, padding=dilations[0], dilation=dilations[0], bias=False),
            InPlaceABNSync(inner_features))
        self.conv4 = nn.Sequential(
            nn.Conv2d(features, inner_features, kernel_size=3, padding=dilations[1], dilation=dilations[1], bias=False),
            InPlaceABNSync(inner_features))
        self.conv5 = nn.Sequential(
            nn.Conv2d(features, inner_features, kernel_size=3, padding=dilations[2], dilation=dilations[2], bias=False),
            InPlaceABNSync(inner_features))

        self.bottleneck = nn.Sequential(
            nn.Conv2d(inner_features * 5, out_features, kernel_size=1, padding=0, dilation=1, bias=False),
            InPlaceABNSync(out_features),
            nn.Dropout2d(0.1)
        )

    def forward(self, x):
        _, _, h, w = x.size()

        feat1 = F.interpolate(self.conv1(x), size=(h, w), mode='bilinear', align_corners=True)

        feat2 = self.conv2(x)
        feat3 = self.conv3(x)
        feat4 = self.conv4(x)
        feat5 = self.conv5(x)
        out = torch.cat((feat1, feat2, feat3, feat4, feat5), 1)

        bottle = self.bottleneck(out)
        return bottle