fcn8s.py

"""
This file contains a modified version of the FCN-8s code available in https://github.com/wkentaro/pytorch-fcn
The original copyright notice from that repository is included below:

Copyright (c) 2017 - 2019 Kentaro Wada.

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
"""

import numpy as np
import torch
import torch.nn as nn


def _upsampling_weights(in_channels, out_channels, kernel_size):
    factor = (kernel_size + 1) // 2
    if kernel_size % 2 == 1:
        center = factor - 1
    else:
        center = factor - 0.5
    og = np.ogrid[:kernel_size, :kernel_size]
    filt = (1 - abs(og[0] - center) / factor) * (1 - abs(og[1] - center) / factor)
    weight = np.zeros(
        (in_channels, out_channels, kernel_size, kernel_size), dtype=np.float64
    )
    weight[range(in_channels), range(out_channels), :, :] = filt
    return torch.from_numpy(weight).float()


class Fcn8s(nn.Module):
    def __init__(self, n_class=21):
        """
        Create the FCN-8s network the the given number of classes.

        Args:
            n_class:    The number of semantic classes.
        """

        super(Fcn8s, self).__init__()

        # conv1
        self.conv1_1 = nn.Conv2d(3, 64, 3, padding=100)
        self.relu1_1 = nn.ReLU(inplace=True)
        self.conv1_2 = nn.Conv2d(64, 64, 3, padding=1)
        self.relu1_2 = nn.ReLU(inplace=True)
        self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)

        # conv2
        self.conv2_1 = nn.Conv2d(64, 128, 3, padding=1)
        self.relu2_1 = nn.ReLU(inplace=True)
        self.conv2_2 = nn.Conv2d(128, 128, 3, padding=1)
        self.relu2_2 = nn.ReLU(inplace=True)
        self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)

        # conv3
        self.conv3_1 = nn.Conv2d(128, 256, 3, padding=1)
        self.relu3_1 = nn.ReLU(inplace=True)
        self.conv3_2 = nn.Conv2d(256, 256, 3, padding=1)
        self.relu3_2 = nn.ReLU(inplace=True)
        self.conv3_3 = nn.Conv2d(256, 256, 3, padding=1)
        self.relu3_3 = nn.ReLU(inplace=True)
        self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)

        # conv4
        self.conv4_1 = nn.Conv2d(256, 512, 3, padding=1)
        self.relu4_1 = nn.ReLU(inplace=True)
        self.conv4_2 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu4_2 = nn.ReLU(inplace=True)
        self.conv4_3 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu4_3 = nn.ReLU(inplace=True)
        self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)

        # conv5
        self.conv5_1 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu5_1 = nn.ReLU(inplace=True)
        self.conv5_2 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu5_2 = nn.ReLU(inplace=True)
        self.conv5_3 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu5_3 = nn.ReLU(inplace=True)
        self.pool5 = nn.MaxPool2d(2, stride=2, ceil_mode=True)

        # fc6
        self.fc6 = nn.Conv2d(512, 4096, 7)
        self.relu6 = nn.ReLU(inplace=True)
        self.drop6 = nn.Dropout2d()

        # fc7
        self.fc7 = nn.Conv2d(4096, 4096, 1)
        self.relu7 = nn.ReLU(inplace=True)
        self.drop7 = nn.Dropout2d()

        self.score_fr = nn.Conv2d(4096, n_class, 1)
        self.score_pool3 = nn.Conv2d(256, n_class, 1)
        self.score_pool4 = nn.Conv2d(512, n_class, 1)

        self.upscore2 = nn.ConvTranspose2d(n_class, n_class, 4, stride=2, bias=True)
        self.upscore8 = nn.ConvTranspose2d(n_class, n_class, 16, stride=8, bias=False)
        self.upscore_pool4 = nn.ConvTranspose2d(
            n_class, n_class, 4, stride=2, bias=False
        )

        self._initialize_weights()

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                m.weight.data.zero_()
                if m.bias is not None:
                    m.bias.data.zero_()
            if isinstance(m, nn.ConvTranspose2d):
                assert m.kernel_size[0] == m.kernel_size[1]
                initial_weight = _upsampling_weights(
                    m.in_channels, m.out_channels, m.kernel_size[0]
                )
                m.weight.data.copy_(initial_weight)

    def forward(self, image):
        h = self.relu1_1(self.conv1_1(image))
        h = self.relu1_2(self.conv1_2(h))
        h = self.pool1(h)

        h = self.relu2_1(self.conv2_1(h))
        h = self.relu2_2(self.conv2_2(h))
        h = self.pool2(h)

        h = self.relu3_1(self.conv3_1(h))
        h = self.relu3_2(self.conv3_2(h))
        h = self.relu3_3(self.conv3_3(h))
        h = self.pool3(h)
        pool3 = h  # 1/8

        h = self.relu4_1(self.conv4_1(h))
        h = self.relu4_2(self.conv4_2(h))
        h = self.relu4_3(self.conv4_3(h))
        h = self.pool4(h)
        pool4 = h  # 1/16

        h = self.relu5_1(self.conv5_1(h))
        h = self.relu5_2(self.conv5_2(h))
        h = self.relu5_3(self.conv5_3(h))
        h = self.pool5(h)

        h = self.relu6(self.fc6(h))
        h = self.drop6(h)

        h = self.relu7(self.fc7(h))
        h = self.drop7(h)

        h = self.score_fr(h)
        h = self.upscore2(h)
        upscore2 = h  # 1/16

        h = self.score_pool4(pool4)
        h = h[:, :, 5:5 + upscore2.size()[2], 5:5 + upscore2.size()[3]]
        score_pool4c = h  # 1/16

        h = upscore2 + score_pool4c  # 1/16
        h = self.upscore_pool4(h)
        upscore_pool4 = h  # 1/8

        h = self.score_pool3(pool3)
        h = h[:, :, 9:9 + upscore_pool4.size()[2], 9:9 + upscore_pool4.size()[3]]
        score_pool3c = h  # 1/8

        h = upscore_pool4 + score_pool3c  # 1/8

        h = self.upscore8(h)
        h = h[:, :, 31:31 + image.size()[2], 31:31 + image.size()[3]].contiguous()

        return h