training/models.py [98:160]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.num_classes = num_classes
        self.conv_block1 = nn.Sequential(
            nn.Conv2d(3, 8, 5),
            nn.BatchNorm2d(8),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.conv_block2 = nn.Sequential(
            nn.Conv2d(8, 16, 5),
            nn.BatchNorm2d(16),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.conv_block3 = nn.Sequential(
            nn.Conv2d(16, 32, 5),
            nn.BatchNorm2d(32),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.conv_block4 = nn.Sequential(
            nn.Conv2d(32, 32, 5),
            nn.BatchNorm2d(32),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.classifier = nn.Sequential(
            nn.Conv2d(32, 512, 5),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.Dropout2d(),
            nn.Conv2d(512, 512, 1),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.Dropout2d())

        self.encoder_seg = nn.Conv2d(512, self.num_classes, 1)
        self.encoder_depth = nn.Conv2d(512, 1, 1)
        self.encoder_ae = nn.Conv2d(512, 3, 1)

        self.score_pool2_seg = nn.Conv2d(16, self.num_classes, 1)
        self.score_pool3_seg = nn.Conv2d(32, self.num_classes, 1)

        self.score_pool2_depth = nn.Conv2d(16, 1, 1)
        self.score_pool3_depth = nn.Conv2d(32, 1, 1)

        self.score_pool2_ae = nn.Conv2d(16, 3, 1)
        self.score_pool3_ae = nn.Conv2d(32, 3, 1)

        self.pretrained = pretrained
        if self.pretrained == True:
            print('Loading CNN weights from %s' % checkpoint_path)
            checkpoint = torch.load(
                checkpoint_path, map_location={'cuda:0': 'cpu'})
            self.load_state_dict(checkpoint['model_state'])
            for param in self.parameters():
                param.requires_grad = False
        else:
            for m in self.modules():
                if isinstance(m, nn.Conv2d):
                    n = m.kernel_size[0] * m.kernel_size[1] * (
                        m.out_channels + m.in_channels)
                    m.weight.data.normal_(0, math.sqrt(2. / n))
                elif isinstance(m, nn.BatchNorm2d):
                    m.weight.data.fill_(1)
                    m.bias.data.zero_()

    def forward(self, x):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/models.py [211:273]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.num_classes = num_classes
        self.conv_block1 = nn.Sequential(
            nn.Conv2d(3, 8, 5),
            nn.BatchNorm2d(8),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.conv_block2 = nn.Sequential(
            nn.Conv2d(8, 16, 5),
            nn.BatchNorm2d(16),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.conv_block3 = nn.Sequential(
            nn.Conv2d(16, 32, 5),
            nn.BatchNorm2d(32),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.conv_block4 = nn.Sequential(
            nn.Conv2d(32, 32, 5),
            nn.BatchNorm2d(32),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(2, 2))
        self.classifier = nn.Sequential(
            nn.Conv2d(32, 512, 5),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.Dropout2d(),
            nn.Conv2d(512, 512, 1),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.Dropout2d())

        self.encoder_seg = nn.Conv2d(512, self.num_classes, 1)
        self.encoder_depth = nn.Conv2d(512, 1, 1)
        self.encoder_ae = nn.Conv2d(512, 3, 1)

        self.score_pool2_seg = nn.Conv2d(16, self.num_classes, 1)
        self.score_pool3_seg = nn.Conv2d(32, self.num_classes, 1)

        self.score_pool2_depth = nn.Conv2d(16, 1, 1)
        self.score_pool3_depth = nn.Conv2d(32, 1, 1)

        self.score_pool2_ae = nn.Conv2d(16, 3, 1)
        self.score_pool3_ae = nn.Conv2d(32, 3, 1)

        self.pretrained = pretrained
        if self.pretrained == True:
            print('Loading CNN weights from %s' % checkpoint_path)
            checkpoint = torch.load(
                checkpoint_path, map_location={'cuda:0': 'cpu'})
            self.load_state_dict(checkpoint['model_state'])
            for param in self.parameters():
                param.requires_grad = False
        else:
            for m in self.modules():
                if isinstance(m, nn.Conv2d):
                    n = m.kernel_size[0] * m.kernel_size[1] * (
                        m.out_channels + m.in_channels)
                    m.weight.data.normal_(0, math.sqrt(2. / n))
                elif isinstance(m, nn.BatchNorm2d):
                    m.weight.data.fill_(1)
                    m.bias.data.zero_()

    def forward(self, x):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -