cd9d42d875e636b39bf14eb3a45fe4f41087e776,pytorch/pytorchcv/models/others/oth_resattnet3.py,AttentionModule_stage1,__init__,#AttentionModule_stage1#Any#Any#Any#Any#Any#,199

Before Change

            ResBlock(in_channels, out_channels)
        )

        self.interpolation3 = nn.UpsamplingBilinear2d(size=size3)

        self.softmax4_blocks = ResBlock(in_channels, out_channels)

        self.interpolation2 = nn.UpsamplingBilinear2d(size=size2)

        self.softmax5_blocks = ResBlock(in_channels, out_channels)

        self.interpolation1 = nn.UpsamplingBilinear2d(size=size1)

        self.softmax6_blocks = nn.Sequential(
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels , kernel_size = 1, stride = 1, bias = False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels , kernel_size = 1, stride = 1, bias = False),
            nn.Sigmoid()
        )

        self.last_blocks = ResBlock(in_channels, out_channels)

    def forward(self, x):

After Change

        // self.interpolation1 = nn.UpsamplingBilinear2d(size=size1)

        self.softmax6_blocks = nn.Sequential(
            pre_conv1x1_block(
                in_channels=out_channels,
                out_channels=out_channels),
            pre_conv1x1_block(
                in_channels=out_channels,
                out_channels=out_channels),
            nn.Sigmoid()
        )

        self.last_blocks = ResBlock(in_channels, out_channels)

    def forward(self, x):

Instances