search

cvlab-yonsei / MNAD

An official implementation of "Learning Memory-guided Normality for Anomaly Detection" (CVPR 2020) in PyTorch.
333 stars 82 forks source link

A question about the structure of reconstruction network #22

Open NeuZhangQiang opened 3 years ago

NeuZhangQiang commented 3 years ago

In the Encoder of reconstruction network, some code is:

        def Basic(intInput, intOutput):
            return torch.nn.Sequential(
                torch.nn.Conv2d(in_channels=intInput, out_channels=intOutput, kernel_size=3, stride=1, padding=1),
                torch.nn.BatchNorm2d(intOutput),
                torch.nn.ReLU(inplace=False),
                torch.nn.Conv2d(in_channels=intOutput, out_channels=intOutput, kernel_size=3, stride=1, padding=1),
                torch.nn.BatchNorm2d(intOutput),
                torch.nn.ReLU(inplace=False)
            )

        def Basic_(intInput, intOutput):
            return torch.nn.Sequential(
                torch.nn.Conv2d(in_channels=intInput, out_channels=intOutput, kernel_size=3, stride=1, padding=1),
                torch.nn.BatchNorm2d(intOutput),
                torch.nn.ReLU(inplace=False),
                torch.nn.Conv2d(in_channels=intOutput, out_channels=intOutput, kernel_size=3, stride=1, padding=1),
            )

I wonder why the Basic_ do not include BatchNorm2d and ReLU for the second convolution kernel.

Any suggestion is appreciated~