How To Manipulate (constrain) The Weights Of The Filter Kernel In Conv2d In Keras?

I understand that there are several options for kernel_constraint in Conv2D in Keras: max_norm, non_neg or unit_norm.. But what I needed is to set the anchor (center) position in t

Solution 1:

You need a custom Conv2D layer for that, where you change its call method to apply the zero at the center.

classZeroCenterConv2D(Conv2D):
    def__init__(self, filters, kernel_size, **kwargs):
        super(ZeroCenterConv2D, self).__init__(filters, kernel_size, **kwargs)

    defcall(self, inputs):
        assert self.kernel_size[0] % 2 == 1, "Error: the kernel size is an even number"assert self.kernel_size[1] % 2 == 1, "Error: the kernel size is an even number"

        centerX = (self.kernel_size[0] - 1) // 2
        centerY = (self.kernel_size[1] - 1) // 2

        kernel_mask = np.ones(self.kernel_size + (1, 1))
        kernel_mask[centerX, centerY] = 0
        kernel_mask = K.variable(kernel_mask)

        customKernel = self.kernel * kernel_mask

        outputs = K.conv2d(
            inputs,
            customKernel,
            strides=self.strides,
            padding=self.padding,
            data_format=self.data_format,
            dilation_rate=self.dilation_rate)

        if self.use_bias:
            outputs = K.bias_add(
                outputs,
                self.bias,
                data_format=self.data_format)

        if self.activation isnotNone:
            return self.activation(outputs)

        return outputs

This will not replace the actual weights, though, but the center ones will never be used.

When you use layer.get_weights() of model.get_weights(), you will see the center weights as they were initialized (not as zeros).