Problem in _to_bc_h_w_2 ??

[mschoeler]

In deform_conv/layers.py:39

    @staticmethod
    def _to_bc_h_w_2(x, x_shape):
        """(b, h, w, 2c) -> (b*c, h, w, 2)"""
        x = tf.transpose(x, [0, 3, 1, 2])
        x = tf.reshape(x, (-1, int(x_shape[1]), int(x_shape[2]), 2))
        return x

I think the transpose changes the array from
(b, h, w, 2c) -> (b, 2c, h, w)
So the subsequent reshape will splitt the width dimension of your array.

This seems like a bug in the code to me.

Cheers