layers.py

from __future__ import absolute_import, division


import tensorflow as tf
from keras.layers import Conv2D
from keras.initializers import RandomNormal
from deform_conv import tf_batch_map_offsets


class ConvOffset2D(Conv2D):
    """ConvOffset2D

    Convolutional layer responsible for learning the 2D offsets and output the
    deformed feature map using bilinear interpolation

    Note that this layer does not perform convolution on the deformed feature
    map. See get_deform_cnn in cnn.py for usage
    """

    def __init__(self, filters, init_normal_stddev=0.01, **kwargs):
        """Init

        Parameters
        ----------
        filters : int
            Number of channel of the input feature map
        init_normal_stddev : float
            Normal kernel initialization
        **kwargs:
            Pass to superclass. See Con2D layer in Keras
        """

        self.filters = filters
        super(ConvOffset2D, self).__init__(
            self.filters * 2, (3, 3), padding='same', use_bias=False,
            kernel_initializer=RandomNormal(0, init_normal_stddev),
            **kwargs
        )

    def call(self, x):
        """Return the deformed featured map"""
        x_shape = x.get_shape()
        offsets = super(ConvOffset2D, self).call(x)

        # offsets: (b*c, h, w, 2)
        offsets = self._to_bc_h_w_2(offsets, x_shape)

        # x: (b*c, h, w)
        x = self._to_bc_h_w(x, x_shape)

        # X_offset: (b*c, h, w)
        x_offset = tf_batch_map_offsets(x, offsets)

        # x_offset: (b, h, w, c)
        x_offset = self._to_b_h_w_c(x_offset, x_shape)

        return x_offset

    def compute_output_shape(self, input_shape):
        """Output shape is the same as input shape

        Because this layer does only the deformation part
        """
        return input_shape

    @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

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

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