Exemple #1
0
def _transform(theta, input, downsample_factor):
    num_batch, num_channels, height, width = input.shape
    theta = T.reshape(theta, (-1, 2, 3))

    # grid of (x_t, y_t, 1), eq (1) in ref [1]
    out_height = T.cast(height / downsample_factor[0], 'int64')
    out_width = T.cast(width / downsample_factor[1], 'int64')
    grid = _meshgrid(out_height, out_width)

    # Transform A x (x_t, y_t, 1)^T -> (x_s, y_s)
    T_g = T.dot(theta, grid)
    x_s = T_g[:, 0]
    y_s = T_g[:, 1]
    x_s_flat = x_s.flatten()
    y_s_flat = y_s.flatten()

    # dimshuffle input to  (bs, height, width, channels)
    input_dim = input.dimshuffle(0, 2, 3, 1)
    input_transformed = _interpolate(
        input_dim, x_s_flat, y_s_flat,
        out_height, out_width)

    output = T.reshape(
        input_transformed, (num_batch, out_height, out_width, num_channels))
    output = output.dimshuffle(0, 3, 1, 2)  # dimshuffle to conv format
    return output
Exemple #2
0
    def get_output_for(self, input, **kwargs):
        if input.ndim > 2:
            # if the input has more than two dimensions, flatten it into a
            # batch of feature vectors.
            input = T.flatten(input, 2)

        activation = T.dot(input, self.W)
        if self.b is not None:
            activation = T.broadcast('+', activation , T.dimshuffle(self.b, 'x', 0), 'xx,1x')
        return self.nonlinearity(activation)
Exemple #3
0
def _meshgrid(height, width):
    # This function is the grid generator from eq. (1) in reference [1].
    # It is equivalent to the following numpy code:
    #  x_t, y_t = np.meshgrid(np.linspace(-1, 1, width),
    #                         np.linspace(-1, 1, height))
    #  ones = np.ones(np.prod(x_t.shape))
    #  grid = np.vstack([x_t.flatten(), y_t.flatten(), ones])
    # It is implemented in Theano instead to support symbolic grid sizes.
    # Note: If the image size is known at layer construction time, we could
    # compute the meshgrid offline in numpy instead of doing it dynamically
    # in Theano. However, it hardly affected performance when we tried.
    x_t = T.dot(T.ones((height, 1)),
                _linspace(-1.0, 1.0, width).dimshuffle('x', 0))
    y_t = T.dot(_linspace(-1.0, 1.0, height).dimshuffle(0, 'x'),
                T.ones((1, width)))

    x_t_flat = x_t.reshape((1, -1))
    y_t_flat = y_t.reshape((1, -1))
    ones = T.ones_like(x_t_flat)
    grid = T.concatenate([x_t_flat, y_t_flat, ones], axis=0)
    return grid