pixel_rnn.py 文件源码

def Conv1D(name, input_dim, output_dim, filter_size, inputs, apply_biases=True):
    """
    inputs.shape: (batch size, height, input_dim)
    output.shape: (batch size, height, output_dim)
    * performs valid convs
    """
    def uniform(stdev, size):
        """uniform distribution with the given stdev and size"""
        return numpy.random.uniform(
            low=-stdev * numpy.sqrt(3),
            high=stdev * numpy.sqrt(3),
            size=size
        ).astype(theano.config.floatX)

    filters = lib.param(
        name+'.Filters',
        uniform(
            1./numpy.sqrt(input_dim * filter_size),
            # output dim, input dim, height, width
            (output_dim, input_dim, filter_size, 1)
        )
    )

    # conv2d takes inputs as (batch size, input channels, height[?], width[?])
    inputs = inputs.reshape((inputs.shape[0], inputs.shape[1], 1, inputs.shape[2]))
    inputs = inputs.dimshuffle(0, 3, 1, 2)
    result = T.nnet.conv2d(inputs, filters, border_mode='valid', filter_flip=False)

    if apply_biases:
        biases = lib.param(
            name+'.Biases',
            numpy.zeros(output_dim, dtype=theano.config.floatX)
        )
        result = result + biases[None, :, None, None]

    result = result.dimshuffle(0, 2, 3, 1)
    return result.reshape((result.shape[0], result.shape[1], result.shape[3]))