layers.py 文件源码

def MDCL(incoming,num_filters,scales,name,dnn=True):
    if dnn:
        from lasagne.layers.dnn import Conv2DDNNLayer as C2D
    # W initialization method--this should also work as Orthogonal('relu'), but I have yet to validate that as thoroughly.
    winit = initmethod(0.02)

    # Initialization method for the coefficients
    sinit = lasagne.init.Constant(1.0/(1+len(scales)))

    # Number of incoming channels
    ni =lasagne.layers.get_output_shape(incoming)[1]

    # Weight parameter--the primary parameter for this block
    W = theano.shared(lasagne.utils.floatX(winit.sample((num_filters,lasagne.layers.get_output_shape(incoming)[1],3,3))),name=name+'W')

    # Primary Convolution Layer--No Dilation
    n = C2D(incoming = incoming,
                            num_filters = num_filters,
                            filter_size = [3,3],
                            stride = [1,1],
                            pad = (1,1),
                            W = W*theano.shared(lasagne.utils.floatX(sinit.sample(num_filters)), name+'_coeff_base').dimshuffle(0,'x','x','x'), # Note the broadcasting dimshuffle for the num_filter scalars.
                            b = None,
                            nonlinearity = None,
                            name = name+'base'
                        )
    # List of remaining layers. This should probably just all be concatenated into a single list rather than being a separate deal.
    nd = []    
    for i,scale in enumerate(scales):

        # I don't think 0 dilation is technically defined (or if it is it's just the regular filter) but I use it here as a convenient keyword to grab the 1x1 mean conv.
        if scale==0:
            nd.append(C2D(incoming = incoming,
                            num_filters = num_filters,
                            filter_size = [1,1],
                            stride = [1,1],
                            pad = (0,0),
                            W = T.mean(W,axis=[2,3]).dimshuffle(0,1,'x','x')*theano.shared(lasagne.utils.floatX(sinit.sample(num_filters)), name+'_coeff_1x1').dimshuffle(0,'x','x','x'),
                            b = None,
                            nonlinearity = None,
                            name = name+str(scale)))
        # Note the dimshuffles in this layer--these are critical as the current DilatedConv2D implementation uses a backward pass.
        else:
            nd.append(lasagne.layers.DilatedConv2DLayer(incoming = lasagne.layers.PadLayer(incoming = incoming, width=(scale,scale)),
                                num_filters = num_filters,
                                filter_size = [3,3],
                                dilation=(scale,scale),
                                W = W.dimshuffle(1,0,2,3)*theano.shared(lasagne.utils.floatX(sinit.sample(num_filters)), name+'_coeff_'+str(scale)).dimshuffle('x',0,'x','x'),
                                b = None,
                                nonlinearity = None,
                                name =  name+str(scale)))
    return ESL(nd+[n])

# MDC-based Upsample Layer.
# This is a prototype I don't make use of extensively. It's operational but it doesn't seem to improve results yet.