layers.py 文件源码

def __init__(self, args, incoming, num_filters, filter_size, stride=(1, 1),
                 pad=0, untie_biases=False,
                 W=init.GlorotUniform(), b=init.Constant(0.),
                 nonlinearity=nonlinearities.rectify,
                 convolution=T.nnet.conv2d, **kwargs):
        super(Conv2DLayerWithReg, self).__init__(incoming, **kwargs)

        if nonlinearity is None:
            self.nonlinearity = nonlinearities.identity
        else:
            self.nonlinearity = nonlinearity

        self.num_filters = num_filters
        self.filter_size = _as_tuple(filter_size, 2)
        self.stride = _as_tuple(stride, 2)
        self.untie_biases = untie_biases
        self.convolution = convolution

        if pad == 'valid':
            self.pad = (0, 0)
        elif pad in ('full', 'same'):
            self.pad = pad
        else:
            self.pad = _as_tuple(pad, 2, int)

        self.W = self.add_param(W, self.get_W_shape(), name="W")
        if b is None:
            self.b = None
        else:
            if self.untie_biases:
                biases_shape = (num_filters, self.output_shape[2], self.
                                output_shape[3])
            else:
                biases_shape = (num_filters,)
            self.b = self.add_param(b, biases_shape, name="b",
                                    regularizable=False)

        if args.regL1 is True:
            self.L1 = self.add_param(init.Constant(args.regInit['L1']),
                                     self.get_W_shape() , name="L1")
        if args.regL2 is True:
            self.L2 = self.add_param(init.Constant(args.regInit['L2']),
                                     self.get_W_shape() , name="L2")