layers.py 文件源码

def __init__(self, rng, x, n_in, n_out, W = None, b = None, activation = T.tanh, p=0.0, training=0):
        n_in = int(n_in)  # ensure sizes have integer type
        n_out = int(n_out)# ensure sizes have integer type

        self.x = x

        if p > 0.0:
            if training==1:
                srng = RandomStreams(seed=123456)
                self.x = T.switch(srng.binomial(size=x.shape, p=p), x, 0)
            else:
                self.x =  (1-p) * x


        # initialize with 0 the weights W as a matrix of shape (n_in, n_out)
        if W is None:
            W_value = numpy.asarray(rng.normal(0.0, 1.0/numpy.sqrt(n_in),
                      size=(n_in, n_out)), dtype=theano.config.floatX)
            W = theano.shared(value=W_value,
                              name='W', borrow=True)
        if b is None:
            b = theano.shared(value=numpy.zeros((n_out,),
                              dtype=theano.config.floatX),
                              name='b', borrow=True)

        self.W = W
        self.b = b

        self.delta_W = theano.shared(value = numpy.zeros((n_in,n_out),
                                     dtype=theano.config.floatX), name='delta_W')

        self.delta_b = theano.shared(value = numpy.zeros_like(self.b.get_value(borrow=True),
                                     dtype=theano.config.floatX), name='delta_b')

        self.output = T.dot(self.x, self.W) + self.b
        self.output = activation(self.output)

        self.params = [self.W, self.b]
        self.delta_params = [self.delta_W, self.delta_b]