convnet_3d.py 文件源码

def __init__(self, rng, input, n_in, n_out, share_with=None, activation=None):

        self.input = input
        self.n_in = n_in
        self.n_out = n_out
        self.activation = activation
        if share_with:
            self.W = share_with.W
            self.b = share_with.b

            self.W_delta = share_with.W_delta
            self.b_delta = share_with.b_delta
        else:
            W_values = np.asarray(
                rng.uniform(
                    low=-np.sqrt(6. / (n_in + n_out)),
                    high=np.sqrt(6. / (n_in + n_out)),
                    size=(n_in, n_out)
                ),
                dtype=theano.config.floatX
            )
            if activation == nnet.sigmoid:
                W_values *= 4

            self.W = theano.shared(value=W_values, name='W', borrow=True)

            b_values = np.zeros((n_out,), dtype=theano.config.floatX)
            self.b = theano.shared(value=b_values, name='b', borrow=True)

            self.W_delta = theano.shared(
                    np.zeros((n_in, n_out), dtype=theano.config.floatX),
                    borrow=True
                )

            self.b_delta = theano.shared(value=b_values, borrow=True)

        self.params = [self.W, self.b]

        self.deltas = [self.W_delta, self.b_delta]

        lin_output = T.dot(self.input, self.W) + self.b

        if activation == 'tanh':
            self.output = T.tanh(lin_output)
        elif activation == 'sigmoid':
            self.output = nnet.sigmoid(lin_output)
        elif activation == 'relu':
            self.output = T.maximum(lin_output, 0)
        else:
            self.output = lin_output