layers.py 文件源码

def gru_layer(tparams, state_below, init_state, options, prefix='gru', mask=None, **kwargs):
    """
    Feedforward pass through GRU
    """
    nsteps = state_below.shape[0]
    if state_below.ndim == 3:
        n_samples = state_below.shape[1]
    else:
        n_samples = 1

    dim = tparams[_p(prefix,'Ux')].shape[1]

    if init_state == None:
        init_state = tensor.alloc(0., n_samples, dim)

    if mask == None:
        mask = tensor.alloc(1., state_below.shape[0], 1)

    def _slice(_x, n, dim):
        if _x.ndim == 3:
            return _x[:, :, n*dim:(n+1)*dim]
        return _x[:, n*dim:(n+1)*dim]

    state_below_ = tensor.dot(state_below, tparams[_p(prefix, 'W')]) + tparams[_p(prefix, 'b')]
    state_belowx = tensor.dot(state_below, tparams[_p(prefix, 'Wx')]) + tparams[_p(prefix, 'bx')]
    U = tparams[_p(prefix, 'U')]
    Ux = tparams[_p(prefix, 'Ux')]

    def _step_slice(m_, x_, xx_, h_, U, Ux):
        preact = tensor.dot(h_, U)
        preact += x_

        r = tensor.nnet.sigmoid(_slice(preact, 0, dim))
        u = tensor.nnet.sigmoid(_slice(preact, 1, dim))

        preactx = tensor.dot(h_, Ux)
        preactx = preactx * r
        preactx = preactx + xx_

        h = tensor.tanh(preactx)

        h = u * h_ + (1. - u) * h
        h = m_[:,None] * h + (1. - m_)[:,None] * h_

        return h

    seqs = [mask, state_below_, state_belowx]
    _step = _step_slice

    rval, updates = theano.scan(_step,
                                sequences=seqs,
                                outputs_info = [init_state],
                                non_sequences = [tparams[_p(prefix, 'U')],
                                                 tparams[_p(prefix, 'Ux')]],
                                name=_p(prefix, '_layers'),
                                n_steps=nsteps,
                                profile=False,
                                strict=True)
    rval = [rval]
    return rval