cans.py 文件源码

def __call__(self,i):
        # assume hidden, input is of shape [batch,num_h] and [batch,num_in]
        hidden = i[0]
        inp = i[1]
        wz,wr,w = self.wz,self.wr,self.w
        dims = tf.rank(inp)
        c = tf.concat([hidden,inp],axis=dims-1)
        z = tf.sigmoid(wz(c))
        r = tf.sigmoid(wr(c))
        h_c = tf.tanh(w(tf.concat([hidden*r,inp],axis=dims-1)))
        h_new = (1-z) * hidden + z * h_c
        return h_new

# GRU2 as reported in *Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks*
# the gates are now only driven by hidden state.
# mod: removed reset gate.
# conclusion 20171220: GRU2(without reset gate) is almost as good as GRU.