cnn_lstm.py 文件源码

def forward_prop_step(x_t, sentence_t, s_t1_prev, s_t2_prev):

    filtered_words = T.tanh(F.dot(sentence_t) + d)
    pooled_words = filtered_words.max(axis = 1)

    x_e = T.concatenate([x_t, pooled_words])

    # GRU Layer 1.
    z_t1 = T.nnet.hard_sigmoid(U_1[0].dot(x_e) + W[0].dot(s_t1_prev) + b[0])
    r_t1 = T.nnet.hard_sigmoid(U_1[1].dot(x_e) + W[1].dot(s_t1_prev) + b[1])
    c_t1 = T.tanh(U_1[2].dot(x_e) + W[2].dot(s_t1_prev * r_t1) + b[2])
    s_t1 = (T.ones_like(z_t1) - z_t1) * c_t1 + z_t1 * s_t1_prev

    # GRU Layer 2.
    z_t2 = T.nnet.hard_sigmoid(U_2[0].dot(s_t1) + W[3].dot(s_t2_prev) + b[3])
    r_t2 = T.nnet.hard_sigmoid(U_2[1].dot(s_t1) + W[4].dot(s_t2_prev) + b[4])
    c_t2 = T.tanh(U_2[2].dot(s_t1) + W[5].dot(s_t2_prev * r_t2) + b[5])
    s_t2 = (T.ones_like(z_t2) - z_t2) * c_t2 + z_t2 * s_t2_prev

    # Final output calculation.
    o_t = T.nnet.sigmoid(V.dot(s_t2) + c)

    return [o_t, s_t1, s_t2]