在 TensorFlow 中设置循环神经网络时出现值错误

Question

我正在尝试构建一个循环神经网络

def setupRNN(self):
        "create RNN layers and return output of these layers"
        rnnIn3d = tf.squeeze(self.cnnOut4d, axis=[2])

        # basic cells which is used to build RNN
        numHidden = 256
        cells = [tf.contrib.rnn.LSTMCell(num_units=numHidden, state_is_tuple=True) for _ in range(2)] # 2 layers

        # stack basic cells
        stacked = tf.contrib.rnn.MultiRNNCell(cells, state_is_tuple=True)

        # bidirectional RNN

        ((fw, bw), _) = tf.nn.bidirectional_dynamic_rnn(cell_fw=stacked, cell_bw=stacked,
                                                        inputs=rnnIn3d,dtype=rnnIn3d.dtype)


        # BxTxH + BxTxH -> BxTx2H -> BxTx1X2H
        concat = tf.expand_dims(tf.concat([fw, bw], 2), 2)

        # project output to chars (including blank): BxTx1x2H -> BxTx1xC -> BxTxC
        kernel = tf.Variable(tf.truncated_normal([1, 1, numHidden * 2, len(self.charList) + 1], stddev=0.1))
        self.rnnOut3d = tf.squeeze(tf.nn.atrous_conv2d(value=concat, filters=kernel, rate=1, padding='SAME'),
                                       axis=[2])

它返回错误为

ValueError: Variable bidirectional_rnn/fw/multi_rnn_cell/cell_0/lstm_cell/kernel already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:

Answer 1

使用 tf.compat.v1.reset_default_graph() 并得到解决