ValueError: Variable rnnlm/multi_rnn_cell/cell_0/basic_lstm_cell/kernel already exists, disallowed.

布满荆棘的人生 2022-04-18 00:19 323阅读 0赞

报错：  
ValueError: Variable rnnlm/multi\_rnn\_cell/cell\_0/basic\_lstm\_cell/kernel already exists, disallowed.

原因：**模型重用**

解决方法：在构建图的代码块上加上**with tf.Graph().as\_default():**

graph = tf.Graph()
    with graph.as_default():
    
        #定义输入,输出
        x=tf.placeholder(dtype=tf.float32,shape=[None,sequence_length*frame_size],name="inputx")
        y=tf.placeholder(dtype=tf.float32,shape=[None,n_classes],name="expected_y")
        #定义权值
        weights=tf.Variable(tf.truncated_normal(shape=[hidden_num,n_classes]))
        bias=tf.Variable(tf.zeros(shape=[n_classes]))
    
        # 定义RNN网络
        def RNN(x,weights,bias):
            '''返回[batch_size,n_classes]'''
            x=tf.reshape(x,shape=[-1,sequence_length,frame_size])
    # rnn_cell=tf.nn.rnn_cell.BasicRNNCell(hidden_num) # RNN/LSTM/GRU在此处选择BasicRNNCell/BasicLSTMCell/GRUCell。该网络中包含一个深度RNN网络，这个RNN包含hidden_num个隐层单元/RNN cell
            rnn_cell = tf.nn.rnn_cell.MultiRNNCell([tf.nn.rnn_cell.GRUCell(hidden_num) for _ in range(3)]) # 构建多层RNN/LSTM/GRU网络,3表示3层（这里都是用MultiRNNCell，没有MultiGRUCell等）
        
            output,states=tf.nn.dynamic_rnn(rnn_cell,x,dtype=tf.float32)
            return tf.nn.softmax(tf.matmul(output[:,-1,:],weights)+bias,1)
    
        # 计算预计输出
        predy=RNN(x,weights,bias)
        # 定义损失函数和优化算法
        cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=predy,labels=y))
        train=tf.train.AdamOptimizer(train_rate).minimize(cost)
        # 计算accuracy
        correct_pred=tf.equal(tf.argmax(predy,1),tf.argmax(y,1))
        accuracy=tf.reduce_mean(tf.to_float(correct_pred))
    
    
    ## 开始训练
    with tf.Session(graph=graph) as sess:
        print('step','accuracy','loss')
        sess.run(tf.initialize_all_variables())
        step=1
        testx,testy=mnist.test.next_batch(batch_size)
        while step<train_step:
            batch_x,batch_y=mnist.train.next_batch(batch_size)
        # batch_x=tf.reshape(batch_x,shape=[batch_size,sequence_length,frame_size])
            _loss,__=sess.run([cost,train],feed_dict={ x:batch_x,y:batch_y})
            if step % display_step ==0:
                acc,loss=sess.run([accuracy,cost],feed_dict={ x:testx,y:testy})
                print(step,acc,loss)
    
            step+=1

这样就不会报错了。