Question

我正在使用tensorflow的ctc_cost和ctc_greedy_decoder。当我训练模型最小化ctc_cost时，成本会下降，但是当我解码它时总是没有任何东西。这有可能发生吗？我的代码如下。

我想知道我是否正确预处理了数据。我预测fbank功能的给定帧上的电话的序列。有48个电话（48个类），每个帧有69个功能。我将num_classes设置为49，因此logits将具有维度(max_time_steps, num_samples, 49)。对于我的稀疏张量，我的值范围从0到47（48为空白保留）。我从未在数据中添加空白，我认为不应该这样做？（我应该做那样的事吗？）

经过训练后，每次迭代和时期后成本会降低，但编辑距离永远不会减少。实际上它保持在1，因为解码器几乎总是预测和清空序列。我有什么不对的吗？

graph = tf.Graph()
with graph.as_default():

    inputs  = tf.placeholder(tf.float32, [None, None, num_features])
    targets = tf.sparse_placeholder(tf.int32)
    seq_len = tf.placeholder(tf.int32, [None])
    seq_len_t = tf.placeholder(tf.int32, [None])
    cell = tf.contrib.rnn.LSTMCell(num_hidden)
    stack = tf.contrib.rnn.MultiRNNCell([cell] * num_layers)
    outputs, _ = tf.nn.dynamic_rnn(stack, inputs, seq_len, dtype=tf.float32)
    outputs, _ = tf.nn.dynamic_rnn(stack, inputs, seq_len, dtype=tf.float32)

    input_shape = tf.shape(inputs)
    outputs = tf.reshape(outputs, [-1, num_hidden])
    W = tf.Variable(tf.truncated_normal([num_hidden,
                                     num_classes],
                                    stddev=0.1))

    b = tf.Variable(tf.constant(0., shape=[num_classes]))


    logits = tf.matmul(outputs, W) + b

    logits = tf.reshape(logits, [input_shape[0], -1, num_classes])

    logits = tf.transpose(logits, (1, 0, 2))

    loss = tf.nn.ctc_loss(targets, logits, seq_len)
    cost = tf.reduce_mean(loss)

    decoded, log_probabilities = tf.nn.ctc_greedy_decoder(logits, seq_len, merge_repeated=True)
    optimizer = tf.train.MomentumOptimizer(initial_learning_rate, 0.1).minimize(cost)
    err = tf.reduce_mean(tf.edit_distance(tf.cast(decoded[0],tf.int32), targets))
    saver = tf.train.Saver()    

with tf.Session(graph=graph) as session:

    X, Y, ids, seq_length, label_to_int, int_to_label = get_data('train')

    session.run(tf.global_variables_initializer())

    print(seq_length)

    num_batches = len(X)//batch_size + 1



    for epoch in range(epochs):
        print ('epoch'+str(epoch))
        for batch in range(num_batches):
            input_X, target_input, seq_length_X = get_next_batch(batch,X, Y ,seq_length,batch_size)
            feed = {inputs: input_X ,
            targets: target_input,
            seq_len: seq_length_X}

            print ('epoch'+str(epoch))
            _, print_cost, print_er = session.run([optimizer, cost, err], feed_dict = feed)
            print('epoch '+ str(epoch)+' batch '+str(batch)+ ' cost: '+str(print_cost)+' er: '+str(print_er))

    save_path = saver.save(session, '/tmp/model.ckpt')
    print('model saved')

    X_t, ids_t, seq_length_t = get_data('test')

    feed_t = {inputs: X_t, seq_len: seq_length_t}   
    print(X.shape)
    print(X_t.shape)
    print(type(seq_length_t[0]))


    de, lo = session.run([decoded[0], log_probabilities],feed_dict = feed_t)
    with open('predict.pickle', 'wb') as f:
        pickle.dump((de, lo), f)

Answer 1

我遇到了同样的问题并通过提高初始学习率来解决。

此外，在验证集上输出LER对于检查培训过程的进度是必要的。

tensorflow - CTC损失减少但解码器输出空白

1 个答案: