Question

我正在训练用于预测角色的PTB数据集（即角色级LSTM）训练批次的维度是[len（dataset）x vocabulary_size]。这里，vocabulary_size = 27（26 + 1 [对于unk令牌和空格或者fullstops。]）。
这是为批次输入（arrX）和标签（arrY）转换为one_hot的代码。

arrX = np.zeros((len(train_data), vocabulary_size), dtype=np.float32)
arrY = np.zeros((len(train_data)-1, vocabulary_size), dtype=np.float32)
for i, x in enumerate(train_data):
     arrX[i, x] = 1
arrY = arrX[1, :]

我在Graph中创建了一个输入（X）和标签（Y）的占位符，以将其传递给tflearn LSTM。以下是图形和会话的代码。

batch_size = 256
with tf.Graph().as_default():
    X = tf.placeholder(shape=(None, vocabulary_size), dtype=tf.float32)       
    Y = tf.placeholder(shape=(None, vocabulary_size), dtype=tf.float32)      
    print (utils.get_incoming_shape(tf.concat(0, Y)))
    print (utils.get_incoming_shape(X))
    net = tflearn.lstm(X, 512, return_seq=True)
    print (utils.get_incoming_shape(net))
    net = tflearn.dropout(net, 0.5)
    print (utils.get_incoming_shape(net))
    net = tflearn.lstm(net, 256)
    net = tflearn.fully_connected(net, vocabulary_size, activation='softmax')
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(net, Y))
    optimizer = tf.train.AdamOptimizer(learning_rate=0.01).minimize(loss)

init = tf.initialize_all_variables()

with tf.Session() as sess:
    sess.run(init)
    offset=0
    avg_cost = 0
    total_batch = (train_length-1) / 256
    print ("No. of batches:", '%d' %total_batch)
    for i in range(total_batch) :
        batch_xs, batch_ys = trainX[offset : batch_size + offset], trainY[offset : batch_size + offset]
        sess.run(optimizer, feed_dict={X: batch_xs, Y: batch_ys})
        cost = sess.run(loss, feed_dict={X: batch_xs, Y: batch_ys})
        avg_cost += cost/total_batch
        if i % 20 == 0:
            print("Step:", '%03d' % i, "Loss:", str(cost))
        offset += batch_size

所以，我收到以下错误assert ndim >= 3, "Input dim should be at least 3." AssertionError: Input dim should be at least 3.

我怎样才能resolve this error？有替代解决方案吗？我应该写单独的LSTM定义吗？

Answer 1

我不习惯这些数据集，但您是否尝试过将tflearn.input_data（shape）与tflearn.embedding图层一起使用？如果您使用嵌入，我认为您不必在三维中重塑数据。

Answer 2

lstm图层输入形状3-D Tensor [samples，timesteps，input dim]。您可以将输入数据重新整形为3D。在您的问题中，trainX的形状为[len(dataset) x vocabulary_size]。使用trainX = trainX.reshape( trainX.shape+ (1,))形状将更改为[len(dataset), vocabulary_size, 1]。通过输入占位符X中的简单更改，可以将此数据传递给lstm。通过X = tf.placeholder(shape=(None, vocabulary_size, 1), dtype=tf.float32)向占位符添加一个维度。

tflearn中LSTM的维度错误

2 个答案: