Tensorflow 形状必须为秩1，但“CTCLoss”的秩为0（op:“CTCLoss”）

我已成功地用以下代码将张量转换为SparseTensor：

def dense_to_sparse(dense_tensor, out_type):
    indices = tf.where(tf.not_equal(dense_tensor, tf.constant(0, dense_tensor.dtype)
    values = tf.gather_nd(dense_tensor, indices)
    shape = tf.shape(dense_tensor, out_type=out_type)
    return tf.SparseTensor(indices, values, shape)

我想尝试使用由密集传感器转换而来的SparseTensor：

input_layer = tf.placeholder(tf.float32, [None, 1596, 48])
dense_labels = tf.placeholder(tf.int32)
sparse_from_dense = dense_to_sparse(dense_lables, out_type=tf.int64)
cell_fw = grid_rnn.Grid2LSTMCell(num_units=128)
cell_bw = grid_rnn.Grid2LSTMCell(num_units=128)
bidirectional_grid_rnn = tf.nn.bidirectional_dynamic_rnn(cell_fw, cell_bw, input_layer, dtype=tf.float32)
outputs = tf.reshape(bidirectional_grid_rnn[0], [-1, 256])

W = tf.Variable(tf.truncated_normal([256, 80], stddev=0.1, dtype=tf.float32), name='W')
b = tf.Variable(tf.constant(0., dtype=tf.float32, shape=[80], name='b'))

logits = tf.matmul(outputs, W) + b
logits = tf.reshape(logits, [tf.shape(input_layer)[0], -1, 80])
logits = tf.transpose(logits, (1, 0, 2))

loss = tf.nn.ctc_loss(inputs=logits, labels=sparse, sequence_length=320)

不幸的是，在执行此操作时，我遇到了以下错误：

Shape must be rank 1 but is rank 0 for 'CTCLoss' (op: 'CTCLoss') with input shapes: [?,?,80], [?,1], [?], [].

---

如何修复此错误？

来自Tensorflow文档

序列长度：一维int32向量，大小[批次大小]。序列长度

因此，您需要传递长度为batch_size的数组/向量，而不是整数