tensorflow - 值错误 : List argument 'values' to 'ConcatV2' Op with length 0 shorter than minimum length 2

Question

我是 TF 的新手，并开始通过 TF 教程学习它。我只是简单地从 TF 站点复制了 Swivel 模型，并尝试运行它，但是，我收到一条错误消息:
回溯(最近调用最后):

文件“C:\Users\jhan\Desktop\tensorflow prac\swivel\swivel.py”，第 362 行，位于 tf.app.run()

文件“C:\Users\jhan\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\platform\app.py”，第 44 行，在运行中 _sys.exit(main(_sys.argv[:1] + flags_passthrough))

文件“C:\Users\jhan\Desktop\tensorflow prac\swivel\swivel.py”，第 289 行，在 main 模型 = SwivelModel(FLAGS)

init 中的文件“C:\Users\jhan\Desktop\tensorflow prac\swivel\swivel.py”，第 257 行 l2_loss = tf.reduce_mean(tf.concat(axis=0, values=l2_losses), 0,

文件“C:\Users\jhan\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\array_ops.py”，第 1034 行，concat 名字=名字)

文件“C:\Users\jhan\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\gen_array_ops.py”，第 519 行，在 _concat_v2 名字=名字)

文件“C:\Users\jhan\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py”，第 546 行，在 apply_op (input_name, op_type_name, len(values), num_attr.minimum))

ValueError:列出参数“values”到“ConcatV2”Op，长度 0 短于最小长度 2..

我的代码是:

class SwivelModel(object):

 def __init__(self, config):
    """Construct graph for dmc."""
    self._config = config
# Create paths to input data files
log('Reading model from: %s', config.input_base_path)
count_matrix_files = glob.glob(config.input_base_path + '/shard-*.pb')
row_sums_path = config.input_base_path + '/row_sums.txt'
col_sums_path = config.input_base_path + '/col_sums.txt'

# Read marginals
row_sums = read_marginals_file(row_sums_path)
col_sums = read_marginals_file(col_sums_path)

self.n_rows = len(row_sums)
self.n_cols = len(col_sums)
log('Matrix dim: (%d,%d) SubMatrix dim: (%d,%d)',
    self.n_rows, self.n_cols, config.submatrix_rows, config.submatrix_cols)
self.n_submatrices = (self.n_rows * self.n_cols /
                      (config.submatrix_rows * config.submatrix_cols))
log('n_submatrices: %d', self.n_submatrices)

with tf.device('/cpu:0'):
  # ===== CREATE VARIABLES ======
  # Get input
  global_row, global_col, count = count_matrix_input(
    count_matrix_files, config.submatrix_rows, config.submatrix_cols)

  # Embeddings
  self.row_embedding = embeddings_with_init(
    embedding_dim=config.embedding_size,
    vocab_size=self.n_rows,
    name='row_embedding')
  self.col_embedding = embeddings_with_init(
    embedding_dim=config.embedding_size,
    vocab_size=self.n_cols,
    name='col_embedding')
  tf.summary.histogram('row_emb', self.row_embedding)
  tf.summary.histogram('col_emb', self.col_embedding)

  matrix_log_sum = math.log(np.sum(row_sums) + 1)
  row_bias_init = [math.log(x + 1) for x in row_sums]
  col_bias_init = [math.log(x + 1) for x in col_sums]
  self.row_bias = tf.Variable(
      row_bias_init, trainable=config.trainable_bias)
  self.col_bias = tf.Variable(
      col_bias_init, trainable=config.trainable_bias)
  tf.summary.histogram('row_bias', self.row_bias)
  tf.summary.histogram('col_bias', self.col_bias)

  # Add optimizer
  l2_losses = []
  sigmoid_losses = []
  self.global_step = tf.Variable(0, name='global_step')
  opt = tf.train.AdagradOptimizer(config.learning_rate)

  all_grads = []

devices = ['/gpu:%d' % i for i in range(FLAGS.num_gpus)] \
    if FLAGS.num_gpus > 0 else get_available_gpus()
self.devices_number = len(devices)
with tf.variable_scope(tf.get_variable_scope()):
  for dev in devices:
    with tf.device(dev):
      with tf.name_scope(dev[1:].replace(':', '_')):
        # ===== CREATE GRAPH =====
        # Fetch embeddings.
        selected_row_embedding = tf.nn.embedding_lookup(
            self.row_embedding, global_row)
        selected_col_embedding = tf.nn.embedding_lookup(
            self.col_embedding, global_col)

        # Fetch biases.
        selected_row_bias = tf.nn.embedding_lookup(
            [self.row_bias], global_row)
        selected_col_bias = tf.nn.embedding_lookup(
            [self.col_bias], global_col)

        # Multiply the row and column embeddings to generate predictions.
        predictions = tf.matmul(
            selected_row_embedding, selected_col_embedding,
            transpose_b=True)

        # These binary masks separate zero from non-zero values.
        count_is_nonzero = tf.to_float(tf.cast(count, tf.bool))
        count_is_zero = 1 - count_is_nonzero

        objectives = count_is_nonzero * tf.log(count + 1e-30)
        objectives -= tf.reshape(
            selected_row_bias, [config.submatrix_rows, 1])
        objectives -= selected_col_bias
        objectives += matrix_log_sum

        err = predictions - objectives

        # The confidence function scales the L2 loss based on the raw
        # co-occurrence count.
        l2_confidence = (config.confidence_base +
                         config.confidence_scale * tf.pow(
                             count, config.confidence_exponent))

        l2_loss = config.loss_multiplier * tf.reduce_sum(
            0.5 * l2_confidence * err * err * count_is_nonzero)
        l2_losses.append(tf.expand_dims(l2_loss, 0))

        sigmoid_loss = config.loss_multiplier * tf.reduce_sum(
            tf.nn.softplus(err) * count_is_zero)
        sigmoid_losses.append(tf.expand_dims(sigmoid_loss, 0))

        loss = l2_loss + sigmoid_loss
        grads = opt.compute_gradients(loss)
        all_grads.append(grads)

with tf.device('/cpu:0'):
  # ===== MERGE LOSSES =====
  l2_loss = tf.reduce_mean(tf.concat(axis=0, values=l2_losses), 0,
                           name="l2_loss")
  sigmoid_loss = tf.reduce_mean(tf.concat(axis=0, values=sigmoid_losses), 0,
                                name="sigmoid_loss")
  self.loss = l2_loss + sigmoid_loss
  average = tf.train.ExponentialMovingAverage(0.8, self.global_step)
  loss_average_op = average.apply((self.loss,))
  tf.summary.scalar("l2_loss", l2_loss)
  tf.summary.scalar("sigmoid_loss", sigmoid_loss)
  tf.summary.scalar("loss", self.loss)

  # Apply the gradients to adjust the shared variables.
  apply_gradient_ops = []
  for grads in all_grads:
    apply_gradient_ops.append(opt.apply_gradients(
        grads, global_step=self.global_step))

  self.train_op = tf.group(loss_average_op, *apply_gradient_ops)
  self.saver = tf.train.Saver(sharded=True)

Answer 1

我不太清楚错误在哪里但是:

查看代码，错误是说 l2_losses 是空的。在此行之前放置一个 print 语句，以检查 l2_losses 的值:

print(l2_losses) # new print statement
l2_loss = tf.reduce_mean(tf.concat(axis=0, values=l2_losses), 0,
                           name="l2_loss")

该代码应该开箱即用，那么您对代码做了什么吗？