tensorflow - 关于 tensorflow 教程“model()”与“model.predict()”的问题

Question

为什么我将“predictions = model(input_eval)”更改为“predictions = model.predict(input_eval)”时出现错误：

CancelledError: [Op:StatefulPartitionedCall]

这是代码

def generate_text(model, start_string):
  # Evaluation step (generating text using the learned model)

  # Number of characters to generate
  num_generate = 1000

  # Converting our start string to numbers (vectorizing) 
  input_eval = [char2idx[s] for s in start_string]
  input_eval = tf.expand_dims(input_eval, 0)

  # Empty string to store our results
  text_generated = []

  # Low temperatures results in more predictable text.
  # Higher temperatures results in more surprising text.
  # Experiment to find the best setting.
  temperature = 1.0

  # Here batch size == 1
  model.reset_states()
  for i in range(num_generate):
      predictions = model(input_eval)
      # remove the batch dimension
      predictions = tf.squeeze(predictions, 0)

      # using a multinomial distribution to predict the word returned by the model
      predictions = predictions / temperature
      predicted_id = tf.multinomial(predictions, num_samples=1)[-1,0].numpy()

      # We pass the predicted word as the next input to the model
      # along with the previous hidden state
      input_eval = tf.expand_dims([predicted_id], 0)

      text_generated.append(idx2char[predicted_id])

  return (start_string + ''.join(text_generated))

链接：https ://colab.research.google.com/drive/1hoEHMCQrZYFJnNoWzRNTmPjQUFrPvTWy

标签： tensorflow