python - 为什么我会收到“ValueError：此模型尚未构建”？[以下教程]

Question

我正在关注本教程： SLES 15 上的https://www.tensorflow.org/text/tutorials/text_generation。运行代码时出现以下错误。

Traceback (most recent call last):
  File "ml2.py", line 107, in <module>
    model.summary()
  File "/usr/lib/python3.6/site-packages/keras/engine/training.py", line 2521, in summary
    raise ValueError('This model has not yet been built. '
ValueError: This model has not yet been built. Build the model first by calling `build()` or calling `fit()` with some data, or specify an `input_shape` argument in the first layer(s) for automatic build.

奇怪的是，它在没有我调用 build 或 fit 的情况下以某种方式工作。我搜索了教程，它没有提到任何关于构建或拟合或 input_shape 的内容。我搞砸了什么让它停止工作？

import tensorflow as tf
from tensorflow.keras.layers.experimental import preprocessing

import numpy as np
import os
import time
path_to_file = tf.keras.utils.get_file('namefile.txt', 'https://raw.githubusercontent.com/redrover9/nameGenerator/master/fakeNames.txt')
# Read, then decode for py2 compat.
text = open(path_to_file, 'rb').read().decode(encoding='utf-8')
# length of text is the number of characters in it
print(f'Length of text: {len(text)} characters')
# Take a look at the first 250 characters in text
print(text[:250])
# The unique characters in the file
vocab = sorted(set(text))
print(f'{len(vocab)} unique characters')
example_texts = ['abcdefg', 'xyz']

chars = tf.strings.unicode_split(example_texts, input_encoding='UTF-8')
chars
ids_from_chars = preprocessing.StringLookup(
    vocabulary=list(vocab), mask_token=None)
ids = ids_from_chars(chars)
ids
chars_from_ids = tf.keras.layers.experimental.preprocessing.StringLookup(
    vocabulary=ids_from_chars.get_vocabulary(), invert=True, mask_token=None)
chars = chars_from_ids(ids)
chars
tf.strings.reduce_join(chars, axis=-1).numpy()
def text_from_ids(ids):
  return tf.strings.reduce_join(chars_from_ids(ids), axis=-1)
all_ids = ids_from_chars(tf.strings.unicode_split(text, 'UTF-8'))
all_ids
ids_dataset = tf.data.Dataset.from_tensor_slices(all_ids)
for ids in ids_dataset.take(10):
    print(chars_from_ids(ids).numpy().decode('utf-8'))
seq_length = 100
examples_per_epoch = len(text)//(seq_length+1)
sequences = ids_dataset.batch(seq_length+1, drop_remainder=True)

for seq in sequences.take(1):
    print(chars_from_ids(seq))
for seq in sequences.take(5):
    print(text_from_ids(seq).numpy())
def split_input_target(sequence):
    input_text = sequence[:-1]
    target_text = sequence[1:]
    return input_text, target_text
split_input_target(list("Tensorflow"))
dataset = sequences.map(split_input_target)
for input_example, target_example in dataset.take(1):
    print("Input :", text_from_ids(input_example).numpy())
    print("Target:", text_from_ids(target_example).numpy())
# Batch size
BATCH_SIZE = 64

# Buffer size to shuffle the dataset
# (TF data is designed to work with possibly infinite sequences,
# so it doesn't attempt to shuffle the entire sequence in memory. Instead,
# it maintains a buffer in which it shuffles elements).
BUFFER_SIZE = 10000

dataset = (
    dataset
    .shuffle(BUFFER_SIZE)
    .batch(BATCH_SIZE, drop_remainder=True)
    .prefetch(tf.data.experimental.AUTOTUNE))

dataset
# Length of the vocabulary in chars
vocab_size = len(vocab)

# The embedding dimension
embedding_dim = 256

# Number of RNN units
rnn_units = 1024
class MyModel(tf.keras.Model):
  def __init__(self, vocab_size, embedding_dim, rnn_units):
    super().__init__(self)
    self.embedding = tf.keras.layers.Embedding(vocab_size, embedding_dim)
    self.gru = tf.keras.layers.GRU(rnn_units,
                                   return_sequences=True,
                                   return_state=True)
    self.dense = tf.keras.layers.Dense(vocab_size)

  def call(self, inputs, states=None, return_state=False, training=False):
    x = inputs
    x = self.embedding(x, training=training)
    if states is None:
      states = self.gru.get_initial_state(x)
    x, states = self.gru(x, initial_state=states, training=training)
    x = self.dense(x, training=training)

    if return_state:
      return x, states
    else:
      return x
model = MyModel(
    # Be sure the vocabulary size matches the `StringLookup` layers.
    vocab_size=len(ids_from_chars.get_vocabulary()),
    embedding_dim=embedding_dim,
    rnn_units=rnn_units)
for input_example_batch, target_example_batch in dataset.take(1):
    example_batch_predictions = model(input_example_batch)
    print(example_batch_predictions.shape, "# (batch_size, sequence_length, vocab_size)")

model.summary()

标签： pythontensorflowkeras