I got this error when training gru model TypeError: unsupported operand type(s) for *: 'int' and 'NoneType'

Question

使用 Scikit Learn Keras 和 TensorFlow 进行机器学习实践的代码，2019 年第 2 版

import tensorflow as tf
from tensorflow import keras

from __future__ import print_function
from keras.callbacks import LambdaCallback
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.optimizers import RMSprop
from keras.utils.data_utils import get_file
import numpy as np
import random
import sys
import io
import gzip
import urllib

shakespeare_url = "https://homl.info/shakespeare" # shortcut URL
filepath = keras.utils.get_file("shakespeare.txt", shakespeare_url)
with open(filepath) as f:
    shakespeare_text = f.read()

tokenizer = keras.preprocessing.text.Tokenizer(char_level=True)
tokenizer.fit_on_texts([shakespeare_text])

max_id = len(tokenizer.word_index) # number of distinct characters
dataset_size = tokenizer.document_count # total number of characters

[encoded] = np.array(tokenizer.texts_to_sequences([shakespeare_text])) - 1
train_size = dataset_size * 90 // 100
dataset = tf.data.Dataset.from_tensor_slices(encoded[:train_size])
n_steps = 100
window_length = n_steps + 1 # target = input shifted 1 character ahead
dataset = dataset.window(window_length, shift=1, drop_remainder=True)

dataset = dataset.flat_map(lambda window: window.batch(window_length))
batch_size = 32
dataset = dataset.shuffle(10000).batch(batch_size)
dataset = dataset.map(lambda windows: (windows[:, :-1], windows[:, 1:]))

dataset = dataset.map(
    lambda X_batch, Y_batch: (tf.one_hot(X_batch, depth=max_id), Y_batch))
dataset = dataset.prefetch(1)

model = keras.models.Sequential([
    keras.layers.GRU(128, return_sequences=True, input_shape=[None, max_id],
                     dropout=0.2, recurrent_dropout=0.2),
    keras.layers.GRU(128, return_sequences=True,
                     dropout=0.2, recurrent_dropout=0.2),
    keras.layers.TimeDistributed(keras.layers.Dense(max_id, 
                                                    activation="softmax"))
])
model.compile(loss="sparse_categorical_crossentropy", optimizer="adam")

history = model.fit(dataset, epochs=20)

当执行 history = model.fit(dataset, epochs=20) 它给我 1/Unknown - 3s 3s/step 和错误 TypeError：* 不支持的操作数类型：'int' 和 'NoneType'

Answer 1

我已经重现了您的错误，错误不在于数据或任何包，而是您尝试使用 tokenizer.fit_on_texts().
将分词器安装到您的数据上的方式由于您已经在字符串中形成了数据，因此您需要直接使用字符串数据而不是在列表中进行调整。

我修改了你的代码，运行没有任何错误。

import tensorflow as tf
from tensorflow import keras

from __future__ import print_function
from keras.callbacks import LambdaCallback
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.optimizers import RMSprop
from keras.utils.data_utils import get_file
import numpy as np
import random
import sys
import io
import gzip
import urllib 

shakespeare_url = "https://homl.info/shakespeare" # shortcut URL
filepath = keras.utils.get_file("shakespeare.txt", shakespeare_url)
with open(filepath) as f:
    shakespeare_text = f.read() 


tokenizer = keras.preprocessing.text.Tokenizer(char_level=True)
#tokenizer.fit_on_texts(shakespeare_text) old line with text input as a list.
tokenizer.fit_on_texts(shakespeare_text)



max_id = len(tokenizer.word_index) # number of distinct characters
dataset_size = tokenizer.document_count # total number of characters

[encoded] = np.array(tokenizer.texts_to_sequences([shakespeare_text])) - 1
train_size = dataset_size * 90 // 100
dataset = tf.data.Dataset.from_tensor_slices(encoded[:train_size])
n_steps = 100
window_length = n_steps + 1 # target = input shifted 1 character ahead
dataset = dataset.window(window_length, shift=1, drop_remainder=True)

dataset = dataset.flat_map(lambda window: window.batch(window_length))
batch_size = 32
dataset = dataset.shuffle(10000).batch(batch_size)
dataset = dataset.map(lambda windows: (windows[:, :-1], windows[:, 1:]))

dataset = dataset.map(
    lambda X_batch, Y_batch: (tf.one_hot(X_batch, depth=max_id), Y_batch))
dataset = dataset.prefetch(1) 


model = keras.models.Sequential([
    keras.layers.GRU(128, return_sequences=True, input_shape=[None, max_id],
                     dropout=0.2, recurrent_dropout=0.2),
    keras.layers.GRU(128, return_sequences=True,
                     dropout=0.2, recurrent_dropout=0.2),
    keras.layers.TimeDistributed(keras.layers.Dense(max_id, 
                                                    activation="softmax"))
])
model.compile(loss="sparse_categorical_crossentropy", optimizer="adam")

history = model.fit(dataset,steps_per_epoch=train_size // batch_size, epochs=20)

由于是大数据，考虑到时间消耗，我无法在此处提供输出。

训练中：

Epoch 1/20
  138/31370 [..............................] - ETA: 3:47:54 - loss: 2.8267

I got this error when training gru model TypeError: unsupported operand type(s) for *: 'int' and 'NoneType'

I got this error when training gru model TypeError: unsupported operand type(s) for *: 'int' and 'NoneType'

python

training-data

deep-learning

keras

tensorflow

使用 Scikit Learn Keras 和 TensorFlow 进行机器学习实践的代码，2019 年第 2 版