预取数据集对象没有属性“ndim”

Question

我正在使用下面的代码使用GRU预测下一个单词。

import numpy as np
shakespeare_url = "https://homl.info/shakespeare"
filepath = keras.utils.get_file("shakespeare.txt",shakespeare_urlspeare_url)

with open(filepath) as f:
    shakespeare_txt = f.read()
    
tokenizer = keras.preprocessing.text.Tokenizer(char_level=True)
tokenizer.fit_on_texts(shakespeare_txt)
max_id = len(tokenizer.word_index) ## Number of distinct words
dataset_size = tokenizer.document_count ## total number of character
[encoded] = np.array(tokenizer.texts_to_sequences([shakespeare_txt])) - 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
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)

低于异常。请帮我解决这个问题？？

AttributeError Traceback(最近一次调用),在-

c:\ users \ dixit \ appdata \ local \ programs \ python \ python 38 \ lib \ site-packages \ keras \ engine \ training . py in fit(self，x，y，batch_size，epochs，verbose，callbacks，validation_split，validation_data，shuffle，class_weight，sample_weight，initial_epoch，steps_per_epoch，validation_steps，validation_freq，max_queue_size，workers，use_multiprocessing，**kwargs) 1148 1149 #情况2:符号张量-

C：\user\dixit\appdata\local\Program\python\python38\lib\site-包\keras\引擎\training.py_standardize_user_data（self， x， y，sample_weight，class_weight，check_array_lengths，batch_size）572 573#标准化输入。--

c： \users\dixit\appdata\local\programs\python\python38\lib\site packages\keras\engine\training_utils。py在标准化输入数据（数据、名称、形状、检查批处理轴、异常前缀）97数据=数据。值，如果是data.class。名称=='DataFrame'否则数据98数据=[data]---

C：\user\dixit\appdata\local\Program\python\python38\lib\site-包\keras\引擎\training_utils.pyin（.0）97 data=data.valuesifdata.class.name=='DataFrame'e data 98 data=[data]---

c:\ users \ dixit \ appdata \ local \ programs \ python \ python 38 \ lib \ site-packages \ keras \ engine \ training _ utils . py in standard ization _ single _ array(x)32 ' get tensor with shape:% s ' % str(shape)]33 return x-

属性错误：“预取数据集”对象没有属性“ndim”

Answer 1

确保从tenorflow导入keras并使用版本2.2.4-tf。得到了同样的错误，这对我有用。

from tensorflow import keras
keras.__version__

2.2.4-tf