FailedPreconditionError: Table not initialized
FailedPreconditionError: Table not initialized
我正在尝试使用以下代码创建 NLP 神经网络：
进口：
import zipfile
import pandas as pd
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import TextVectorization,Embedding,Input,GlobalAveragePooling1D,Dense
from sklearn.model_selection import train_test_split
下载并解压数据集：
# Download data (same as from Kaggle)
!wget "https://storage.googleapis.com/ztm_tf_course/nlp_getting_started.zip"
# Unzip data
zip_ref = zipfile.ZipFile("nlp_getting_started.zip", "r")
zip_ref.extractall()
zip_ref.close()
将数据拆分为训练和测试数据集：
train_df = pd.read_csv("train.csv")
train_sentences, val_sentences, train_labels, val_labels = train_test_split(train_df['text'], train_df['target'],train_size=.8)
average_output_sequence_length = 15
创建神经网络：
input = Input(shape=(1,),dtype='string')
x = TextVectorization(max_tokens=10000,
ngrams=5,
standardize='lower_and_strip_punctuation',
output_mode='int',
output_sequence_length = average_output_sequence_length)(input)
x = Embedding(input_dim=22,embeddings_initializer='uniform',output_dim=128, name= 'embeding_layer')(x)
x = GlobalAveragePooling1D()(x)
output = Dense(1,activation='sigmoid')(x)
model = tf.keras.Model(input,output)
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'] )
model.fit(x=train_sentences,y=train_labels,epochs=6,validation_data=(val_sentences,val_labels))
不幸的是，当我 运行 代码时，我遇到以下错误：
Epoch 1/6
---------------------------------------------------------------------------
FailedPreconditionError Traceback (most recent call last)
<ipython-input-52-991547d73612> in <module>()
13 model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'] )
14
---> 15 model.fit(x=train_sentences,y=train_labels,epochs=6,validation_data=(val_sentences,val_labels))
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
57 ctx.ensure_initialized()
58 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 59 inputs, attrs, num_outputs)
60 except core._NotOkStatusException as e:
61 if name is not None:
FailedPreconditionError: Table not initialized.
[[node model_6/text_vectorization_7/string_lookup_7/None_Lookup/LookupTableFindV2
(defined at /usr/local/lib/python3.7/dist-packages/keras/layers/preprocessing/index_lookup.py:669)
]] [Op:__inference_train_function_5066]
Errors may have originated from an input operation.
更新：
当我改变我使用功能代码的方式时，我让它工作了：
创建 TextVectorization 函数：
text_vectorization_layer = TextVectorization(max_tokens=10000,
ngrams=5,
standardize='lower_and_strip_punctuation',
output_mode='int',
output_sequence_length = average_output_sequence_length
)
最后创建神经网络：
input = Input(shape=(1,),dtype='string')
x = text_vectorization_layer(input)
x = Embedding(input_dim=22,embeddings_initializer='uniform',output_dim=128, name= 'embeding_layer')(x)
x = GlobalAveragePooling1D()(x)
output = Dense(1,activation='sigmoid')(x)
model = tf.keras.Model(input,output)
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'] )
model.fit(x=train_sentences,y=train_labels,epochs=6,validation_data=(val_sentences,val_labels))
问题：
但是，我仍然不明白为什么这些更改可以解决问题？
换句话说，为什么：
x = TextVectorization(input)
和
x = TextVectorization(max_tokens=10000,
ngrams=5,
standardize='lower_and_strip_punctuation',
output_mode='int',
output_sequence_length = average_output_sequence_length)(input)
不等于?
TextVectorization层是预处理层，调用前需要实例化。也正如 docs 解释的那样：
The vocabulary for the layer must be either supplied on construction
or learned via adapt().
可以找到另一个重要信息here:
Crucially, these layers are non-trainable. Their state is not set during training; it must be set before training, either by initializing them from a precomputed constant, or by "adapting" them on data
此外，需要注意的是，TextVectorization 层使用底层 StringLookup 层，该层也需要预先初始化。否则，您将获得您发布的 FailedPreconditionError: Table not initialized。
我正在尝试使用以下代码创建 NLP 神经网络：
进口：
import zipfile
import pandas as pd
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import TextVectorization,Embedding,Input,GlobalAveragePooling1D,Dense
from sklearn.model_selection import train_test_split
下载并解压数据集：
# Download data (same as from Kaggle)
!wget "https://storage.googleapis.com/ztm_tf_course/nlp_getting_started.zip"
# Unzip data
zip_ref = zipfile.ZipFile("nlp_getting_started.zip", "r")
zip_ref.extractall()
zip_ref.close()
将数据拆分为训练和测试数据集：
train_df = pd.read_csv("train.csv")
train_sentences, val_sentences, train_labels, val_labels = train_test_split(train_df['text'], train_df['target'],train_size=.8)
average_output_sequence_length = 15
创建神经网络：
input = Input(shape=(1,),dtype='string')
x = TextVectorization(max_tokens=10000,
ngrams=5,
standardize='lower_and_strip_punctuation',
output_mode='int',
output_sequence_length = average_output_sequence_length)(input)
x = Embedding(input_dim=22,embeddings_initializer='uniform',output_dim=128, name= 'embeding_layer')(x)
x = GlobalAveragePooling1D()(x)
output = Dense(1,activation='sigmoid')(x)
model = tf.keras.Model(input,output)
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'] )
model.fit(x=train_sentences,y=train_labels,epochs=6,validation_data=(val_sentences,val_labels))
不幸的是，当我 运行 代码时，我遇到以下错误：
Epoch 1/6
---------------------------------------------------------------------------
FailedPreconditionError Traceback (most recent call last)
<ipython-input-52-991547d73612> in <module>()
13 model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'] )
14
---> 15 model.fit(x=train_sentences,y=train_labels,epochs=6,validation_data=(val_sentences,val_labels))
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
57 ctx.ensure_initialized()
58 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 59 inputs, attrs, num_outputs)
60 except core._NotOkStatusException as e:
61 if name is not None:
FailedPreconditionError: Table not initialized.
[[node model_6/text_vectorization_7/string_lookup_7/None_Lookup/LookupTableFindV2
(defined at /usr/local/lib/python3.7/dist-packages/keras/layers/preprocessing/index_lookup.py:669)
]] [Op:__inference_train_function_5066]
Errors may have originated from an input operation.
更新： 当我改变我使用功能代码的方式时，我让它工作了：
创建 TextVectorization 函数：
text_vectorization_layer = TextVectorization(max_tokens=10000,
ngrams=5,
standardize='lower_and_strip_punctuation',
output_mode='int',
output_sequence_length = average_output_sequence_length
)
最后创建神经网络：
input = Input(shape=(1,),dtype='string')
x = text_vectorization_layer(input)
x = Embedding(input_dim=22,embeddings_initializer='uniform',output_dim=128, name= 'embeding_layer')(x)
x = GlobalAveragePooling1D()(x)
output = Dense(1,activation='sigmoid')(x)
model = tf.keras.Model(input,output)
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'] )
model.fit(x=train_sentences,y=train_labels,epochs=6,validation_data=(val_sentences,val_labels))
问题：
但是，我仍然不明白为什么这些更改可以解决问题？
换句话说，为什么：
x = TextVectorization(input)
和
x = TextVectorization(max_tokens=10000,
ngrams=5,
standardize='lower_and_strip_punctuation',
output_mode='int',
output_sequence_length = average_output_sequence_length)(input)
不等于?
TextVectorization层是预处理层，调用前需要实例化。也正如 docs 解释的那样：
The vocabulary for the layer must be either supplied on construction or learned via adapt().
可以找到另一个重要信息here:
Crucially, these layers are non-trainable. Their state is not set during training; it must be set before training, either by initializing them from a precomputed constant, or by "adapting" them on data
此外，需要注意的是，TextVectorization 层使用底层 StringLookup 层，该层也需要预先初始化。否则，您将获得您发布的 FailedPreconditionError: Table not initialized。