我有一个运行良好的神经网络模型，但是我使用的是非常大的数据，并且尝试使用生成器来运行该模型，但是它给了我以下错误：
"UnimplementedError:
File "<ipython-input-63-352f4097b60f>", line 146, in <module>
validation_steps = len(df_valid)/batch_size, shuffle=True)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 1297, in fit_generator
steps_name='steps_per_epoch')
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_generator.py", line 265, in model_iteration
batch_outs = batch_function(*batch_data)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 973, in train_on_batch
class_weight=class_weight, reset_metrics=reset_metrics)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py", line 264, in train_on_batch
output_loss_metrics=model._output_loss_metrics)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py", line 311, in train_on_batch
output_loss_metrics=output_loss_metrics))
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py", line 252, in _process_single_batch
training=training))
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py", line 166, in _model_loss
per_sample_losses = loss_fn.call(targets[i], outs[i])
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\losses.py", line 221, in call
return self.fn(y_true, y_pred, **self._fn_kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\losses.py", line 978, in sparse_categorical_crossentropy
y_true, y_pred, from_logits=from_logits, axis=axis)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\backend.py", line 4530, in sparse_categorical_crossentropy
target = cast(target, 'int64')
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\backend.py", line 1571, in cast
return math_ops.cast(x, dtype)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\util\dispatch.py", line 180, in wrapper
return target(*args, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\ops\math_ops.py", line 704, in cast
x = gen_math_ops.cast(x, base_type, name=name)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\ops\gen_math_ops.py", line 2211, in cast
_six.raise_from(_core._status_to_exception(e.code, message), None)
File "<string>", line 3, in raise_from
UnimplementedError: Cast string to int64 is not supported [Op:Cast] name: loss/dense_38_loss/Cast/
发生器有什么问题？
import numpy as np
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from keras.preprocessing.text import Tokenizer
from keras.preprocessing import sequence
from keras.utils import np_utils
import pandas as pd
batch_size = 64
# Read in the training and validation data
df_train = pd.read_csv(r'C:\train.txt', sep='|', encoding='latin-1',
low_memory=False)
df_valid = pd.read_csv(r'C:\valid.txt', sep='|', encoding='latin-1',
low_memory=False)
print('training rows:', len(df_train))
print('validation rows:', len(df_valid))
def generator(df,vocab_size,batch_size, tokenizer,input_encoder,onehot):
n_examples = len(df)
number_of_batches = n_examples / batch_size
counter = 0
while 1:
start_index = counter * batch_size
end_index = start_index + batch_size
X_out1 = np.array(([batch_size, n_examples, vocab_size]), dtype=int)
if counter > number_of_batches + 1:
# reshuffle dataframe and start over
df.sample(frac=1).reset_index(drop=True)
counter = 0
counter += 1
X_out1 = tokenizer.texts_to_sequences(df.iloc[start_index: end_index]['var1'])
X_out1 = sequence.pad_sequences(X_out1, maxlen=200)
X_out2 = df.iloc[start_index: end_index][['var2','var3']]
X_out2 = input_encoder.transform(df.iloc[start_index: end_index][[ 'var2','var3']])
X_out2 = onehot.transform(df.iloc[start_index: end_index][[ 'var2','var3']])
Y_out = df.iloc[start_index: end_index]['code']
yield [X_out1, X_out2], [Y_out]
tokenizer = Tokenizer()
tokenizer.fit_on_texts(df_train['var1'])
input_encoder = MultiColumnLabelEncoder()
train_X2=df_train[['var2','var3']]
valid_X2 =df_valid[['var2','var3']]
input_encoder.fit(train_X2)
onehot = OneHotEncoder(sparse=False,categories='auto')
onehot.fit(train_X2)
code_type = 'code'
train_labels = df_train[code_type]
valid_labels = df_valid[code_type]
label_encoder = LabelEncoder()
labels = set(df_train[code_type].tolist() + df_valid[code_type].tolist())
label_encoder.fit(list(labels))
n_classes = len(set(labels))
print('n_classes = %s' % n_classes)
input_text = Input(shape=(200,), dtype='int32', name='input_text')
meta_input = Input(shape=(2,), name='meta_input')
embedding = Embedding(input_dim=len(tokenizer.word_index) + 1,
output_dim=300,
input_length=200)(input_text)
lstm = Bidirectional(LSTM(units=128,
dropout=0.5,
recurrent_dropout=0.5,
return_sequences=True),
merge_mode='concat')(embedding)
pool = GlobalMaxPooling1D()(lstm)
dropout = Dropout(0.5)(pool)
text_output = Dense(n_codes, activation='sigmoid', name='aux_output')(dropout)
output = concatenate([text_output, meta_input])
output = Dense(n_codes, activation='relu')(output)
main_output = Dense(n_codes, activation='softmax', name='main_output')(output)
model = Model(inputs=[input_text,meta_input], outputs=[output])
optimer = Adam(lr=.001)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
# Generators
train_generator = generator(df_train,vocab_size,batch_size, tokenizer,input_encoder,onehot)
validation_generator = generator(df_valid,vocab_size,batch_size, tokenizer,input_encoder,onehot)
model.summary()
model.fit_generator(generator=train_generator,
validation_data=validation_generator,
epochs=20,steps_per_epoch = len(df_train)/batch_size,
validation_steps = len(df_valid)/batch_size, shuffle=True)
答案 0 :(得分：0)
从我可以看到的问题是由于使用了CSV文件导致类型不匹配。从CSV读取的数字（标签）为字符串，并且不会自动转换为int。
这是您从CSV读取的预期输出（标签）：
Y_out = df.iloc[start_index: end_index]['code']
可能是字符串，请尝试打印Y_out.dtypes进行确认。
您模型的输出（预测）是一个一次性编码的标签，它是int64；类型不匹配发生在TF尝试计算损失值（从字符串中减去一个数字）时。