1。概述
我正在使用Conv1d进行文本分类任务。我定义了第一个输入层，如
Input(shape=(self.input_size,), name='sent_input', dtype='int64') # here input_size is 1014。我正在使用
(143614,)X将(143614,)形状的numpy ndarray作为Y形成numpy ndarray作为batch_size与128{{1}的keras拟合函数}}。但它引发了一个奇怪的错误
ValueError: Error when checking input: expected sent_input to have shape (1014,) but got array with shape (1,)
2。我的输入概述（我如何生成输入）：
我实际上正在this repository之后制作一个基于字符的cnn文本分类算法。我的原始数据框看起来像这样
|id| text | class_target(0 or 1)|
------------------------------------
|54| some text1| 0
------------------------------------
|55| some text2| 1
数据处理
class Data(object):
"""
Class to handle loading and processing of raw datasets.
"""
def __init__(self, data_source,
alphabet="abcdefghijklmnopqrstuvwxyz0123456789-,;.!?:'\"/\\|_@#$%^&*~`+-=<>()[]{}",
input_size=1014, batch_size=128, no_of_classes=1):
"""
Initialization of a Data object.
Args:
data_source (str): Raw data file path
alphabet (str): Alphabet of characters to index
input_size (int): Size of input features
batch_size (int): Batch size
no_of_classes (int): Number of classes in data
"""
self.alphabet = alphabet
self.alphabet_size = len(self.alphabet)
self.dict = {} # Maps each character to an integer
self.no_of_classes = no_of_classes
for idx, char in enumerate(self.alphabet):
self.dict[char] = idx + 1
self.length = input_size
self.batch_size = batch_size
self.data_source = data_source
def load_data(self):
self.data = pd.read_csv(self.data_source)
print("Data loaded from " + self.data_source)
def get_all_data(self):
return self.data['text'].apply(lambda x : self.str_to_indexes(x)).values,self.data['class_target'].values
def str_to_indexes(self, s):
"""
Convert a string to character indexes based on character dictionary.
Args:
s (str): String to be converted to indexes
Returns:
str2idx (np.ndarray): Indexes of characters in s
"""
s = s.lower()
max_length = min(len(s), self.length)
str2idx = np.zeros(self.length, dtype='int64')
for i in range(1, max_length + 1):
c = s[-i]
if c in self.dict:
str2idx[i - 1] = self.dict[c]
return str2idx
在调用keras fit方法之前，我将这些函数称为
training_data = Data(data_source=data_config.training_data_source,
alphabet=data_config.alphabet,
input_size=data_config.input_size,
batch_size=128,
no_of_classes=data_config.num_of_classes)
training_data.load_data()
training_inputs, training_labels = training_data.get_all_data()
training_inputs = training_inputs.values
training_labels = training_labels.values
通过这种方式，我得到了输入。它的形状是（143614，）
第3。以下是模型概述
inputs = Input(shape=(self.input_size,), name='sent_input', dtype='int64') # here input_size is 1014
# Embedding layers
x = Embedding(self.alphabet_size + 1, self.embedding_size, input_length=self.input_size)(inputs)
# Convolution layers
for cl in self.conv_layers:
x = Convolution1D(cl[0], cl[1])(x)
x = ThresholdedReLU(self.threshold)(x)
if not cl[2] is None:
x = MaxPooling1D(cl[2])(x)
x = Flatten()(x)
# Fully connected layers
for fl in self.fully_connected_layers:
x = Dense(fl)(x)
x = ThresholdedReLU(self.threshold)(x)
x = Dropout(self.dropout_p)(x)
# Output layer
predictions = Dense(self.num_of_classes, activation='sigmoid')(x) # here num_of_classes is 1
# Build and compile model
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer=self.optimizer, loss=self.loss)
4.这是我的健康功能
model.fit(training_inputs, training_labels,
validation_data=(validation_inputs, validation_labels),
epochs=epochs,
batch_size=batch_size, # Here batch_size is 128
verbose=2,
callbacks=[tensorboard])
5.这是模型摘要
Layer (type) Output Shape Param #
=================================================================
sent_input (InputLayer) (None, 1014) 0
_________________________________________________________________
embedding_21 (Embedding) (None, 1014, 128) 8960
_________________________________________________________________
conv1d_121 (Conv1D) (None, 1008, 256) 229632
_________________________________________________________________
thresholded_re_lu_161 (Thres (None, 1008, 256) 0
_________________________________________________________________
max_pooling1d_61 (MaxPooling (None, 336, 256) 0
_________________________________________________________________
conv1d_122 (Conv1D) (None, 330, 256) 459008
_________________________________________________________________
thresholded_re_lu_162 (Thres (None, 330, 256) 0
_________________________________________________________________
max_pooling1d_62 (MaxPooling (None, 110, 256) 0
_________________________________________________________________
conv1d_123 (Conv1D) (None, 108, 256) 196864
_________________________________________________________________
thresholded_re_lu_163 (Thres (None, 108, 256) 0
_________________________________________________________________
conv1d_124 (Conv1D) (None, 106, 256) 196864
_________________________________________________________________
thresholded_re_lu_164 (Thres (None, 106, 256) 0
_________________________________________________________________
conv1d_125 (Conv1D) (None, 104, 256) 196864
_________________________________________________________________
thresholded_re_lu_165 (Thres (None, 104, 256) 0
_________________________________________________________________
conv1d_126 (Conv1D) (None, 102, 256) 196864
_________________________________________________________________
thresholded_re_lu_166 (Thres (None, 102, 256) 0
_________________________________________________________________
max_pooling1d_63 (MaxPooling (None, 34, 256) 0
_________________________________________________________________
flatten_21 (Flatten) (None, 8704) 0
_________________________________________________________________
dense_61 (Dense) (None, 1024) 8913920
_________________________________________________________________
thresholded_re_lu_167 (Thres (None, 1024) 0
_________________________________________________________________
dropout_41 (Dropout) (None, 1024) 0
_________________________________________________________________
dense_62 (Dense) (None, 1024) 1049600
_________________________________________________________________
thresholded_re_lu_168 (Thres (None, 1024) 0
_________________________________________________________________
dropout_42 (Dropout) (None, 1024) 0
_________________________________________________________________
dense_63 (Dense) (None, 1) 1025
=================================================================
Total params: 11,449,601
Trainable params: 11,449,601
Non-trainable params: 0
5。这是错误追溯
ValueErrorTraceback (most recent call last)
<ipython-input-118-29fc7a1b6318> in <module>()
----> 1 execfile('main.py')
/content/main.py in <module>()
65 epochs=training_config.epochs,
66 batch_size=training_config.batch_size,
---> 67 checkpoint_every=training_config.checkpoint_every)
/content/zhang_char_cnn.py in train(self, training_inputs, training_labels, validation_inputs, validation_labels, epochs, batch_size, checkpoint_every)
102 batch_size=batch_size,
103 verbose=2,
--> 104 callbacks=[tensorboard])
105
106 def test(self, testing_inputs, testing_labels, batch_size):
/usr/local/lib/python2.7/dist-packages/keras/engine/training.pyc 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, **kwargs)
1635 sample_weight=sample_weight,
1636 class_weight=class_weight,
-> 1637 batch_size=batch_size)
1638 # Prepare validation data.
1639 do_validation = False
/usr/local/lib/python2.7/dist-packages/keras/engine/training.pyc in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
1481 self._feed_input_shapes,
1482 check_batch_axis=False,
-> 1483 exception_prefix='input')
1484 y = _standardize_input_data(y, self._feed_output_names,
1485 output_shapes,
/usr/local/lib/python2.7/dist-packages/keras/engine/training.pyc in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
121 ': expected ' + names[i] + ' to have shape ' +
122 str(shape) + ' but got array with shape ' +
--> 123 str(data_shape))
124 return data
125
ValueError: Error when checking input: expected sent_input to have shape (1014,) but got array with shape (1,)
回应轰鸣声评论为什么我要喂一个（143614，）numpy ndarray。我是角色标签CNN的新手。我只是关注这个Github repo。据我所知，我将我的文本转换为数字表示，然后将其输入模型。在字符CNN中我必须量化文本，我从该回购中获取量化部分。完成所有这些预处理之后，如果我在数据上调用.shape，我就会将功能提供给模型，它会显示此(143614,)
我显然正在喂(143614,)形状numpy ndarray，但shape (1,)来自哪里。 有人可以帮我解决这个问题 。我在Google上搜索并在Stackoverflow中检查了很多Q＆amp; A但是没有找到解决我问题的方法。