Question

我正在进行核心学习。我必须创建一个大小为3的n_gram模型。为此我使用了sklearn的HashingVectorizer。然后我必须使用keras来创建神经网络。但是我不确定如何输入输入形状

vec = HashingVectorizer(decode_error = 'ignore', n_features = 2**20, ngram_range = (3,3))
X = vec.fit_transform(tags)
y = np_utils.to_categorical(tag)


print(X.shape)
print(y.shape)


model = Sequential()
model.add(Dense(1024, input_shape = (1,X.shape[1]), activation = 'softmax'))
model.add(Dense(y.shape[1], activation = 'softmax'))

model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
model.fit(X, y, epochs = 10, batch_size = 200)

我的第二次编辑：在这里，几乎所有的东西都是一样的，它仍然会抛出错误。代码是：

from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.neural_network import MLPClassifier
from sklearn.feature_extraction import FeatureHasher
from sklearn.preprocessing import OneHotEncoder, LabelEncoder
from keras.models import Sequential
from keras.layers.recurrent import LSTM, GRU, SimpleRNN
from keras.layers import Dense
from keras.utils import np_utils
from numpy import array
from scipy.sparse import csr_matrix

text = open('eng.train').read().lower().split()
X_train = []
y_train = []

for i in range (len(text)):
    if i % 4 == 0:
        X_train.append(text[i])
    if i % 4 == 1:
        y_train.append(text[i])

unq_tags = []
for i in range(len(y_train)):
    if y_train[i] not in unq_tags:
        unq_tags.append(y_train[i])
 #hashing X_train       
vec = HashingVectorizer(decode_error = 'ignore', n_features = 2**15)
X = vec.fit_transform(X_train)
X.toarray()
#one hot encoding y_train
values = array(y_train)
label_encoder = LabelEncoder()
integer_encoded = label_encoder.fit_transform(values)
encoded = np_utils.to_categorical(integer_encoded)

print(type(X))
print(X.shape)
print(type(encoded))
print(encoded.shape)

model = Sequential()
model.add(SimpleRNN(1024, input_shape = (X.shape[1],), activation = 'softmax'))
model.add(Dense(y.shape[1], activation = 'softmax'))
model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
model.fit(X, y, epochs = 20, batch_size = 200)

它抛出的错误如下：

class 'scipy.sparse.csr.csr_matrix'>
(204567, 32768)
<class 'numpy.ndarray'>
(204567, 46)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-58-4ac701f1ade4> in <module>()
     47 '''
     48 model = Sequential()
---> 49 model.add(SimpleRNN(1024, input_shape = (X.shape[1],), activation = 'softmax'))
     50 model.add(Dense(y.shape[1], activation = 'softmax'))
     51 model.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])

/home/manish/anaconda3/lib/python3.6/site-packages/keras/models.py in add(self, layer)
    420                 # and create the node connecting the current layer
    421                 # to the input layer we just created.
--> 422                 layer(x)
    423 
    424             if len(layer.inbound_nodes) != 1:

/home/manish/anaconda3/lib/python3.6/site-packages/keras/layers/recurrent.py in __call__(self, inputs, initial_state, **kwargs)
    250             else:
    251                 kwargs['initial_state'] = initial_state
--> 252         return super(Recurrent, self).__call__(inputs, **kwargs)
    253 
    254     def call(self, inputs, mask=None, initial_state=None, training=None

):

/home/manish/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py in __call__(self, inputs, **kwargs)
    509                 # Raise exceptions in case the input is not compatible
    510                 # with the input_spec specified in the layer constructor.
--> 511                 self.assert_input_compatibility(inputs)
    512 
    513                 # Collect input shapes to build layer.

home/manish/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py in assert_input_compatibility(self, inputs)
    411                                      self.name + ': expected ndim=' +
    412                                      str(spec.ndim) + ', found ndim=' +
--> 413                                      str(K.ndim(x)))
    414             if spec.max_ndim is not None:
    415                 ndim = K.ndim(x)

ValueError: Input 0 is incompatible with layer simple_rnn_8: expected ndim=3, found ndim=2

我只做了一些调整但是我收到了这个错误

Answer 1

指定input_shape = (1,X.shape[1])时，模型需要输入维[n_samples, 1, 1048576]。这是3个维度。但是您的实际数据只有2个维度。因此，您应该从input_shape中删除1。

尝试input_shape = (X.shape[1],)

请查看documentation以了解它。

n_gram模型HashingVectorizer并将其与keras一起使用

1 个答案: