python-3.x - 使用 LSTM 训练的模型仅预测所有值相同的值

Question

我有一个包含 4000 行和两列的数据集。第一列包含一些句子，第二列包含一些对应的数字。 大约有 4000 个句子，并按大约 100 个不同的数字进行分类。例如:

Sentences                                         Codes

Google headquarters is in California              87390
Steve Jobs was a great man                        70214
Steve Jobs has done great technology innovations  70214
Google pixel is a very nice phone                 87390
Microsoft is another great giant in technology    67012
Bill Gates founded Microsoft                      67012 

同样，包含这些句子的行共有 4000 行，这些行由 100 个这样的代码进行分类

我已经尝试了下面的代码，但是当我预测时，它为所有人预测一个相同的值。换句话说 y_pred 给出了一个相同值的数组。

请问代码哪里出了问题

import pandas as pd
import numpy as np

xl = pd.ExcelFile("dataSet.xlsx")
df = xl.parse('Sheet1') 

#df = df.sample(frac=1).reset_index(drop=True)# shuffling the dataframe


df = df.sample(frac=1).reset_index(drop=True)# shuffling the dataframe
X = df.iloc[:, 0].values
Y = df.iloc[:, 1].values

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
import pickle 

count_vect = CountVectorizer()
X = count_vect.fit_transform(X)

tfidf_transformer = TfidfTransformer()
X = tfidf_transformer.fit_transform(X)

X = X.toarray()

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
y = Y.reshape(-1, 1)  # Because Y has only one column

onehotencoder = OneHotEncoder(categories='auto')
Y = onehotencoder.fit_transform(y).toarray()


from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=0)

inputDataLength = len(X_test[0])
outputDataLength = len(Y[0])

from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from keras.layers import Dropout

# fitting the model
embedding_vector_length = 100
model = Sequential()
model.add(Embedding(outputDataLength,embedding_vector_length, input_length=inputDataLength))
model.add(Dropout(0.2))
model.add(LSTM(outputDataLength))
model.add(Dense(outputDataLength, activation='softmax'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=20)
y_pred = model.predict(X_test)
invorg = model.inverse_transform(y_test)
y_test = labelencoder_Y.inverse_transform(invorg)
inv = onehotencoder.inverse_transform(y_pred)
y_pred = labelencoder_Y.inverse_transform(inv)

Answer 1

即使您有 100 类，您仍在使用 binary_crossentropy。这不是正确的做法。您必须使用categorical_crossentropy来完成此任务。

像这样编译你的模型，

model.compile(loss='categorical_crossentropy'，optimizer='adam'，metrics=['accuracy'])

此外，您正在使用模型进行预测并转换为这样的类标签，

y_pred = model.predict(X_test)
inv = onehotencoder.inverse_transform(y_pred)
y_pred = labelencoder_Y.inverse_transform(inv)

由于您的模型是使用 softmax 激活的以便获取类标签，因此您必须找到预测的 argmax。

例如，如果预测为 [0.2, 0.3, 0.0005, 0.99]，您必须采用 argmax，这将为您提供输出 3。概率较高的类别。

所以你必须像这样修改预测代码，

y_pred = model.predict(X_test)
y_pred = np.argmax(y_pred, axis=1)
y_pred = labelencoder_Y.inverse_transform(y_pred)

invorg = np.argmax(y_test, axis=1)
invorg = labelencoder_Y.inverse_transform(invorg)

现在，您将在 invorg 中获得实际的类标签，并在 y_pred 中获得预测的类标签