Machine learning 卷积网络用于文本分类
我正在尝试用Keras训练一个卷积神经网络,用于识别有关烹饪的堆栈交换问题的标签 我的数据集的第i个问题元素如下所示:Machine learning 卷积网络用于文本分类,machine-learning,nlp,deep-learning,keras,Machine Learning,Nlp,Deep Learning,Keras,我正在尝试用Keras训练一个卷积神经网络,用于识别有关烹饪的堆栈交换问题的标签 我的数据集的第i个问题元素如下所示: id 2 title How should I cook bacon in an oven? content <p>I've heard of people cooking bacon in an ov... t
id 2
title How should I cook bacon in an oven?
content <p>I've heard of people cooking bacon in an ov...
tags oven cooking-time bacon
Name: 1, dtype: object
这表示我的输入向量。我也有矢量化的标签,并为输入和标签提取密集矩阵
tags = [" ".join(x) for x in dataframes['cooking']['tags']]
Xd = X.todense()
Y = vectorizer.fit_transform(tags)
Yd = Y.todense()
将数据拆分为训练集和验证集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(Xd, Yd, test_size=0.33, random_state=42)
现在我正在尝试训练一个Conv1D网络
from keras.models import Sequential
from keras.layers import Dense, Activation,Flatten
from keras.layers import Conv2D, MaxPooling2D,Conv1D, Embedding,GlobalMaxPooling1D,Dropout,MaxPooling1D
model = Sequential()
model.add(Embedding(Xd.shape[1],
128,
input_length=Xd.shape[1]))
model.add(Conv1D(32,5,activation='relu'))
model.add(MaxPooling1D(100,stride=50))
model.add(Conv1D(32,5,activation='relu'))
model.add(GlobalMaxPooling1D())
model.add(Dense(Yd.shape[1], activation ='softmax'))
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(X_train, y_train, batch_size=32,verbose=1)
但它的准确率非常低,而且它显示出随着时代的发展,损失几乎没有增加
Epoch 1/10
10320/10320 [==============================] - 401s - loss: 15.8098 - acc: 0.0604
Epoch 2/10
10320/10320 [==============================] - 339s - loss: 15.5671 - acc: 0.0577
Epoch 3/10
10320/10320 [==============================] - 314s - loss: 15.5509 - acc: 0.0578
Epoch 4/10
10320/10320 [==============================] - 34953s - loss: 15.5493 - acc: 0.0578
Epoch 5/10
10320/10320 [==============================] - 323s - loss: 15.5587 - acc: 0.0578
Epoch 6/10
6272/10320 [=================>............] - ETA: 133s - loss: 15.6005 - acc: 0.0550
你的损失函数值的方向不对。这意味着您的模型无法捕获需要关注的功能。有两种方法可以尝试
可以通过对文本进行词干分析来减少特征。可以通过处理诸如“wooooow”之类的词来实现进一步的缩减,这些词被认为是“哇”或“looooove”,后者指的是“爱”。同时我也希望大家把所有的文字放低,这将把“爱”和“爱”统一为一个特征。
Epoch 1/10
10320/10320 [==============================] - 401s - loss: 15.8098 - acc: 0.0604
Epoch 2/10
10320/10320 [==============================] - 339s - loss: 15.5671 - acc: 0.0577
Epoch 3/10
10320/10320 [==============================] - 314s - loss: 15.5509 - acc: 0.0578
Epoch 4/10
10320/10320 [==============================] - 34953s - loss: 15.5493 - acc: 0.0578
Epoch 5/10
10320/10320 [==============================] - 323s - loss: 15.5587 - acc: 0.0578
Epoch 6/10
6272/10320 [=================>............] - ETA: 133s - loss: 15.6005 - acc: 0.0550