使用keras做多标签分类

发布时间：2020-12-14 04:45:19 所属栏目：大数据来源：网络整理

导读：In short Don‘t use? softmax . Use? sigmoid ?for activation of your output layer. Use? binary_crossentropy ?for loss function. Use? predict ?for evaluation. Why In? softmax ?when increasing score for one label,all others are lowered (it‘s

In short

Don‘t use?softmax.

Use?sigmoid?for activation of your output layer.

Use?binary_crossentropy?for loss function.

Use?predict?for evaluation.

Why

In?softmax?when increasing score for one label,all others are lowered (it‘s a probability distribution). You don‘t want that when you have multiple labels.

Complete Code

from keras.models import Sequential
from keras.layers import Dense,Dropout,Activation
from keras.optimizers import SGD

model = Sequential()
model.add(Dense(5000,activation=‘relu‘,input_dim=X_train.shape[1]))
model.add(Dropout(0.1))
model.add(Dense(600,activation=‘relu‘))
model.add(Dropout(0.1))
model.add(Dense(y_train.shape[1],activation=‘sigmoid‘))

sgd = SGD(lr=0.01,decay=1e-6,momentum=0.9,nesterov=True)
model.compile(loss=‘binary_crossentropy‘,optimizer=sgd)

model.fit(X_train,y_train,epochs=5,batch_size=2000)

preds = model.predict(X_test)
preds[preds>=0.5] = 1
preds[preds<0.5] = 0
# score = compare preds and y_test

Ref：

https://medium.com/@vijayabhaskar96/multi-label-image-classification-tutorial-with-keras-imagedatagenerator-cd541f8eaf24
How does Keras handle multilabel classification?
Guide To Multi-Class Multi-Label Classification With Neural Networks In Python
Multi-label classification with Keras

（编辑：李大同）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!