[英]How to get my class prediction LSTM Keras
I recently trying to build a program, that classify Quora (question pair) dataset, whether it's duplicate or not. 我最近尝试构建一个程序,对Quora(问题对)数据集进行分类,无论它是否重复。 I got the accuracy and loss based on real y, but IDK how to proceed the output (predicted y) can anyone help me?
我得到了基于真实y的准确性和损失,但是IDK如何进行输出(预测y),有人可以帮助我吗? the output shud be 1 or 0 (binary class)
输出shud是1或0(二进制类)
This is the sentence merger code, training process use LSTM 这是句子合并代码,培训过程使用LSTM
merged = RNN(EMBED_HIDDEN_SIZE)(merged)
merged = layers.Dropout(dropoutp)(merged)
preds = layers.Dense(answer_size, activation='sigmoid')(merged)
model = Model([questiona, questionb], preds)
rmsprop = keras.optimizers.rmsprop(lr=lrn)
model.summary()
You can get the predictions by passing the test data to predict funtion 您可以通过传递测试数据来预测功能来获得预测
predictions=model.predict(X)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.