from keras.models import Model
from keras.layers import *
#inp is a "tensor", that can be passed when calling other layers to produce an output
inp = Input((10,)) #supposing you have ten numeric values as input
#here, SomeLayer() is defining a layer,
#and calling it with (inp) produces the output tensor x
x = SomeLayer(blablabla)(inp)
x = SomeOtherLayer(blablabla)(x) #here, I just replace x, because this intermediate output is not interesting to keep
#here, I want to keep the two different outputs for defining the model
#notice that both left and right are called with the same input x, creating a fork
out1 = LeftSideLastLayer(balbalba)(x)
out2 = RightSideLastLayer(banblabala)(x)
#here, you define which path you will follow in the graph you've drawn with layers
#notice the two outputs passed in a list, telling the model I want it to have two outputs.
model = Model(inp, [out1,out2])
model.compile(optimizer = ...., loss = ....) #loss can be one for both sides or a list with different loss functions for out1 and out2
model.fit(inputData,[outputYLeft, outputYRight], epochs=..., batch_size=...)

Keras中的多个输出

共 1 个回答
高赞
时间
活跃
0

新手导航
- 社区规范
- 提出问题
- 进行投票
- 个人资料
- 优化问题
- 回答问题
0
给定一个预测变量向量时,我有一个问题要处理两个输出。假设预测变量矢量看起来像
x1, y1, att1, att2, ..., attn
,它表示x1, y1
是坐标,而att's
是附加到x1, y1
坐标出现的其他属性。基于这个预测变量集,我想预测x2, y2
。这是一个时间序列问题,我正在尝试使用多元回归解决。我的问题是如何设置keras,这可以在最后一层给我2个输出。我已经解决了keras中的简单回归问题,并且代码在我的github中可用。