如何使用Tensorflow张量设置功能模型的Keras层的输入?

问题描述：

我有两个要使用的软件包，一个是用Keras1.2编写的，另一个是用tensorflow编写的.我想将在tensorflow中构建的架构的一部分用于Keras模型中.

I have two packages I'd like to use, one is written in Keras1.2, and the other one in tensorflow. I'd like to use a part of the architecture that is built in tensorflow into a Keras model.

建议部分解决方案

A partial solution is suggested here, but it's for a sequential model. The suggestion regarding functional models - wrapping the pre-processing in a Lambda layer - didn't work.

以下代码有效:

inp = Input(shape=input_shape)
def ID(x):
    return x
lam = Lambda(ID)  
flatten = Flatten(name='flatten')
output = flatten(lam(inp))
Model(input=[inp], output=output)

但是，当用预处理的输出张量flatten(lam(TF_processed_layer))替换flatten(lam(inp))时，我得到:模型的输出张量必须是Keras张量.找到:Tensor("Reshape:0"，shape =(?, ?)，dtype = float32)"

But, when replacing flatten(lam(inp)) with a pre-processed output tensor flatten(lam(TF_processed_layer)), I got: "Output tensors to a Model must be Keras tensors. Found: Tensor("Reshape:0", shape=(?, ?), dtype=float32)"

答

您没有为Keras正确定义您的lamba. 尝试这样的事情

You are not defining your lamba correctly for Keras. Try something like this

def your_lambda_layer(x):
    x -= K.mean(x, axis=1, keepdims=True)
    x = K.l2_normalize(x, axis=1)
    return x

....
model.add(Lambda(your_lambda_layer))

看到您正在使用功能性API

of seeing you are using the Functional API like this

def your_lambda_layer(x):
    x -= K.mean(x, axis=1, keepdims=True)
    x = K.l2_normalize(x, axis=1)
    return x

....
x = SomeLayerBeforeLambda(options...)(x)
x = (Lambda(your_lambda_layer))(x)

但是，即使这样，lambda层也可能无法变平，因此请打印出lambda的形状并对其进行观察，看看它是什么.

But even so, the lambda layer may not be able to be flattened so printout the shape of the lambda and take a look at it and see what it is.

如何使用Tensorflow张量设置功能模型的Keras层的输入?

相关推荐