1

With a model like this, how can one access the trained parameters like weight and bias of each layer?

model = Sequential ([
                Dense(xx, activation=cntk.sigmoid),
                Dense(outputs)])
z = model(features)

Thanks.

4

1 回答 1

2

本教程中显示了具体机制。这是显示如何访问参数的示例:

模型 = 创建模型()

打印(长度(模型层))

打印(model.layers[0].E.shape)

打印(model.layers[2].b.value)

于 2017-01-23T22:01:22.807 回答