List structure obtained by keras model.get_weights ()

I had an opportunity to apply the weights obtained by learning with keras to my own neural network, so I investigated it.

About model.get_weights ()

The Keras Documentation says:

model.get_weights (): Returns a list of all model weight tensors (Numpy arrays).

So this function returns a list of multiple Numpy arrays, which represents the weight of the training result. However, it was not mentioned here what weight this part of the essential list points to in the neural network.

Survey results

As a result of trial and error such as setting the weight obtained in my own neural network and various searches, I found that it has such a structure. The meaning of the symbols and the structure of the neural network are based on the figure in Reference.

## list[0]
[[w11(1) w12(1)]
 [w21(1) w22(1)]]
## list[1]
[w10(1) w20(1)]
## list[2]
[[w11(2)]
 [w12(2)]]
## list[3]
[w10(2)]

Summary

In the case of a three-layer fully connected neural network, in order from list [0], the input layer → the weight to the intermediate layer, the bias input to the intermediate layer, the intermediate layer → the weight to the output layer, and the bias input to the output layer. It seems.

reference

http://ni4muraano.hatenablog.com/entry/2017/02/01/000000 https://keras.io/ja/models/about-keras-models/ https://groups.google.com/forum/#!topic/keras-users/kLm-bTvDTaw

Recommended Posts

List structure obtained by keras model.get_weights ()
Machine Sommelier by Keras-
About batch_size specified by keras