Tensorflow - Get hidden layer output of an autoencoder

Question

I have a stacked autoencoder that is structured like 500-250-100-50-100-250-500. I now want to take out the 50-dimensional hidden layer and use it to classify my input data in 2 classes using a softmax layer.

That means I need my autoencoder to compress my 500-dimensional input vectors from my training dataset into 50-dimensional vectors and use it to train the softmax layer. In addition to that I also need the 50-dimensional hidden layer.

How I would get the hidden layer: autoencoder.layers[3]

But how do I get the compressed 50-dimensional vectors of the 500-dimensional input vectors? I would need to get the output of that hidden layer when using autoencoder.predict(x_train).

Kaveh · Accepted Answer · 2021-06-18 18:15:21Z

1

If you want to have another output from a hidden layer, you can get the output and add it to a new model like this:

new_model = tf.keras.Model(inputs=autoencoder.input, outputs=[autoencoder.layers[3].output, autoencoder.output])

Then you can get the predictions like this:

hidden_layer_pred, last_layer_pred = new_model.predict(x_train)

answered Jun 18, 2021 at 18:15

Kaveh

5,0112 gold badges23 silver badges36 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

abcdefghi019283 Over a year ago

Why would I need the autoencoder.output in tf.keras.Model? Wouldn't autoencoder.layers[3].output suffice?

Kaveh Over a year ago

If you want both of them in a one model, you can do like this. But if just hidden layer is enough for you, yes you can.

Collectives™ on Stack Overflow

Tensorflow - Get hidden layer output of an autoencoder

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related