Tensorflow Keras use encoder and decoder separately in autoencoder

Question

I'm messing around with the Keras api in tensorflow, attempting to implement an autoencoder. The sequential model works, but I want to be able to use the encoder (first two layers) and the decoder (last two layers) separately, but using the weights of my already trained model. Is there a way to do this? Do I have to make a custom model?

model = keras.Sequential()
model.add(encoder_1)
model.add(leaky_relu)
model.add(encoder_2)
model.add(leaky_relu2)
model.add(decoder_1)
model.add(leaky_relu3)
model.add(decoder_2)

encoder_model = keras.Sequential()
encoder_model.add(encoder_1)
encoder_model.add(leaky_relu)
encoder_model.add(encoder_2)
encoder_model.add(leaky_relu2)

decoder_model = keras.Sequential()
decoder_model.add(decoder_1)
model.add(leaky_relu3)
decoder_model.add(decoder_2)

I define my models like this but trying to run predict on either the encoder or decoder outputs

'Sequential' object has no attribute '_feed_input_names'

sdcbr · Accepted Answer · 2018-08-24T17:13:14.660

2

Yes, you should wrap the encoding and decoding layers in separate Model instances that you call separately. The Keras blogporst on autoencoders should contain everything you need to know: https://blog.keras.io/building-autoencoders-in-keras.html

edited Aug 24 '18 at 17:13

answered Jul 29 '18 at 07:37

sdcbr

7,021
3
27
44

1

This does not seem to work in tensorflow, I've edited my original post with a code sample and error – TheMagicalCake Jul 30 '18 at 18:25
1

You want to use the functional api, as in the example, and not the sequential api. – sdcbr Jul 31 '18 at 00:26
checkout [this answer](https://stackoverflow.com/a/54931203/4913143) on how to define and run encoder and decoder independently – Rodrigo Laguna Oct 15 '20 at 12:37

Tensorflow Keras use encoder and decoder separately in autoencoder

1 Answers1