0
$\begingroup$

I am training a variational autoencoder and I am getting a loss-plot as follows:

enter image description here

Rigt after epoch 224, val-loss overtakes train-loss and sort of getting bigger but at an extremely slow pace as you can notice. I trained for 300 epochs.

Any opinion about the training. I don't think it is overfitting the data. But I want to be sure and hence seeking opinion from the data science community.

Thanks.

$\endgroup$
1
$\begingroup$

You tagged your question with vae, so I will assume that this is a variational autoencoder. In that case, your loss has 2 components: reconstruction error and KL divergence of the bottleneck distribution, probably balanced with a weight $\beta$. You should plot both components separately in order to understand how the training dynamics evolve. The reconstruction loss is what will tell you if there's overfitting. The KL divergence will tell you if there is posterior collapse.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.