I am struggling with the cifar10 autoencoder model training. The loss goes down, but the accuracy does not go up.

As a starting point, I use the architecture of the CNN autoencoder used for FashionMNIST in Lab 4 of this week. So far I have experimented with the following:

more conv2d layers

less conv2d layers

kernel size tweaking

pool size tweaking

number of filters tweaking

more epochs
As well as several combinations of those. Always keeping in mind the symmetrical shape of the architecture.

Are there any parameters that I have overlooked, which could help in increasing the accuracy?

If its a matter of model design then you also need Batchnormalizations and and an upsampling layer. I think the structure of the notebook and the model is similar to the labs of that week.

I figured it out, turned out I simply forgot to take into account that these pictures are colour pictures, and thus the number of filters of the last Conv2D layer was incorrect.
After changing that number it worked well.

This was a great find. Forgot we were only working with grayscale in the lab. Man, so much of deep learning comes down to counting shapes of tensors its funny.