The last step in this section will be to build a shell script called run_autoencoder.sh at the root of this directory and add the following:

#/bin/bash

# Run autoencoder step
xhost +
docker run -it 
   --runtime=nvidia 
   --rm 
   -e DISPLAY=$DISPLAY 
   -v /tmp/.X11-unix:/tmp/.X11-unix 
   -v $HOME/3d-gan-from-images/out:/out 
   -v $HOME/3d-gan-from-images/src:/src 
   ch8 python3 /src/encoder.py

To create the npy and model files, run the following command in the Terminal:

sudo ./run_autoencoder.sh

Now, we'll move on to building the core of the GAN architecture that will make use of these encodings.