chenmingxiang110 / growing-neural-cellular-automata

A reproduction of growing neural cellular automata using PyTorch.

Growing-Neural-Cellular-Automata

An unofficial reproduction of Growing Neural Cellular Automata using PyTorch:

Mordvintsev, et al., "Growing Neural Cellular Automata", Distill, 2020.

Run "training.ipynb" to train a model, and "main_pygame_dl.py" to play the demo (A pre-trained model is already given, see ./models).

growing-neural-cellular-automata's Issues

RuntimeError when loading the model

Hi, I was new to torch, and I have no idea what is wrong with my code. I used your Jupiter notebook to train the model. When I try to load and do the inference, an error message showed up:

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location='cpu' to map your storages to the CPU.

How to solve this problem?

Regarding the update rule

I have been following this GitHub repository. Can you explain why you decided to use fully connected layers? Why not use 2D convolutional layers instead?