CodeReclaimers / neat-python

Python implementation of the NEAT neuroevolution algorithm
BSD 3-Clause "New" or "Revised" License
1.41k stars 490 forks source link

neat/nn/feed_forward #230

Closed Shikamaru5 closed 2 years ago

Shikamaru5 commented 2 years ago

Trying to run my code, and when it hits net = neat.nn.FeedForwardNetwork.create(genome, config) it throws up this exception:

connections = [cg.key for cg in genome.connections.values() if cg.enabled]
AttributeError: 'list' object has no attribute 'connections'

It was throwing up an exception that said: Warning: initial_connection = full with hidden nodes will not do direct input-output connections;
if this is desired, set initial_connection = full_nodirect;
if not, set initial_connection = full_direct So when I saw this I set my hidden layers to 0 and now it only tells me the first part without giving me that warning, I have a huge set of inputs and outputs though, so might that be the problem?

idk if anybody else has come across this problem but I can't seem to find the solution and any help would be appreciated thanks.