steffen/self-replicating-neural-networks
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor:

Browse Source 
Step 6: Experiments
This commit is contained in:
Si11ium
2019-06-14 18:32:38 +02:00
parent 4a81279b58
commit 5dfbfcaa20
15 changed files with 78 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
code/setups/soup_trajectorys.py
View File

@@ -10,23 +10,22 @@ from experiment import *
if __name__ == '__main__':
if True:
with SoupExperiment("soup") as exp:
for run_id in range(1):
net_generator = lambda: TrainingNeuralNetworkDecorator(WeightwiseNeuralNetwork(2, 2)) \
.with_keras_params(activation='linear').with_params(epsilon=0.0001)
# net_generator = lambda: TrainingNeuralNetworkDecorator(AggregatingNeuralNetwork(4, 2, 2))\
# .with_keras_params(activation='linear')
# net_generator = lambda: TrainingNeuralNetworkDecorator(FFTNeuralNetwork(4, 2, 2))\
# .with_keras_params(activation='linear')
# net_generator = lambda: RecurrentNeuralNetwork(2, 2).with_keras_params(activation='linear').with_params()
soup = Soup(20, net_generator).with_params(remove_divergent=True, remove_zero=True,
train=30,
learn_from_rate=-1)
soup.seed()
for _ in tqdm(range(100)):
soup.evolve()
exp.log(soup.count())
# you can access soup.historical_particles[particle_uid].states[time_step]['loss']
# or soup.historical_particles[particle_uid].states[time_step]['weights']
# from soup.dill
exp.save(soup=soup.without_particles())
with SoupExperiment(namne="soup") as exp:
net_generator = lambda: TrainingNeuralNetworkDecorator(WeightwiseNeuralNetwork(2, 2)) \
.with_keras_params(activation='linear').with_params(epsilon=0.0001)
# net_generator = lambda: TrainingNeuralNetworkDecorator(AggregatingNeuralNetwork(4, 2, 2))\
# .with_keras_params(activation='linear')
# net_generator = lambda: TrainingNeuralNetworkDecorator(FFTNeuralNetwork(4, 2, 2))\
# .with_keras_params(activation='linear')
# net_generator = lambda: RecurrentNeuralNetwork(2, 2).with_keras_params(activation='linear').with_params()
soup = Soup(20, net_generator).with_params(remove_divergent=True, remove_zero=True,
train=30,
learn_from_rate=-1)
soup.seed()
for _ in tqdm(range(100)):
soup.evolve()
exp.log(soup.count())
# you can access soup.historical_particles[particle_uid].states[time_step]['loss']
# or soup.historical_particles[particle_uid].states[time_step]['weights']
# from soup.dill
exp.save(soup=soup.without_particles())