116 lines
4.3 KiB
Python
116 lines
4.3 KiB
Python
from networks.auto_encoder import *
|
|
import os
|
|
import time
|
|
from networks.variational_auto_encoder import *
|
|
from networks.adverserial_auto_encoder import *
|
|
from networks.seperating_adversarial_auto_encoder import *
|
|
from networks.modules import LightningModule
|
|
from torch.optim import Adam
|
|
from torch.utils.data import DataLoader
|
|
from pytorch_lightning import data_loader
|
|
from dataset import DataContainer
|
|
|
|
from torch.nn import BatchNorm1d
|
|
from pytorch_lightning import Trainer
|
|
from test_tube import Experiment
|
|
|
|
# ToDo: How to implement this better?
|
|
# other_classes = [AutoEncoder, AutoEncoderLightningOverrides]
|
|
class Model(VariationalAutoEncoderLightningOverrides, LightningModule):
|
|
|
|
def __init__(self, dataParams: dict):
|
|
super(Model, self).__init__()
|
|
self.dataParams = dataParams
|
|
self.network = VariationalAutoEncoder(self.dataParams)
|
|
|
|
def configure_optimizers(self):
|
|
return [Adam(self.parameters(), lr=0.02)]
|
|
|
|
@data_loader
|
|
def tng_dataloader(self):
|
|
return DataLoader(DataContainer('data', **self.dataParams), shuffle=True, batch_size=100)
|
|
|
|
|
|
class AdversarialModel(AdversarialAELightningOverrides, LightningModule):
|
|
|
|
@property
|
|
def name(self):
|
|
return self.network.name
|
|
|
|
def __init__(self, dataParams: dict):
|
|
super(AdversarialModel, self).__init__()
|
|
self.dataParams = dataParams
|
|
self.normal = Normal(0, 1)
|
|
self.network = AdversarialAutoEncoder(self.dataParams)
|
|
pass
|
|
|
|
# This is Fucked up, why do i need to put an additional empty list here?
|
|
def configure_optimizers(self):
|
|
return [Adam(self.network.discriminator.parameters(), lr=0.02),
|
|
Adam([*self.network.encoder.parameters(), *self.network.decoder.parameters()], lr=0.02)],\
|
|
[]
|
|
|
|
@data_loader
|
|
def tng_dataloader(self):
|
|
return DataLoader(DataContainer('data', **self.dataParams), shuffle=True, batch_size=100)
|
|
|
|
|
|
class SeparatingAdversarialModel(SeparatingAdversarialAELightningOverrides, LightningModule):
|
|
|
|
def __init__(self, latent_dim, dataParams: dict):
|
|
super(SeparatingAdversarialModel, self).__init__()
|
|
self.latent_dim = latent_dim
|
|
self.dataParams = dataParams
|
|
self.normal = Normal(0, 1)
|
|
self.network = SeperatingAdversarialAutoEncoder(self.latent_dim, self.dataParams)
|
|
pass
|
|
|
|
# This is Fucked up, why do i need to put an additional empty list here?
|
|
def configure_optimizers(self):
|
|
return [Adam([*self.network.spatial_discriminator.parameters(), *self.network.spatial_encoder.parameters()]
|
|
, lr=0.02),
|
|
Adam([*self.network.temporal_discriminator.parameters(), *self.network.temporal_encoder.parameters()]
|
|
, lr=0.02),
|
|
Adam([*self.network.temporal_encoder.parameters(),
|
|
*self.network.spatial_encoder.parameters(),
|
|
*self.network.decoder.parameters()]
|
|
, lr=0.02)], []
|
|
|
|
@data_loader
|
|
def tng_dataloader(self):
|
|
return DataLoader(DataContainer('data', **self.dataParams), shuffle=True, batch_size=100)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
features = 6
|
|
latent_dim = 4
|
|
model = SeparatingAdversarialModel(latent_dim=latent_dim, dataParams=dict(refresh=False, size=5, step=5,
|
|
features=features, transforms=[BatchNorm1d(features)]
|
|
)
|
|
)
|
|
|
|
# PyTorch summarywriter with a few bells and whistles
|
|
outpath = os.path.join(os.getcwd(), 'output', model.name, time.asctime().replace(' ', '_').replace(':', '-'))
|
|
os.makedirs(outpath, exist_ok=True)
|
|
exp = Experiment(save_dir=outpath)
|
|
|
|
from pytorch_lightning.callbacks import ModelCheckpoint
|
|
|
|
checkpoint_callback = ModelCheckpoint(
|
|
filepath=os.path.join(outpath, 'weights.ckpt'),
|
|
save_best_only=True,
|
|
verbose=True,
|
|
monitor='val_loss',
|
|
mode='min',
|
|
|
|
)
|
|
|
|
trainer = Trainer(experiment=exp, checkpoint_callback=checkpoint_callback, max_nb_epochs=15) # gpus=[0...LoL]
|
|
trainer.fit(model)
|
|
trainer.save_checkpoint(os.path.join(outpath, 'weights.ckpt'))
|
|
|
|
# view tensorflow logs
|
|
print(f'View tensorboard logs by running\ntensorboard --logdir {outpath}')
|
|
print('and going to http://localhost:6006 on your browser')
|