All models running.

dataset.py

@@ -47,8 +47,8 @@ class AbstractDataset(ConcatDataset, ABC):
     # maps = ['hotel', 'tum','gallery', 'queens', 'oet']
     @property
     def maps(self):
-        return ['test', 'test2']
+        # return ['test', 'test2']
-        # return ['hotel', 'tum','gallery', 'queens', 'oet']
+        return ['hotel', 'tum','gallery', 'queens', 'oet']
 
     @property
     @abstractmethod

networks/adverserial_auto_encoder.py

@@ -6,6 +6,9 @@ from networks.modules import *
 import torch
 
 
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+
 class AdversarialAutoEncoder(AutoEncoder):
 
     def __init__(self, *args, **kwargs):
@@ -32,18 +35,18 @@ class AdversarialAELightningOverrides(LightningModuleOverrides):
         if optimizer_i == 0:
             # ---------------------
             #  Train Discriminator
-            # ---------------------
+            # ---------------------p
             # latent_fake, reconstruction
-            latent_fake, _ = self.network.forward(batch)
+            latent_fake = self.network.encoder.forward(batch)
-            latent_real = self.normal.sample(latent_fake.shape)
+            latent_real = self.normal.sample(latent_fake.shape).to(device)
 
             # Evaluate the input
             d_real_prediction = self.network.discriminator.forward(latent_real)
             d_fake_prediction = self.network.discriminator.forward(latent_fake)
 
             # Train the discriminator
-            d_loss_real = mse_loss(d_real_prediction, torch.zeros(d_real_prediction.shape))
+            d_loss_real = mse_loss(d_real_prediction, torch.zeros(d_real_prediction.shape, device=device))
-            d_loss_fake = mse_loss(d_fake_prediction, torch.ones(d_fake_prediction.shape))
+            d_loss_fake = mse_loss(d_fake_prediction, torch.ones(d_fake_prediction.shape, device=device))
 
             # Calculate the mean over both the real and the fake acc
             # ToDo: do i need to compute this seperate?

networks/modules.py

@@ -25,9 +25,9 @@ class LightningModuleOverrides:
 
     @data_loader
     def tng_dataloader(self):
-        num_workers = os.cpu_count() // 2
+        num_workers = 0  #  os.cpu_count() // 2
         return DataLoader(DataContainer('data', self.size, self.step),
-                          shuffle=True, batch_size=100, num_workers=num_workers)
+                          shuffle=True, batch_size=10000, num_workers=num_workers)
 
 
 class AbstractNeuralNetwork(Module):

networks/seperating_adversarial_auto_encoder.py

@@ -1,21 +1,22 @@
 from torch.optim import Adam
-
-from networks.auto_encoder import AutoEncoder
 from torch.nn.functional import mse_loss
 from networks.modules import *
 import torch
 
 
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+
 class SeperatingAdversarialAutoEncoder(Module):
 
-    def __init__(self, latent_dim, features, **kwargs):
+    def __init__(self, latent_dim, features):
         super(SeperatingAdversarialAutoEncoder, self).__init__()
 
         self.latent_dim = latent_dim
         self.features = features
         self.spatial_encoder = PoolingEncoder(self.latent_dim)
         self.temporal_encoder = Encoder(self.latent_dim)
-        self.decoder = Decoder(self.latent_dim, self.features)
+        self.decoder = Decoder(self.latent_dim * 2, self.features)
         self.spatial_discriminator = Discriminator(self.latent_dim, self.features)
         self.temporal_discriminator = Discriminator(self.latent_dim, self.features)
 
@@ -43,15 +44,17 @@ class SeparatingAdversarialAELightningOverrides(LightningModuleOverrides):
             #  Train temporal Discriminator
             # ---------------------
             # latent_fake, reconstruction
-            temporal_latent_real = self.normal.sample(temporal_latent_fake.shape)
+            temporal_latent_real = self.normal.sample(temporal_latent_fake.shape).to(device)
 
             # Evaluate the input
             temporal_real_prediction = self.network.temporal_discriminator.forward(temporal_latent_real)
             temporal_fake_prediction = self.network.temporal_discriminator.forward(temporal_latent_fake)
 
             # Train the discriminator
-            temporal_loss_real = mse_loss(temporal_real_prediction, torch.zeros(temporal_real_prediction.shape))
+            temporal_loss_real = mse_loss(temporal_real_prediction,
-            temporal_loss_fake = mse_loss(temporal_fake_prediction, torch.ones(temporal_fake_prediction.shape))
+                                          torch.zeros(temporal_real_prediction.shape, device=device))
+            temporal_loss_fake = mse_loss(temporal_fake_prediction,
+                                          torch.ones(temporal_fake_prediction.shape, device=device))
 
             # Calculate the mean over bot the real and the fake acc
             # ToDo: do i need to compute this seperate?
@@ -63,15 +66,17 @@ class SeparatingAdversarialAELightningOverrides(LightningModuleOverrides):
             #  Train spatial Discriminator
             # ---------------------
             # latent_fake, reconstruction
-            spatial_latent_real = self.normal.sample(spatial_latent_fake.shape)
+            spatial_latent_real = self.normal.sample(spatial_latent_fake.shape).to(device)
 
             # Evaluate the input
             spatial_real_prediction = self.network.spatial_discriminator.forward(spatial_latent_real)
             spatial_fake_prediction = self.network.spatial_discriminator.forward(spatial_latent_fake)
 
             # Train the discriminator
-            spatial_loss_real = mse_loss(spatial_real_prediction, torch.zeros(spatial_real_prediction.shape))
+            spatial_loss_real = mse_loss(spatial_real_prediction,
-            spatial_loss_fake = mse_loss(spatial_fake_prediction, torch.ones(spatial_fake_prediction.shape))
+                                         torch.zeros(spatial_real_prediction.shape, device=device))
+            spatial_loss_fake = mse_loss(spatial_fake_prediction,
+                                         torch.ones(spatial_fake_prediction.shape, device=device))
 
             # Calculate the mean over bot the real and the fake acc
             # ToDo: do i need to compute this seperate?

run_models.py

@@ -1,37 +1,33 @@
 from torch.distributions import Normal
-
 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
 
 from argparse import Namespace
 from argparse import ArgumentParser
+from distutils.util import strtobool
 
 args = ArgumentParser()
-args.add_argument('--step', default=0)
+args.add_argument('--step', default=6)
-args.add_argument('--features', default=0)
+args.add_argument('--features', default=6)
-args.add_argument('--size', default=0)
+args.add_argument('--size', default=9)
-args.add_argument('--latent_dim', default=0)
+args.add_argument('--latent_dim', default=4)
 args.add_argument('--model', default='Model')
+args.add_argument('--refresh', type=strtobool, default=False)
+
 
 
 # ToDo: How to implement this better?
 # other_classes = [AutoEncoder, AutoEncoderLightningOverrides]
 class Model(AutoEncoderLightningOverrides, LightningModule):
 
-    def __init__(self, parameters, **kwargs):
+    def __init__(self, parameters):
         assert all([x in parameters for x in ['step', 'size', 'latent_dim', 'features']])
         self.size = parameters.size
         self.latent_dim = parameters.latent_dim
@@ -43,7 +39,7 @@ class Model(AutoEncoderLightningOverrides, LightningModule):
 
 class AdversarialModel(AdversarialAELightningOverrides, LightningModule):
 
-    def __init__(self, parameters: Namespace, **kwargs):
+    def __init__(self, parameters: Namespace):
         assert all([x in parameters for x in ['step', 'size', 'latent_dim', 'features']])
         self.size = parameters.size
         self.latent_dim = parameters.latent_dim
@@ -57,7 +53,7 @@ class AdversarialModel(AdversarialAELightningOverrides, LightningModule):
 
 class SeparatingAdversarialModel(SeparatingAdversarialAELightningOverrides, LightningModule):
 
-    def __init__(self, parameters: Namespace, **kwargs):
+    def __init__(self, parameters: Namespace):
         assert all([x in parameters for x in ['step', 'size', 'latent_dim', 'features']])
         self.size = parameters.size
         self.latent_dim = parameters.latent_dim
@@ -65,16 +61,12 @@ class SeparatingAdversarialModel(SeparatingAdversarialAELightningOverrides, Ligh
         self.step = parameters.step
         super(SeparatingAdversarialModel, self).__init__()
         self.normal = Normal(0, 1)
-        self.network = SeperatingAdversarialAutoEncoder(self.latent_dim, self.features, **kwargs)
+        self.network = SeperatingAdversarialAutoEncoder(self.latent_dim, self.features)
         pass
 
 
 if __name__ == '__main__':
-    features = 6
-    tag_dict = dict(features=features, latent_dim=4, size=5, step=6, refresh=False,
-                     transforms=[BatchNorm1d(features)])
     arguments = args.parse_args()
-    arguments.__dict__.update(tag_dict)
 
     model = globals()[arguments.model](arguments)
 
@@ -82,19 +74,19 @@ if __name__ == '__main__':
     outpath = os.path.join(os.getcwd(), 'output', model.name, time.asctime().replace(' ', '_').replace(':', '-'))
     os.makedirs(outpath, exist_ok=True)
     exp = Experiment(save_dir=outpath)
-    exp.tag(tag_dict=tag_dict)
+    exp.tag(tag_dict=arguments.__dict__)
 
     from pytorch_lightning.callbacks import ModelCheckpoint
 
     checkpoint_callback = ModelCheckpoint(
         filepath=os.path.join(outpath, 'weights.ckpt'),
-        save_best_only=True,
+        save_best_only=False,
         verbose=True,
-        monitor='val_loss',  # val_loss
+        period=4
-        mode='min',
     )
 
-    trainer = Trainer(experiment=exp, checkpoint_callback=checkpoint_callback, max_nb_epochs=15)  # gpus=[0...LoL]
+    trainer = Trainer(experiment=exp, max_nb_epochs=250, gpus=[0],
+                      add_log_row_interval=1000, checkpoint_callback=checkpoint_callback)
     trainer.fit(model)
     trainer.save_checkpoint(os.path.join(outpath, 'weights.ckpt'))
 

viz/viz_latent.py

@@ -62,7 +62,7 @@ def load_and_predict(path_like_element):
         plot.savefig(os.path.join(os.path.dirname(path_like_element), f'latent_space_{idx}.png'))
 
 
-def viz_latent(prediction, title=f'Latent Space '):
+def viz_latent(prediction):
     if prediction.shape[-1] <= 1:
         raise ValueError('How did this happen?')
     elif prediction.shape[-1] == 2: