Done: First VIsualization

ToDo: Visualization for all classes, latent space setups

run_models.py

@@ -1,6 +1,9 @@
 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
@@ -9,7 +12,7 @@ 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]
@@ -30,6 +33,10 @@ class Model(VariationalAutoEncoderLightningOverrides, LightningModule):
 
 class AdversarialModel(AdversarialAELightningOverrides, LightningModule):
 
+    @property
+    def name(self):
+        return self.network.name
+
     def __init__(self, dataParams: dict):
         super(AdversarialModel, self).__init__()
         self.dataParams = dataParams
@@ -48,13 +55,61 @@ class AdversarialModel(AdversarialAELightningOverrides, LightningModule):
         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
-    ae = AdversarialModel(
-        dataParams=dict(refresh=False, size=5, step=5,
-                        features=features, transforms=[BatchNorm1d(features)]
-                        )
+    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()
-    trainer.fit(ae)
+    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')