Modified the data_folder to be more generic

Hey @ageorge,

It's a good practice to open a merge request each time you intend to work on branch. Doing this way we can discuss changes in an easier way.

Concerning what you did, are you sure that it still works with Olegs stuff ?

Thanks

bob/learn/pytorch/architectures/ConvAutoencoder.py

@@ -57,10 +57,11 @@ class ConvAutoencoder(nn.Module):
         The forward method.
         """
         x = self.encoder(x)
-        x = self.decoder(x)
 
         if self.return_latent_embedding:
-            return self.encoder(x)
+            return x
+
+        x = self.decoder(x)
 
         return x