bugfix in predict_model for hdf5 larva_dataset files

src/maggotuba/models/predict_model.py

@@ -152,7 +152,7 @@ def predict_individual_data_files(backend, model, input_files_and_labels):
 def predict_larva_dataset(backend, model, file, subset="validation", subsets=(.8, .2, 0)):
     from taggingbackends.data.dataset import LarvaDataset
     dataset = LarvaDataset(file, new_generator(), subsets)
-    return model.predict(dataset, subset)
+    return model.predict((dataset, subset))
 
 def _zip(xs, ys):
     # prevent issues similar to #2