Updated the documentation of MultiNetPatchExtractor

bob/ip/pytorch_extractor/MultiNetPatchExtractor.py

@@ -37,13 +37,23 @@ class MultiNetPatchExtractor(Extractor, object):
     Attributes
     -----------
     config_file: str
-        Relative name of the config file defining the network, and training parameters.
+        Relative name of the config file.
         The path should be relative to ``config_group``,
         for example: "autoencoder/net1_batl_3_layers_partial.py".
 
+        This file **must** contain at least the following definitions:
 
-        ADD THE DOC on what should be in the config!!!!!!!!!!!!!!!!!!!!!!
+        Function namely ``transform``, which is a  Compose transformation of
+        torchvision package, to be applied to the input samples.
 
+        A ``Network`` class, defining your network architecture. Note, if your
+        class is named differently, import it as ``Network``, for example:
+        ``from bob.learn.pytorch.architectures import MyNetwork as Network``
+
+        Optional: ``network_kwargs`` to be used for ``Network`` initialization.
+        For example, if you want to use the latent embeddings of the autoencoder
+        class, set the kwargs accodingly. Note: in current extractor the
+        ``forward()`` method of the ``Network`` is used for feature extraction.
 
     config_group: str
         Group/package name containing the configuration file. Usually all
@@ -163,3 +173,4 @@ class MultiNetPatchExtractor(Extractor, object):
 
         return features
 
+