Moved functions from config to utils, updated docs, renamed train script

bob/learn/pytorch/config/mlp/batl_db_1296x10_relu_mlp.py

@@ -103,43 +103,6 @@ See training script for details
 Define the function to compute the loss. Don't change the signature of this
 function: ``loss_function(output, input, target)``
 """
-from bob.learn.pytorch.utils import comp_bce_loss_weights
 
-
-def loss_function(output, img, target):
-    """
-    Returns a loss defined by a global variable loss_type in this config file.
-
-    **Parameters:**
-
-    ``output`` : Tensor
-        Tensor of the size: ``[num_patches, 1]``
-
-    ``img`` : Tensor
-        Tensor containing input training patches. Input for the above Network()
-        class. The dimensions are: ``[num_patches, 4, 8, 8]``.
-        Note: this argument is not used in current loss function.
-
-    ``target`` : Tensor
-        Tensor containing class labels for each sample in ``img``.
-        Tensor of the size: ``[num_patches]``
-
-    **Returns:**
-
-    ``loss`` : Tensor
-        Tensor containing loss value.
-    """
-
-    target = target.float()  # make sure the target is float, not int
-
-    # convert "target" tensor from size [num_patches] to [num_patches, 1], to match "output" dimensions:
-    target = target.view(-1, 1)
-
-    weight = comp_bce_loss_weights(target)
-
-    loss_type.weight = weight
-
-    loss = loss_type(output, target)
-
-    return loss
+from bob.learn.pytorch.utils import weighted_bce_loss as loss_function
 

bob/learn/pytorch/utils.py

@@ -5,6 +5,9 @@ import numpy as np
 import torch
 from bob.learn.pytorch.datasets import DataFolder
 from torch.utils.data import DataLoader
+from torch import nn
+import logging
+logger = logging.getLogger("bob.learn.pytorch")
 
 
 def get_parameter(args, configuration, keyword, default):
@@ -242,18 +245,18 @@ class MeanStdNormalizer():
 
         Returns
         -------
-        x_norm : Tensor
+        x_norm : :py:class:`torch.Tensor`
             Normalized feature vector of the size ``(1, n_features)``
         """
 
         if self.features_mean is None or self.features_std is None: # pre-compute normalization parameters
 
-            print ("Computing mean-std normalization parameters using real samples of the training set")
+            logger.info ("Computing mean-std normalization parameters using real samples of the training set")
             # compute the normalization parameters on the fly:
             features_mean, features_std = compute_mean_std_bf_class(self.kwargs)
 
             # save normalization parameters:
-            print ("Setting the normalization parameters")
+            logger.info ("Setting the normalization parameters")
             self.features_mean = features_mean
             self.features_std = features_std
 
@@ -266,3 +269,42 @@ class MeanStdNormalizer():
         return torch.Tensor(x_norm).unsqueeze(0)
 
 
+# =============================================================================
+def weighted_bce_loss(output, img, target):
+    """
+    Returns a weighted BCE loss.
+
+    Parameters
+    ----------
+    output : :py:class:`torch.Tensor`
+        Tensor of the size: ``[num_patches, 1]``
+
+    img : :py:class:`torch.Tensor`
+        This argument is not used in current loss function, but is here to
+        match the signature expected by the training script.
+
+    target : :py:class:`torch.Tensor`
+        Tensor containing class labels for each sample in ``img``.
+        Tensor of the size: ``[num_patches]``
+
+    Returns
+    -------
+    loss : :py:class:`torch.Tensor`
+        Tensor containing loss value.
+    """
+
+    loss_type = nn.BCELoss()
+
+    target = target.float()  # make sure the target is float, not int
+
+    # convert "target" tensor from size [num_patches] to [num_patches, 1], to match "output" dimensions:
+    target = target.view(-1, 1)
+
+    weight = comp_bce_loss_weights(target)
+
+    loss_type.weight = weight
+
+    loss = loss_type(output, target)
+
+    return loss
+

doc/guide_conv_autoencoder.rst

@@ -14,7 +14,7 @@ As an example, to train an autoencoder on facial images extracted from the Celeb
 
 .. code-block:: sh
 
-    ./bin/train_autoencoder.py \             # script used for autoencoders training, can be used for other networks as-well
+    ./bin/train_network.py \                 # script used for autoencoders training, can be used for other networks as-well
     <FOLDER_CONTAINING_TRAINING_DATA> \      # substitute the path pointing to training data
     <FOLDER_TO_SAVE_THE_RESULTS>/ \          # substitute the path to save the results to
     -c autoencoder/net1_celeba.py \          # configuration file defining the AE, database, and training parameters
@@ -29,7 +29,7 @@ People in Idiap can benefit from GPU cluster, running the training as follows:
     --name <NAME_OF_EXPERIMENT> \                  # define the name of th job (Idiap only)
     --log-dir <FOLDER_TO_SAVE_THE_RESULTS>/logs/ \ # substitute the path to save the logs to (Idiap only)
     --environment="PYTHONUNBUFFERED=1" -- \        #
-    ./bin/train_autoencoder.py \       # script used for autoencoders training, cand be used for other networks as-well
+    ./bin/train_network.py \                       # script used for autoencoders training, cand be used for other networks as-well
     <FOLDER_CONTAINING_TRAINING_DATA> \            # substitute the path pointing to training data
     <FOLDER_TO_SAVE_THE_RESULTS>/ \                # substitute the path to save the results to
     -c autoencoder/net1_celeba.py \                # configuration file defining the AE, database, and training parameters
@@ -42,7 +42,7 @@ For a more detailed documentation of functionality available in the training scr
 
 .. code-block:: sh
 
-    ./bin/train_autoencoder.py --help   # note: remove ./bin/ if buildout is not used
+    ./bin/train_network.py --help   # note: remove ./bin/ if buildout is not used
 
 Please inspect the corresponding configuration file, ``net1_celeba.py`` for example, for more details on how to define the database, network architecture and training parameters.
 
@@ -61,7 +61,7 @@ the following reconstructions produced by an autoencoder:
 Autoencoder fine-tuning on the multi-channel facial data
 ===========================================================
 
-This section is useful for those trying to reproduce the results form [NGM19]_, or for demonstrative purposes showing the capabilities of ``train_autoencoder.py`` script.
+This section is useful for those trying to reproduce the results form [NGM19]_, or for demonstrative purposes showing the capabilities of ``train_network.py`` script.
 
 Following the training procedure of [NGM19]_, one might want to fine-tune the pre-trained autoencoder on the multi-channel (**MC**) facial data.
 In this example, MC training data is a stack of gray-scale, NIR, and Depth (BW-NIR-D) facial images extracted from WMCA face PAD database.
@@ -74,7 +74,7 @@ autoencoder are fine-tuned.
 
 .. code-block:: sh
 
-    ./bin/train_autoencoder.py \                          # script used for autoencoders training, can be used for other networks as-well
+    ./bin/train_network.py \                              # script used for autoencoders training, can be used for other networks as-well
     <FOLDER_CONTAINING_TRAINING_DATA> \                   # substitute the path pointing to training data
     <FOLDER_TO_SAVE_THE_RESULTS>/ \                       # substitute the path to save the results to
     -p <FOLDER_CONTAINING_RGB_AE_MODELS>/model_70.pth \   # initialize the AE with the model obtained during RGB pre-training
@@ -87,7 +87,7 @@ Below is the command allowing to fine-tine just **one layer of encoder**, which
 
 .. code-block:: sh
 
-    ./bin/train_autoencoder.py \                          # script used for autoencoders training, can be used for other networks as-well
+    ./bin/train_network.py \                              # script used for autoencoders training, can be used for other networks as-well
     <FOLDER_CONTAINING_TRAINING_DATA> \                   # substitute the path pointing to training data
     <FOLDER_TO_SAVE_THE_RESULTS>/ \                       # substitute the path to save the results to
     -p <FOLDER_CONTAINING_RGB_AE_MODELS>/model_70.pth \   # initialize the AE with the model obtained during RGB pre-training

doc/guide_mlp.rst

@@ -17,7 +17,7 @@ As an example, to train an autoencoder on latent embeddings extracted from an en
 
 .. code-block:: sh
 
-    ./bin/train_autoencoder.py \             # script used for MLP training, can be used for other networks as-well
+    ./bin/train_network.py \                 # script used for MLP training, can be used for other networks as-well
     <FOLDER_CONTAINING_TRAINING_DATA> \      # substitute the path pointing to training data
     <FOLDER_TO_SAVE_THE_RESULTS>/ \          # substitute the path to save the results to
     -c mlp/batl_db_1296x10_relu_mlp.py \     # configuration file defining the database, training parameters, transformation to be applied to training data, and an MLP architecture

setup.py

@@ -72,7 +72,7 @@ setup(
         'train_cnn.py = bob.learn.pytorch.scripts.train_cnn:main',
         'train_dcgan.py = bob.learn.pytorch.scripts.train_dcgan:main',
         'train_conditionalgan.py = bob.learn.pytorch.scripts.train_conditionalgan:main',
-        'train_autoencoder.py = bob.learn.pytorch.scripts.train_autoencoder:main',
+        'train_network.py = bob.learn.pytorch.scripts.train_network:main',
       ],
    },