MLPAlgorithm PAD algorithm V1 version

This is an MLP based PAD algorithm.

bob/ip/pytorch_extractor/test_data/mlp_algo_test_config.py

+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+"""
+@author: Olegs Nikisins
+"""
+#==============================================================================
+# Import here:
+
+import numpy as np
+
+import torch
+
+
+#==============================================================================
+# Define parameters here:
+
+"""
+Transformations to be applied to the input 1D numpy arrays (feature vectors).
+Here, for demonstrative purposes, the transformation is mean std-normalization,
+where mean and std values are just numpy generated vectors. In real applications,
+normalizers must be computed in the meaningfull way. This config is just for
+test purposes.
+"""
+
+def transform(x):
+    """
+    Transformation function applying dummy mean-std normalization and converting
+    input numpy feature vectors to PyTorch tensors, making them compatible with
+    MLP.
+
+    Arguments
+    ---------
+    x : numpy array
+        1D numpy array / feature vector.
+
+    Return
+    ------
+    x_transform : Tensor
+        Torch tensor, transformed ``x`` to be used as MLP input.
+    """
+
+    features_mean = np.zeros(x.shape)
+
+    features_std = np.ones(x.shape)
+
+    row_norm_list = []
+    for row in x:  # row is a sample
+        row_norm = (row - features_mean) / features_std
+        row_norm_list.append(row_norm)
+    x_norm = np.vstack(row_norm_list)
+
+    x_norm.squeeze()
+
+    return torch.Tensor(x_norm).unsqueeze(0)
+
+
+"""
+Define the network to be trained as a class, named ``Network``.
+Note: Do not change the name of the below class, always import as ``Network``.
+"""
+
+from bob.learn.pytorch.architectures import TwoLayerMLP as Network
+
+
+"""
+kwargs to be used for ``Network`` initialization. The name must be ``network_kwargs``.
+"""
+network_kwargs = {}
+network_kwargs['in_features'] = 100
+network_kwargs['n_hidden_relu'] = 10
+network_kwargs['apply_sigmoid'] = False # don't use sigmoid to make the scores more even
+
+