[datasets] making docstrings numpy style

bob/learn/pytorch/datasets/casia_webface.py

@@ -2,7 +2,6 @@
 # encoding: utf-8
 
 import os
-
 import numpy
 
 from torch.utils.data import Dataset, DataLoader
@@ -14,22 +13,36 @@ from .utils import map_labels
 
 
 class CasiaWebFaceDataset(Dataset):
-  """Casia WebFace dataset (for CNN training).
-  
-  Class representing the CASIA WebFace dataset
+  """Class representing the CASIA WebFace dataset
 
-  **Parameters**
+  Note that here the only label is identity
 
-  root-dir: path
+  Attributes
+  ----------
+  root_dir : str
     The path to the data
-
-  frontal_only: boolean
-    If you want to only use frontal faces 
-    
-  transform: torchvision.transforms
+  transform : `torchvision.transforms`
     The transform(s) to apply to the face images
+  data_files : list of str
+    The list of data files
+  id_labels : list of int
+    The list of identities, for each data file
+
   """
   def __init__(self, root_dir, transform=None, start_index=0):
+    """Init function
+
+    Parameters
+    ----------
+    root_dir : str
+      The path to the data
+    transform : :py:class:`torchvision.transforms`
+      The transform(s) to apply to the face images
+    start_index : int
+      label of the first identity (useful if you use
+      several databases)
+    
+    """
     self.root_dir = root_dir
     self.transform = transform
     self.data_files = []
@@ -46,14 +59,25 @@ class CasiaWebFaceDataset(Dataset):
     self.id_labels = map_labels(id_labels, start_index)
 
   def __len__(self):
-    """
-    return the length of the dataset (i.e. nb of examples)
+    """Returns the length of the dataset (i.e. nb of examples)
+    
+    Returns
+    -------
+    int 
+      the number of examples in the dataset
+    
     """
     return len(self.data_files)
 
   def __getitem__(self, idx):
-    """
-      return a sample from the dataset
+    """Returns a sample from the dataset
+   
+    Returns
+    -------
+    dict
+      an example of the dataset, containing the 
+      transformed face image and its identity
+    
     """
     image = bob.io.base.load(self.data_files[idx])
     identity = self.id_labels[idx]
@@ -66,39 +90,63 @@ class CasiaWebFaceDataset(Dataset):
 
 
 class CasiaDataset(Dataset):
-  """Casia WebFace dataset.
-  
-  Class representing the CASIA WebFace dataset
+  """Class representing the CASIA WebFace dataset
 
-  **Parameters**
+  Note that in this class, two labels are provided
+  with each image: identity and pose.
 
-  root-dir: path
-    The path to the data
+  Pose labels have been automatically inferred using
+  the ROC face recognirion SDK from RankOne.
 
-  frontal_only: boolean
-    If you want to only use frontal faces 
-    
-  transform: torchvision.transforms
+  There are 13 pose labels, corresponding to cluster
+  of 15 degrees, ranging from -90 degress (left profile)
+  to 90 degrees (right profile)
+
+  Attributes
+  ----------
+  root_dir: str
+    The path to the data
+  transform : `torchvision.transforms`
     The transform(s) to apply to the face images
+  data_files: list of str
+    The list of data files
+  id_labels : list of int
+    The list of identities, for each data file
+  pose_labels : list of int
+    The list containing the pose labels 
+
   """
-  def __init__(self, root_dir, frontal_only=False, transform=None, start_index=0):
+  def __init__(self, root_dir, transform=None, start_index=0):
+    """Init function
+
+    Parameters
+    ----------
+    root_dir: str
+      The path to the data
+    transform: :py:class:`torchvision.transforms`
+      The transform(s) to apply to the face images
+    start_index : int
+      label of the first identity (useful if you use
+      several databases)
+    
+    """
     self.root_dir = root_dir
     self.transform = transform
   
     dir_to_pose_label = {'l90': '0',
-                       'l75': '1',
-                       'l60': '2',
-                       'l45': '3',
-                       'l30': '4',
-                       'l15': '5',
-                       '0'  : '6',
-                       'r15': '7',
-                       'r30': '8',
-                       'r45': '9',
-                       'r60': '10',
-                       'r75': '11',
-                       'r90': '12',
-                      }
+                         'l75': '1',
+                         'l60': '2',
+                         'l45': '3',
+                         'l30': '4',
+                         'l15': '5',
+                         '0'  : '6',
+                         'r15': '7',
+                         'r30': '8',
+                         'r45': '9',
+                         'r60': '10',
+                         'r75': '11',
+                         'r90': '12',
+                        }
 
     # get all the needed file, the pose labels, and the id labels
     self.data_files = []
@@ -119,15 +167,26 @@ class CasiaDataset(Dataset):
       
     
   def __len__(self):
-    """
-      return the length of the dataset (i.e. nb of examples)
+    """Returns the length of the dataset (i.e. nb of examples)
+    
+    Returns
+    -------
+    int 
+      the number of examples in the dataset
+    
     """
     return len(self.data_files)
 
 
   def __getitem__(self, idx):
-    """
-      return a sample from the dataset
+    """Returns a sample from the dataset
+   
+    Returns
+    -------
+    dict
+      an example of the dataset, containing the 
+      transformed face image, its identity and pose information
+    
     """
     image = bob.io.base.load(self.data_files[idx])
     identity = self.id_labels[idx]

bob/learn/pytorch/datasets/multipie.py

@@ -15,28 +15,40 @@ import bob.io.image
 from .utils import map_labels
 
 class MultiPIEDataset(Dataset):
-  """MultiPIE dataset.
-  
-  Class represeting the Multi-PIE dataset
-
-  **Parameters**
+  """Class representing the Multi-PIE dataset
 
-  root-dir: path
+  Attributes
+  ----------
+  root_dir : str
     The path to the data
-
-  world: boolean
+  world : bool
     If you want to only use data corresponding to the world model
-
-  frontal_only: boolean
-    If you want to only use frontal faces 
-    
-  transform: torchvision.transforms
+  transform: `torchvision.transforms`
     The transform(s) to apply to the face images
+  data_files: list of str
+    The list of data files
+  id_labels : list of int
+    The list of identities, for each data file
+  pose_labels : list of int
+    The list containing the pose labels 
+  
   """
 
-  # TODO: Start from original data and annotations - Guillaume HEUSCH, 06-11-2017
-
   def __init__(self, root_dir, world=False, frontal_only=False, transform=None):
+    """Class representing the Multi-PIE dataset
+
+    Attributes
+    ----------
+    root_dir : str
+      The path to the data
+    world : bool
+      If you want to only use data corresponding to the world model
+    frontal_only : bool
+      If you want to only use frontal faces 
+    transform: `torchvision.transforms`
+      The transform(s) to apply to the face images
+    
+    """
     self.root_dir = root_dir
     self.transform = transform
     self.world = world
@@ -110,15 +122,26 @@ class MultiPIEDataset(Dataset):
       
     
   def __len__(self):
-    """
-      return the length of the dataset (i.e. nb of examples)
+    """Returns the length of the dataset (i.e. nb of examples)
+    
+    Returns
+    -------
+    int 
+      the number of examples in the dataset
+    
     """
     return len(self.data_files)
  
 
   def __getitem__(self, idx):
-    """
-      return a sample from the dataset
+    """Returns a sample from the dataset
+   
+    Returns
+    -------
+    dict
+      an example of the dataset, containing the 
+      transformed face image, its identity and pose information
+    
     """
     image = bob.io.base.load(self.data_files[idx])
     identity = self.id_labels[idx]