Commit c94d777c authored by Amir MOHAMMADI's avatar Amir MOHAMMADI

Merge branch 'dask-pipelines' into 'master'

Dask pipelines

See merge request !42
parents 35f6426d 8f2309b8
Pipeline #44914 failed with stages
in 3 minutes and 22 seconds
This diff is collapsed.
import logging
from sklearn.base import BaseEstimator, TransformerMixin
from .. import utils
logger = logging.getLogger(__name__)
class Wrapper(TransformerMixin, BaseEstimator):
"""Wrapper class to run image preprocessing algorithms on video data.
This class provides functionality to read original video data from several databases.
So far, the video content from :ref:`bob.db.mobio <bob.db.mobio>` and the image list content from :ref:` <>` are supported.
Furthermore, frames are extracted from these video data, and a ``preprocessor`` algorithm is applied on all selected frames.
The preprocessor can either be provided as a registered resource, i.e., one of :ref:``, or an instance of a preprocessing class.
Since most of the databases do not provide annotations for all frames of the videos, commonly the preprocessor needs to apply face detection.
The ``frame_selector`` can be chosen to select some frames from the video.
By default, a few frames spread over the whole video sequence are selected.
The ``quality_function`` is used to assess the quality of the frame.
If no ``quality_function`` is given, the quality is based on the face detector, or simply left as ``None``.
So far, the quality of the frames are not used, but it is foreseen to select frames based on quality.
preprocessor : str or :py:class:`` instance
The preprocessor to be used to preprocess the frames.
frame_selector : :py:class:``
A frame selector class to define, which frames of the video to use.
quality_function : function or ``None``
A function assessing the quality of the preprocessed image.
If ``None``, no quality assessment is performed.
If the preprocessor contains a ``quality`` attribute, this is taken instead.
compressed_io : bool
Use compression to write the resulting preprocessed HDF5 files.
This is experimental and might cause trouble.
Use this flag with care.
read_original_data: callable or ``None``
Function that loads the raw data.
If not explicitly defined the raw data will be loaded by :py:meth:``
using the specified ``frame_selector``
def __init__(
self.estimator = estimator
def transform(self, videos, **kwargs):
transformed_videos = []
for i, video in enumerate(videos):
if not hasattr(video, "indices"):
raise ValueError(
f"The input video: {video}\n does not have indices.\n "
f"Processing failed in {self}"
kw = {}
if kwargs:
kw = {k: v[i] for k, v in kwargs.items()}
if "annotations" in kw:
kw["annotations"] = [
kw["annotations"].get(index, kw["annotations"].get(str(index)))
for index in video.indices
data = self.estimator.transform(video, **kw)
dl, vl = len(data), len(video)
if dl != vl:
raise NotImplementedError(
f"Length of transformed data ({dl}) using {self.estimator}"
f" is different from the length of input video: {vl}"
# handle None's
indices = [idx for d, idx in zip(data, video.indices) if d is not None]
data = [d for d in data if d is not None]
data = utils.VideoLikeContainer(data, indices)
return transformed_videos
def _more_tags(self):
return {"stateless": True, "requires_fit": False}
def fit(self, X, y=None, **fit_params):
"""Does nothing"""
return self
from .Wrapper import Wrapper
# gets sphinx autodoc done right - don't remove it
def __appropriate__(*args):
"""Says object was actually declared here, and not in the import module.
Fixing sphinx warnings of not being able to find classes, when path is shortened.
*args: An iterable of objects to modify
Resolves `Sphinx referencing issues
for obj in args: obj.__module__ = __name__
__all__ = [_ for _ in dir() if not _.startswith('_')]
#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
import numpy
import numpy as np
import h5py
import logging
logger = logging.getLogger(__name__)
......@@ -59,9 +57,99 @@ def select_frames(count, max_number_of_frames, selection_style, step_size):
return indices
class VideoAsArray:
def __init__(
self.path = path
reader = self.reader
self.dtype, shape = reader.video_type[:2]
self.ndim = len(shape)
self.selection_style = selection_style
indices = select_frames(
self.indices = indices
self.shape = (len(indices),) + shape[1:]
def reader(self):
def __len__(self):
return self.shape[0]
def __getitem__(self, index):
if isinstance(index, int):
idx = self.indices[index]
return self.reader[idx]
if not (isinstance(index, tuple) and len(index) == self.ndim):
raise NotImplementedError(f"Indxing like {index} is not supported yet!")
if all(i == slice(0, 0) for i in index):
return np.array([], dtype=self.dtype)
if self.selection_style == "all":
return np.asarray(self.reader.load())[index]
idx = self.indices[index[0]]
video = []
for i, frame in enumerate(self.reader):
if i not in idx:
if i == idx[-1]:
index = (slice(len(video)),) + index[1:]
return np.asarray(video)[index]
def __repr__(self):
return f"{self.reader!r} {self.dtype!r} {self.ndim!r} {self.shape!r} {self.indices!r}"
class VideoLikeContainer:
def __init__(self, data, indices, **kwargs):
super().__init__(**kwargs) = data
self.indices = indices
def __len__(self):
return len(
def __getitem__(self, item):
def __array__(self, dtype=None, *args, **kwargs):
return np.asarray(, dtype, *args, **kwargs)
def save(cls, other, file):
with h5py.File(file, mode="w") as f:
f["data"] =
f["indices"] = other.indices
def load(cls, file):
with h5py.File(file, mode="r") as f:
data = np.array(f["data"])
indices = np.array(f["indices"])
self = cls(data=data, indices=indices)
return self
class FrameContainer:
"""A class for reading, manipulating and saving video content.
"""A class for reading, manipulating and saving video content."""
def __init__(self, hdf5=None,, **kwargs):
......@@ -163,7 +251,7 @@ class FrameContainer:
return self
def save(self, hdf5,
""" Save the content to the given HDF5 File.
"""Save the content to the given HDF5 File.
The contained data will be written using the given save_function."""
if not len(self):
logger.warn("Saving empty FrameContainer '%s'", hdf5.filename)
......@@ -191,7 +279,7 @@ class FrameContainer:
return False
if abs(a[2] - b[2]) > 1e-8:
return False
if not numpy.allclose(a[1], b[1]):
if not np.allclose(a[1], b[1]):
return False
return True
......@@ -35,9 +35,21 @@ class FrameSelector:
"Unknown selection style '%s', choose one of ('first', 'spread', 'step', 'all')"
% selection_style
self.selection = selection_style
self.max_frames = max_number_of_frames
self.step = step_size
self.selection_style = selection_style
self.max_number_of_frames = max_number_of_frames
self.step_size = step_size
def selection(self):
return self.selection_style
def max_frames(self):
return self.max_number_of_frames
def step(self):
return self.step_size
def __call__(self, data,
"""Selects frames and returns them in a FrameContainer.
from .FrameContainer import FrameContainer, load_compressed, save_compressed, select_frames
from .FrameContainer import FrameContainer, load_compressed, save_compressed, select_frames, VideoAsArray, VideoLikeContainer
from .FrameSelector import FrameSelector
......@@ -31,7 +31,6 @@ requirements:
- bob.sp
- bob.ip.base
- bob.ip.color
- bob.ip.draw
- bob.ip.gabor
- bob.learn.linear
- bob.learn.em
......@@ -39,9 +38,7 @@ requirements:
- bob.db.base
- bob.learn.boosting
- bob.ip.facedetect
- bob.ip.flandmark
- python
- setuptools
......@@ -23,7 +23,6 @@ develop = src/bob.extension
......@@ -53,7 +52,6 @@ bob.math = git
bob.sp = git
bob.ip.base = git
bob.ip.color = git
bob.ip.draw = git
bob.ip.gabor = git
bob.learn.linear = git
bob.learn.em = git
......@@ -62,9 +60,7 @@ bob.db.base = git
bob.db.atnt = git = git = git
bob.learn.boosting = git
bob.ip.facedetect = git
bob.ip.flandmark = git
recipe = bob.buildout:scripts
Markdown is supported
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment