From 9e1e49c9046109f81bbe3095f348c1ffc4903ed4 Mon Sep 17 00:00:00 2001
From: Olegs NIKISINS <onikisins@italix03.idiap.ch>
Date: Fri, 29 Sep 2017 10:48:59 +0200
Subject: [PATCH] Moved histogram extraction to preprocessor VideoSparseCoding
---
.../preprocessor/video_sparse_coding.py | 85 ++++++++++++++-
.../face/preprocessor/VideoSparseCoding.py | 100 +++++++++++++++++-
setup.py | 4 +
3 files changed, 185 insertions(+), 4 deletions(-)
diff --git a/bob/pad/face/config/preprocessor/video_sparse_coding.py b/bob/pad/face/config/preprocessor/video_sparse_coding.py
index 5de78ecf..905dd7b0 100644
--- a/bob/pad/face/config/preprocessor/video_sparse_coding.py
+++ b/bob/pad/face/config/preprocessor/video_sparse_coding.py
@@ -20,4 +20,87 @@ preprocessor = VideoSparseCoding(gblock_size = BLOCK_SIZE,
min_face_size = MIN_FACE_SIZE,
norm_face_size = NORM_FACE_SIZE,
dictionary_file_names = DICTIONARY_FILE_NAMES,
- frame_step = FRAME_STEP)
\ No newline at end of file
+ frame_step = FRAME_STEP)
+
+
+#=======================================================================================
+
+
+BLOCK_SIZE = 5
+BLOCK_LENGTH = 10
+MIN_FACE_SIZE = 50
+NORM_FACE_SIZE = 64
+DICTIONARY_FILE_NAMES = ["/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_front_10_5_16.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_hor_10_5_16.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_vert_10_5_16.hdf5"]
+FRAME_STEP = 2
+EXTRACT_HISTOGRAMS_FLAG = True
+
+preprocessor_10_5_16 = VideoSparseCoding(gblock_size = BLOCK_SIZE,
+ block_length = BLOCK_LENGTH,
+ min_face_size = MIN_FACE_SIZE,
+ norm_face_size = NORM_FACE_SIZE,
+ dictionary_file_names = DICTIONARY_FILE_NAMES,
+ frame_step = FRAME_STEP,
+ extract_histograms_flag = EXTRACT_HISTOGRAMS_FLAG)
+
+BLOCK_SIZE = 5
+BLOCK_LENGTH = 10
+MIN_FACE_SIZE = 50
+NORM_FACE_SIZE = 64
+DICTIONARY_FILE_NAMES = ["/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_front_10_5_32.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_hor_10_5_32.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_vert_10_5_32.hdf5"]
+FRAME_STEP = 2
+EXTRACT_HISTOGRAMS_FLAG = True
+
+preprocessor_10_5_32 = VideoSparseCoding(gblock_size = BLOCK_SIZE,
+ block_length = BLOCK_LENGTH,
+ min_face_size = MIN_FACE_SIZE,
+ norm_face_size = NORM_FACE_SIZE,
+ dictionary_file_names = DICTIONARY_FILE_NAMES,
+ frame_step = FRAME_STEP,
+ extract_histograms_flag = EXTRACT_HISTOGRAMS_FLAG)
+
+BLOCK_SIZE = 5
+BLOCK_LENGTH = 10
+MIN_FACE_SIZE = 50
+NORM_FACE_SIZE = 64
+DICTIONARY_FILE_NAMES = ["/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_front_10_5_64.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_hor_10_5_64.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_vert_10_5_64.hdf5"]
+FRAME_STEP = 2
+EXTRACT_HISTOGRAMS_FLAG = True
+
+preprocessor_10_5_64 = VideoSparseCoding(gblock_size = BLOCK_SIZE,
+ block_length = BLOCK_LENGTH,
+ min_face_size = MIN_FACE_SIZE,
+ norm_face_size = NORM_FACE_SIZE,
+ dictionary_file_names = DICTIONARY_FILE_NAMES,
+ frame_step = FRAME_STEP,
+ extract_histograms_flag = EXTRACT_HISTOGRAMS_FLAG)
+
+
+BLOCK_SIZE = 5
+BLOCK_LENGTH = 10
+MIN_FACE_SIZE = 50
+NORM_FACE_SIZE = 64
+DICTIONARY_FILE_NAMES = ["/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_front_10_5_128.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_hor_10_5_128.hdf5",
+ "/idiap/user/onikisins/Projects/ODIN/Python/scripts/test_scripts/data/dictionary_vert_10_5_128.hdf5"]
+FRAME_STEP = 2
+EXTRACT_HISTOGRAMS_FLAG = True
+
+preprocessor_10_5_128 = VideoSparseCoding(gblock_size = BLOCK_SIZE,
+ block_length = BLOCK_LENGTH,
+ min_face_size = MIN_FACE_SIZE,
+ norm_face_size = NORM_FACE_SIZE,
+ dictionary_file_names = DICTIONARY_FILE_NAMES,
+ frame_step = FRAME_STEP,
+ extract_histograms_flag = EXTRACT_HISTOGRAMS_FLAG)
+
+
+
+
+
+
diff --git a/bob/pad/face/preprocessor/VideoSparseCoding.py b/bob/pad/face/preprocessor/VideoSparseCoding.py
index 4168882b..63cade37 100644
--- a/bob/pad/face/preprocessor/VideoSparseCoding.py
+++ b/bob/pad/face/preprocessor/VideoSparseCoding.py
@@ -51,7 +51,7 @@ class VideoSparseCoding(Preprocessor, object):
The size of the face after normalization. Default: 64 .
``dictionary_file_names`` : [:py:class:`str`]
- A list of filenames containing the dictionary. The filenames must be
+ A list of filenames containing the dictionaries. The filenames must be
listed in the following order:
[file_name_pointing_to_frontal_dictionary,
file_name_pointing_to_horizontal_dictionary,
@@ -61,6 +61,22 @@ class VideoSparseCoding(Preprocessor, object):
Selected frames for processing with this step. If set to 1, all frames
will be processes. Used to speed up the experiments.
Default: 1.
+
+ ``extract_histograms_flag`` : :py:class:`bool`
+ If this flag is set to ``True`` the histograms of sparse codes will be
+ computed for all stacks of facial images / samples. In this case an
+ empty feature extractor must be used, because feature vectors (histograms)
+ are already extracted in the preprocessing step.
+
+ NOTE: set this flag to``True`` if you want to reduce the amount of
+ memory required to store temporary files.
+ Default: ``False``.
+
+ ``method`` : :py:class:`str`
+ A method to use in the histogram computation. Two options are available:
+ "mean" and "hist". This argument is valid only if ``extract_histograms_flag``
+ is set to ``True``.
+ Default: "hist".
"""
#==========================================================================
@@ -71,6 +87,8 @@ class VideoSparseCoding(Preprocessor, object):
norm_face_size = 64,
dictionary_file_names = [],
frame_step = 1,
+ extract_histograms_flag = False,
+ method = "hist",
**kwargs):
super(VideoSparseCoding, self).__init__(block_size = block_size,
@@ -78,7 +96,9 @@ class VideoSparseCoding(Preprocessor, object):
min_face_size = min_face_size,
norm_face_size = norm_face_size,
dictionary_file_names = dictionary_file_names,
- frame_step = frame_step)
+ frame_step = frame_step,
+ extract_histograms_flag = extract_histograms_flag,
+ method = method)
self.block_size = block_size
self.block_length = block_length
@@ -86,6 +106,8 @@ class VideoSparseCoding(Preprocessor, object):
self.norm_face_size = norm_face_size
self.dictionary_file_names = dictionary_file_names
self.frame_step = frame_step
+ self.extract_histograms_flag = extract_histograms_flag
+ self.method = method
self.video_preprocessor = bob.bio.video.preprocessor.Wrapper()
@@ -692,6 +714,62 @@ class VideoSparseCoding(Preprocessor, object):
return frame_container
+ #==========================================================================
+ def comp_hist_of_sparse_codes(self, frames, method):
+ """
+ Compute the histograms of sparse codes.
+ """
+
+ histograms = []
+
+ for frame_data in frames:
+
+ frame = frame_data[1]
+
+ if method == "mean":
+
+ frame_codes = np.mean(frame, axis=1)
+
+ if method == "hist":
+
+ frame_codes = np.mean(frame!=0, axis=1)
+
+ for idx, row in enumerate(frame_codes):
+
+ frame_codes[idx,:] = row/np.sum(row)
+
+ hist = frame_codes.flatten()
+
+ histograms.append(hist)
+
+ return histograms
+
+
+ #==========================================================================
+ def convert_arrays_to_frame_container(self, list_of_arrays):
+ """
+ Convert an input list of arrays into Frame Container.
+
+ **Parameters:**
+
+ ``list_of_arrays`` : [:py:class:`numpy.ndarray`]
+ A list of arrays.
+
+ **Returns:**
+
+ ``frame_container`` : FrameContainer
+ FrameContainer containing the feature vectors.
+ """
+
+ frame_container = bob.bio.video.FrameContainer() # initialize the FrameContainer
+
+ for idx, item in enumerate(list_of_arrays):
+
+ frame_container.add(idx, item) # add frame to FrameContainer
+
+ return frame_container
+
+
#==========================================================================
def __call__(self, frames, annotations):
"""
@@ -702,6 +780,10 @@ class VideoSparseCoding(Preprocessor, object):
However, this number can be smaller, and is controlled by two arguments
of this class: ``min_face_size`` and ``frame_step``.
+ If ``self.extract_histograms_flag`` flag is set to ``True`` the
+ histograms of sparse codes will be computed for all possible stacks of
+ facial images.
+
**Parameters:**
``frames`` : FrameContainer
@@ -720,12 +802,18 @@ class VideoSparseCoding(Preprocessor, object):
**Returns:**
``frame_container`` : FrameContainer
+ If ``self.extract_histograms_flag`` flag is set to ``False`:
FrameContainer containing the frames with sparse codes for the
frontal, horizontal and vertical patches. Each frame is a 3D array.
- The dimensionality of array is:
+ The dimensionality of each array is:
(``3`` x ``n_samples`` x ``n_words_in_the_dictionary``).
The first slice in the 3D arrays corresponds to frontal sparse codes,
second slice to horizontal, and third to vertical codes.
+
+ If ``self.extract_histograms_flag`` flag is set to ``True`` the
+ histograms of sparse codes will be computed. In this case each
+ frame is a 1D array with dimensionality:
+ (3*``n_words_in_the_dictionary``, )
"""
# Convert frame container to 3D array:
@@ -749,6 +837,12 @@ class VideoSparseCoding(Preprocessor, object):
frame_container = self.convert_sparse_codes_to_frame_container([frontal_video_codes, horizontal_video_codes, vertical_video_codes])
+ if self.extract_histograms_flag: # in this case histograms will be extracted in the preprocessor , no feature extraction is needed then
+
+ histograms = self.comp_hist_of_sparse_codes(frame_container, self.method)
+
+ frame_container = self.convert_arrays_to_frame_container(histograms)
+
return frame_container
diff --git a/setup.py b/setup.py
index 552001a1..474dcb05 100644
--- a/setup.py
+++ b/setup.py
@@ -106,6 +106,10 @@ setup(
# The sparse coding based preprocessors
'sparse-coding-preprocessor = bob.pad.face.config.preprocessor.video_sparse_coding:preprocessor',
+ 'sparse-coding-preprocessor-10-5-16 = bob.pad.face.config.preprocessor.video_sparse_coding:preprocessor_10_5_16',
+ 'sparse-coding-preprocessor-10-5-32 = bob.pad.face.config.preprocessor.video_sparse_coding:preprocessor_10_5_32',
+ 'sparse-coding-preprocessor-10-5-64 = bob.pad.face.config.preprocessor.video_sparse_coding:preprocessor_10_5_64',
+ 'sparse-coding-preprocessor-10-5-128 = bob.pad.face.config.preprocessor.video_sparse_coding:preprocessor_10_5_128',
],
# registered extractors:
--
GitLab