def __init__(self, name="AFEW"):
super(AFEWImageSequenceDataset, self).__init__(name)
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.imagesequences = []
self.labels = []
self.trainIndexes = []
self.validIndexes = []
# For each emotion subfolder
idx = 0
directories = os.listdir(self.absolute_base_directory)
directories.sort()
for emotionName in directories:
# Check if it is a emotion subfolder
abs_emotionDir = os.path.join(self.absolute_base_directory,
emotionName)
rel_emotionDir = os.path.join(self.base_dir, emotionName)
if not os.path.isdir(
abs_emotionDir
) or emotionName not in self.emotionNames.keys():
continue
# abs_picasa_bbox_dir = os.path.join(self.absolute_picasa_boxes_base_directory, emotionName)
# rel_picasa_bbox_dir = os.path.join(self.picasa_boxes_base_dir, emotionName)
# Find all images
fileNames = glob.glob(os.path.join(abs_emotionDir, "*.png"))
# Find all unique sequences
uniqueSequence = list(
set([name.split("-")[0] for name in fileNames]))
uniqueSequence.sort()
# For each unique sequence
for sequence in uniqueSequence:
# Load the Image Sequence object
seq = AFEWImageSequence("AFEW", rel_emotionDir,
"{0}-*.png".format(sequence),
self.emotionNames[emotionName])
seq.set_picasa_path_substitutions(
{
self.base_dir: self.picasa_boxes_base_dir,
'-': '_',
'.png': '.txt',
'.jpg': '.txt',
},
csv_delimiter=' ')
self.imagesequences.append(seq)
# Save label
self.labels.append(self.emotionNames[emotionName])
# Save if in train or valid
self.trainIndexes.append(idx)
idx += 1
return
def __init__(self, name="AFEW"):
super(AFEWImageSequenceDataset,self).__init__(name)
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.imagesequences = []
self.labels = []
self.trainIndexes = []
self.validIndexes = []
# For each emotion subfolder
idx = 0
directories = os.listdir(self.absolute_base_directory)
directories.sort()
for emotionName in directories:
# Check if it is a emotion subfolder
abs_emotionDir = os.path.join(self.absolute_base_directory, emotionName)
rel_emotionDir = os.path.join(self.base_dir, emotionName)
if not os.path.isdir(abs_emotionDir) or emotionName not in self.emotionNames.keys():
continue
# abs_picasa_bbox_dir = os.path.join(self.absolute_picasa_boxes_base_directory, emotionName)
# rel_picasa_bbox_dir = os.path.join(self.picasa_boxes_base_dir, emotionName)
# Find all images
fileNames = glob.glob(os.path.join(abs_emotionDir, "*.png"))
# Find all unique sequences
uniqueSequence = list(set([name.split("-")[0] for name in fileNames]))
uniqueSequence.sort()
# For each unique sequence
for sequence in uniqueSequence:
# Load the Image Sequence object
seq = AFEWImageSequence("AFEW", rel_emotionDir,
"{0}-*.png".format(sequence),
self.emotionNames[emotionName])
seq.set_picasa_path_substitutions(
{self.base_dir:self.picasa_boxes_base_dir,
'-':'_',
'.png':'.txt',
'.jpg':'.txt',
}, csv_delimiter=' ')
self.imagesequences.append(seq)
# Save label
self.labels.append(self.emotionNames[emotionName])
# Save if in train or valid
self.trainIndexes.append(idx)
idx += 1
return
def __init__(self, dataset_name, relative_base_directory=None):
"""
Initilizes a dataset with the given name, and whose
constituent files are located in the specified
directory. This directory is specified only relative to
some standard dataset root location (found with locate_data_path )
"""
self.dataset_name = dataset_name
if relative_base_directory is not None:
self.relative_base_directory = relative_base_directory
self.absolute_base_directory = locate_data_path(relative_base_directory)
def __init__(self):
super(TorontoFaceDataset, self).__init__("TFD", "faces/TFD/")
# Load original 48x48 images
tfd_48x48 = sio.loadmat(os.path.join(self.absolute_base_directory, "TFD_48x48.mat"))
self.images = tfd_48x48["images"]
self.labels = tfd_48x48['labs_ex']
self.folds = tfd_48x48['folds']
# Load mapping file to original dataset
self.mapping = sio.loadmat(locate_data_path("faces/TFD_extra/TFD_info.mat"))
self.mapping = [x[0].encode('ascii', 'ignore') for x in self.mapping["tfd_info"]["imfiles"][0, 0].flatten()]
self.knownDataset = {}
def __init__(self, dataset_name, relative_base_directory=None):
"""
Initilizes a dataset with the given name, and whose
constituent files are located in the specified
directory. This directory is specified only relative to
some standard dataset root location (found with locate_data_path )
"""
self.dataset_name = dataset_name
if relative_base_directory is not None:
self.relative_base_directory = relative_base_directory
self.absolute_base_directory = locate_data_path(
relative_base_directory)
def __init__(self):
super(TorontoFaceDataset, self).__init__("TFD", "faces/TFD/")
# Load original 48x48 images
tfd_48x48 = sio.loadmat(
os.path.join(self.absolute_base_directory, "TFD_48x48.mat"))
self.images = tfd_48x48["images"]
self.labels = tfd_48x48['labs_ex']
self.folds = tfd_48x48['folds']
# Load mapping file to original dataset
self.mapping = sio.loadmat(
locate_data_path("faces/TFD_extra/TFD_info.mat"))
self.mapping = [
x[0].encode('ascii', 'ignore')
for x in self.mapping["tfd_info"]["imfiles"][0, 0].flatten()
]
self.knownDataset = {}
def __init__(self, preload_facetubes=False):
"""
If preload_facetubes is True, all facetubes will be loaded
when the dataset is built, which takes around 1.2 GB.
"""
super(AFEW2ImageSequenceDataset,self).__init__("AFEW2")
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.face_tubes_base_directory = locate_data_path(
self.face_tubes_base_dir)
self.preload_facetubes = preload_facetubes
self.imagesequences = []
self.labels = []
self.seq_info = []
self.trainIndexes = []
self.validIndexes = []
# For each split (Train or Val)
idx = 0
splits = (("Train", self.trainIndexes),
("Val", self.validIndexes))
for split_name, split_index in splits:
#print 'processing %s' % split_name
for emo_name in sorted(self.emotionNames.keys()):
#print ' %s' % emo_name
# Directory containing the images for all clips of that
# emotion in that split
abs_img_dir = os.path.join(self.absolute_base_directory,
split_name, emo_name)
rel_img_dir = os.path.join(self.base_dir,
split_name, emo_name)
#print 'abs_img_dir:', abs_img_dir
if not os.path.isdir(abs_img_dir):
continue
# Directory containing the picasa bounding boxes for clips
# of that emotion in that split
picasa_bbox_dir = os.path.join(
self.absolute_picasa_boxes_base_directory,
split_name, emo_name)
# Find all image names
img_names = glob.glob(os.path.join(abs_img_dir, '*.png'))
#print '%s img_names' % len(img_names)
# Find all clips (sequences)
unique_seq = sorted(set([img.split('-')[0]
for img in img_names]))
#print '%s unique_seq' % len(unique_seq)
# For each clip
for seq in unique_seq:
# Load the Image Sequence object
# pdb.set_trace()
im_seq = afew.AFEWImageSequence("AFEW2",
rel_img_dir,
"{0}-*.png".format(seq),
self.emotionNames[emo_name])
im_seq.set_picasa_path_substitutions(
{self.base_dir:self.picasa_boxes_base_dir,
'.png':'.txt',
'.jpg':'.txt',
}, csv_delimiter=',')
im_seq.set_ramanan_path_substitutions( {
'EmotiW/images/Train/':'EmotiW/ramananExtract/matExtractTrain/',
'EmotiW/images/Val/':'EmotiW/ramananExtract/matExtractVal/',
'Angry/':'1_',
'Disgust/':'2_',
'Fear/':'3_',
'Happy/':'4_',
'Neutral/':'5_',
'Sad/':'6_',
'Surprise/':'7_',
'.jpg':'.mat',
'.png':'.mat'
} )
self.imagesequences.append(im_seq)
# Save (split, emotion, sequence ID) of sequence
seq_id = os.path.basename(seq)
self.seq_info.append((split_name, emo_name, seq_id))
# If needed, load facetubes
if self.preload_facetubes:
self.facetubes.append(self.load_facetubes(
split_name, emo_name, seq_id))
# Save label
self.labels.append(self.emotionNames[emo_name])
# Save split
split_index.append(idx)
idx += 1
def __init__(self, preload_facetubes=False, preproc=[], size=(96, 96)):
"""
If preload_facetubes is True, all facetubes will be loaded when the
data set is built.
"""
self.face_tubes_base_dir = self.face_tubes_base_dir%(size[0], size[1])
self.facetubes_to_filter = None
for opt in preproc:
if opt == "smooth":
# Use the bounding-boxes smoothed version of the face tubes.
self.face_tubes_base_dir = ("faces/new_clips/smooth_picasa_face_tubes_%s_%s"
"/numpy_arr_concatenated")%(size[0], size[1])
self.face_tubes_boxes_base_dir = ("faces/new_clips/smooth_picasa_face_tubes_%s_%s"
"/picasa_tubes_pickles")%(size[0], size[1])
if opt == "remove_background_faces":
# Remove background faces as many as possible from the dataset.
# Path to the dictionary giving for each dataset, the list of
# face tubes corresponding to background faces/objects.
abs_dir = locate_data_path("faces/new_clips")
filename = os.path.join(abs_dir, "background_info.pkl")
try:
f = open(filename, 'rb')
self.facetubes_to_filter = cPickle.load(f)
f.close()
except IOError as e:
print e
super(afew.AFEWImageSequenceDataset, self).__init__("NewClips")
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.face_tubes_base_directory = locate_data_path(
self.face_tubes_base_dir)
self.face_tubes_boxes_base_directory = locate_data_path(
self.face_tubes_boxes_base_dir)
self.emodict_base_directory = locate_data_path(
self.emodict_dir)
self.preload_facetubes = preload_facetubes
self.preproc = preproc
self.size = size
self.imagesequences = []
self.labels = []
self.seq_info = []
self.trainIndexes = []
self.validIndexes = []
self.emo2numDict = {}
self.num2emoDict = {}
# Dictionary that gives a mapping from emotion name to clip id.
file = open(os.path.join(self.emodict_base_directory,
"newFilenameTranslate.txt"), 'r')
line = file.readline()
while line != '':
if line[0] != '=':
ln = line.split(':')
emo = ln[0].strip()
num = ln[1].strip().split(' ')[0]
self.emo2numDict[emo] = num
self.num2emoDict[num] = emo
line = file.readline()
# No validation split for this dataset
# Find all clips to keep (not marked "REJECT" during labeling)
labels_file = os.path.join(self.absolute_base_directory, 'labels.txt')
f = open(labels_file, 'r')
clips_and_targets = [(clip_name[:-4], target)
for clip_name, target in [
l.split() for l in f.readlines()]
if target != 'REJECT']
idx = 0
for clip_name, target in clips_and_targets:
if clip_name in self.seq_info:
# Due to a mistake, some clips have been labeled twice,
# so the same clip_name appears more than once in the list.
# The simplest solution is to only use the first instance.
continue
#abs_img_dir = os.path.join(self.absolute_base_directory,
# clip_name)
rel_img_dir = os.path.join(self.base_dir,
clip_name)
im_seq = afew.AFEWImageSequence(
"NewClips",
rel_img_dir,
'*.png',
self.emotionNames[target])
im_seq.set_picasa_path_substitutions(
{self.base_dir: self.picasa_boxes_base_dir,
'.png': '.txt'},
csv_delimiter=',')
#im_seq.set_ramanan_path_substitutions(
# # ???
# )
self.imagesequences.append(im_seq)
# Save clip_name of sequence
self.seq_info.append(clip_name)
# If needed, load facetubes
if self.preload_facetubes:
self.facetubes.append(self.load_facetubes(clip_name))
# Save label
self.labels.append(self.emotionNames[target])
# Save split
self.trainIndexes.append(idx)
idx += 1
def __init__(self, preload_facetubes=False, preproc=[], size=(96, 96)):
"""
If preload_facetubes is True, all facetubes will be loaded
when the dataset is built, which takes around 1.2 GB.
"""
self.face_tubes_base_dir = self.face_tubes_base_dir % (size[0],
size[1])
self.facetubes_to_filter = None
for opt in preproc:
if opt == "smooth":
# Smoothed face tubes directory.
self.face_tubes_base_dir = (
"faces/EmotiW/smooth_picasa_face_tubes_%s_%s"
"/numpy_arr/concatenate") % (size[0], size[1])
# Smoothed bounding boxes directory.
self.face_tubes_boxes_base_dir = (
"faces/EmotiW/"
"smooth_picasa_face_tubes_%s_%s/picasa_tubes_pickles") % (
size[0], size[1])
if opt == "remove_background_faces":
# Remove background faces as many as possible from the dataset.
# Path to the dictionary giving for each dataset, the list of
# face tubes corresponding to background faces/objects.
abs_dir = locate_data_path("faces/EmotiW")
filename = os.path.join(abs_dir,
"background_faces_info_v2.pkl")
try:
# Retrieve the list of background faces (clip_id, facetube_id)
# for the given dataset that will be filtered out.
f = open(filename, 'rb')
info = cPickle.load(f)
f.close()
self.facetubes_to_filter = info
except IOError as e:
print e
super(afew.AFEWImageSequenceDataset, self).__init__("AFEW2")
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.face_tubes_base_directory = locate_data_path(
self.face_tubes_base_dir)
self.absolute_face_tubes_boxes_base_directory = locate_data_path(
self.face_tubes_boxes_base_dir)
self.preload_facetubes = preload_facetubes
self.preproc = preproc
self.size = size
self.imagesequences = []
self.labels = []
self.seq_info = []
self.trainIndexes = []
self.validIndexes = []
# For each split (Train or Val)
idx = 0
splits = (("Train", self.trainIndexes), ("Val", self.validIndexes))
seqnum = 0
for split_name, split_index in splits:
#print 'processing %s' % split_name
for emo_name in sorted(self.emotionNames.keys()):
#print ' %s' % emo_name
# Directory containing the images for all clips of that
# emotion in that split
abs_img_dir = os.path.join(self.absolute_base_directory,
split_name, emo_name)
rel_img_dir = os.path.join(self.base_dir, split_name, emo_name)
#print 'abs_img_dir:', abs_img_dir
if not os.path.isdir(abs_img_dir):
continue
# Directory containing the picasa bounding boxes for clips
# of that emotion in that split
picasa_bbox_dir = os.path.join(
self.absolute_picasa_boxes_base_directory, split_name,
emo_name)
# Find all image names
img_names = glob.glob(os.path.join(abs_img_dir, '*.png'))
#print '%s img_names' % len(img_names)
# Find all clips (sequences)
unique_seq = sorted(
set([img.split('-')[0] for img in img_names]))
#print '%s unique_seq' % len(unique_seq)
# For each clip
for seq in unique_seq:
# Load the Image Sequence object
# pdb.set_trace()
im_seq = afew.AFEWImageSequence(
"AFEW2_%d" % seqnum, rel_img_dir,
"{0}-*.png".format(seq), self.emotionNames[emo_name])
im_seq.cache_directory = os.path.join(
self.absolute_base_directory,
"cache_dir/seq_%04d" % seqnum)
im_seq.set_picasa_path_substitutions(
{
self.base_dir: self.picasa_boxes_base_dir,
'.png': '.txt',
'.jpg': '.txt',
},
csv_delimiter=',')
im_seq.set_ramanan_path_substitutions({
'EmotiW/images/Train/':
'EmotiW/ramananExtract/matExtractTrain/',
'EmotiW/images/Val/':
'EmotiW/ramananExtract/matExtractVal/',
'Angry/':
'1_',
'Disgust/':
'2_',
'Fear/':
'3_',
'Happy/':
'4_',
'Neutral/':
'5_',
'Sad/':
'6_',
'Surprise/':
'7_',
'.jpg':
'.mat',
'.png':
'.mat'
})
self.imagesequences.append(im_seq)
# Save (split, emotion, sequence ID) of sequence
seq_id = os.path.basename(seq)
self.seq_info.append((split_name, emo_name, seq_id))
# If needed, load facetubes
if self.preload_facetubes:
self.facetubes.append(
self.load_facetubes(split_name, emo_name, seq_id))
# Save label
self.labels.append(self.emotionNames[emo_name])
# Save split
split_index.append(idx)
idx += 1
seqnum += 1
def __init__(self, preload_facetubes=False, preproc=[], size=(96, 96)):
"""
If preload_facetubes is True, all facetubes will be loaded
when the dataset is built.
"""
self.face_tubes_base_dir = self.face_tubes_base_dir%(size[0], size[1])
self.facetubes_to_filter = None
for opt in preproc:
if opt == "smooth":
# Use the bounding-boxes smoothed version of the face tubes.
self.face_tubes_base_dir = ("faces/EmotiWTest/smooth_picasa_face_tubes_%s_%s"
"/v2/numpy_arr_concatenated")%(size[0], size[1])
self.face_tubes_boxes_base_dir = ("faces/EmotiWTest/smooth_picasa_face_tubes_%s_%s"
"/picasa_tubes_pickles")%(size[0], size[1])
if opt == "remove_background_faces":
# Remove background faces as many as possible from the dataset.
# Path to the dictionary giving for each dataset, the list of
# face tubes corresponding to background faces/objects.
abs_dir = locate_data_path("faces/EmotiWTest")
filename = os.path.join(abs_dir, "test_background_info.txt")
try:
f = open(filename)
lines = f.readlines()
f.close()
self.facetubes_to_filter = []
for line in lines:
self.facetubes_to_filter.append(line.strip())
except IOError as e:
print e
super(afew.AFEWImageSequenceDataset, self).__init__("AFEW2Test")
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.face_tubes_base_directory = locate_data_path(
self.face_tubes_base_dir)
self.face_tubes_boxes_base_directory = locate_data_path(
self.face_tubes_boxes_base_dir)
self.preload_facetubes = preload_facetubes
self.preproc = preproc
self.size = size
self.imagesequences = []
self.labels = []
self.seq_info = []
self.trainIndexes = [] # unused
self.validIndexes = [] # unused
self.testIndexes = []
idx = 0
# find all clips
clip_names = glob.glob(os.path.join(self.absolute_base_directory, '*'))
clip_names.sort()
# For each clip
for clip_name in clip_names:
rel_img_dir = os.path.join(self.base_dir, clip_name)
im_seq = afew.AFEWImageSequence(
"AFEW2Test",
rel_img_dir,
'*.png',
None)
im_seq.set_picasa_path_substitutions(
{self.base_dir: self.picasa_boxes_base_dir,
'_.png': '.txt',
'_.jpg': '.txt'},
csv_delimiter=',')
#im_seq.set_ramanan_path_substitutions(
# # ???
# )
self.imagesequences.append(im_seq)
# Save clip_name of sequence
self.seq_info.append(clip_name)
# If needed, load facetubes
if self.preload_facetubes:
self.facetubes.append(self.load_facetubes(clip_name))
# No label
self.labels.append(None)
# Save split
self.trainIndexes.append(idx)
idx += 1
def __init__(self, preload_facetubes=False, preproc=[], size=(96, 96)):
"""
If preload_facetubes is True, all facetubes will be loaded
when the dataset is built.
"""
self.face_tubes_base_dir = self.face_tubes_base_dir % (size[0],
size[1])
self.facetubes_to_filter = None
for opt in preproc:
if opt == "smooth":
# Use the bounding-boxes smoothed version of the face tubes.
self.face_tubes_base_dir = (
"faces/EmotiWTest/smooth_picasa_face_tubes_%s_%s"
"/v2/numpy_arr_concatenated") % (size[0], size[1])
self.face_tubes_boxes_base_dir = (
"faces/EmotiWTest/smooth_picasa_face_tubes_%s_%s"
"/picasa_tubes_pickles") % (size[0], size[1])
if opt == "remove_background_faces":
# Remove background faces as many as possible from the dataset.
# Path to the dictionary giving for each dataset, the list of
# face tubes corresponding to background faces/objects.
abs_dir = locate_data_path("faces/EmotiWTest")
filename = os.path.join(abs_dir, "test_background_info.txt")
try:
f = open(filename)
lines = f.readlines()
f.close()
self.facetubes_to_filter = []
for line in lines:
self.facetubes_to_filter.append(line.strip())
except IOError as e:
print e
super(afew.AFEWImageSequenceDataset, self).__init__("AFEW2Test")
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.face_tubes_base_directory = locate_data_path(
self.face_tubes_base_dir)
self.face_tubes_boxes_base_directory = locate_data_path(
self.face_tubes_boxes_base_dir)
self.preload_facetubes = preload_facetubes
self.preproc = preproc
self.size = size
self.imagesequences = []
self.labels = []
self.seq_info = []
self.trainIndexes = [] # unused
self.validIndexes = [] # unused
self.testIndexes = []
idx = 0
# find all clips
clip_names = glob.glob(os.path.join(self.absolute_base_directory, '*'))
clip_names.sort()
# For each clip
for clip_name in clip_names:
rel_img_dir = os.path.join(self.base_dir, clip_name)
im_seq = afew.AFEWImageSequence("AFEW2Test", rel_img_dir, '*.png',
None)
im_seq.set_picasa_path_substitutions(
{
self.base_dir: self.picasa_boxes_base_dir,
'_.png': '.txt',
'_.jpg': '.txt'
},
csv_delimiter=',')
#im_seq.set_ramanan_path_substitutions(
# # ???
# )
self.imagesequences.append(im_seq)
# Save clip_name of sequence
self.seq_info.append(clip_name)
# If needed, load facetubes
if self.preload_facetubes:
self.facetubes.append(self.load_facetubes(clip_name))
# No label
self.labels.append(None)
# Save split
self.trainIndexes.append(idx)
idx += 1
def __init__(self, preload_facetubes=False, preproc=[], size=(96, 96)):
"""
If preload_facetubes is True, all facetubes will be loaded when the
data set is built.
"""
self.face_tubes_base_dir = self.face_tubes_base_dir % (size[0],
size[1])
self.facetubes_to_filter = None
for opt in preproc:
if opt == "smooth":
# Use the bounding-boxes smoothed version of the face tubes.
self.face_tubes_base_dir = (
"faces/new_clips/smooth_picasa_face_tubes_%s_%s"
"/numpy_arr_concatenated") % (size[0], size[1])
self.face_tubes_boxes_base_dir = (
"faces/new_clips/smooth_picasa_face_tubes_%s_%s"
"/picasa_tubes_pickles") % (size[0], size[1])
if opt == "remove_background_faces":
# Remove background faces as many as possible from the dataset.
# Path to the dictionary giving for each dataset, the list of
# face tubes corresponding to background faces/objects.
abs_dir = locate_data_path("faces/new_clips")
filename = os.path.join(abs_dir, "background_info.pkl")
try:
f = open(filename, 'rb')
self.facetubes_to_filter = cPickle.load(f)
f.close()
except IOError as e:
print e
super(afew.AFEWImageSequenceDataset, self).__init__("NewClips")
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.face_tubes_base_directory = locate_data_path(
self.face_tubes_base_dir)
self.face_tubes_boxes_base_directory = locate_data_path(
self.face_tubes_boxes_base_dir)
self.emodict_base_directory = locate_data_path(self.emodict_dir)
self.preload_facetubes = preload_facetubes
self.preproc = preproc
self.size = size
self.imagesequences = []
self.labels = []
self.seq_info = []
self.trainIndexes = []
self.validIndexes = []
self.emo2numDict = {}
self.num2emoDict = {}
# Dictionary that gives a mapping from emotion name to clip id.
file = open(
os.path.join(self.emodict_base_directory,
"newFilenameTranslate.txt"), 'r')
line = file.readline()
while line != '':
if line[0] != '=':
ln = line.split(':')
emo = ln[0].strip()
num = ln[1].strip().split(' ')[0]
self.emo2numDict[emo] = num
self.num2emoDict[num] = emo
line = file.readline()
# No validation split for this dataset
# Find all clips to keep (not marked "REJECT" during labeling)
labels_file = os.path.join(self.absolute_base_directory, 'labels.txt')
f = open(labels_file, 'r')
clips_and_targets = [
(clip_name[:-4], target)
for clip_name, target in [l.split() for l in f.readlines()]
if target != 'REJECT'
]
idx = 0
for clip_name, target in clips_and_targets:
if clip_name in self.seq_info:
# Due to a mistake, some clips have been labeled twice,
# so the same clip_name appears more than once in the list.
# The simplest solution is to only use the first instance.
continue
#abs_img_dir = os.path.join(self.absolute_base_directory,
# clip_name)
rel_img_dir = os.path.join(self.base_dir, clip_name)
im_seq = afew.AFEWImageSequence("NewClips", rel_img_dir, '*.png',
self.emotionNames[target])
im_seq.set_picasa_path_substitutions(
{
self.base_dir: self.picasa_boxes_base_dir,
'.png': '.txt'
},
csv_delimiter=',')
#im_seq.set_ramanan_path_substitutions(
# # ???
# )
self.imagesequences.append(im_seq)
# Save clip_name of sequence
self.seq_info.append(clip_name)
# If needed, load facetubes
if self.preload_facetubes:
self.facetubes.append(self.load_facetubes(clip_name))
# Save label
self.labels.append(self.emotionNames[target])
# Save split
self.trainIndexes.append(idx)
idx += 1
def __init__(self, preload_facetubes=False, preproc=[], size=(96, 96)):
"""
If preload_facetubes is True, all facetubes will be loaded
when the dataset is built, which takes around 1.2 GB.
"""
self.face_tubes_base_dir = self.face_tubes_base_dir%(size[0], size[1])
self.facetubes_to_filter = None
for opt in preproc:
if opt == "smooth":
# Smoothed face tubes directory.
self.face_tubes_base_dir = ("faces/EmotiW/smooth_picasa_face_tubes_%s_%s"
"/numpy_arr/concatenate")%(size[0], size[1])
# Smoothed bounding boxes directory.
self.face_tubes_boxes_base_dir = ("faces/EmotiW/"
"smooth_picasa_face_tubes_%s_%s/picasa_tubes_pickles")%(size[0], size[1])
if opt == "remove_background_faces":
# Remove background faces as many as possible from the dataset.
# Path to the dictionary giving for each dataset, the list of
# face tubes corresponding to background faces/objects.
abs_dir = locate_data_path("faces/EmotiW")
filename = os.path.join(abs_dir, "background_faces_info_v2.pkl")
try:
# Retrieve the list of background faces (clip_id, facetube_id)
# for the given dataset that will be filtered out.
f = open(filename, 'rb')
info = cPickle.load(f)
f.close()
self.facetubes_to_filter = info
except IOError as e:
print e
super(afew.AFEWImageSequenceDataset,self).__init__("AFEW2")
self.absolute_base_directory = locate_data_path(self.base_dir)
self.absolute_picasa_boxes_base_directory = locate_data_path(
self.picasa_boxes_base_dir)
self.face_tubes_base_directory = locate_data_path(
self.face_tubes_base_dir)
self.absolute_face_tubes_boxes_base_directory = locate_data_path(
self.face_tubes_boxes_base_dir)
self.preload_facetubes = preload_facetubes
self.preproc = preproc
self.size = size
self.imagesequences = []
self.labels = []
self.seq_info = []
self.trainIndexes = []
self.validIndexes = []
# For each split (Train or Val)
idx = 0
splits = (("Train", self.trainIndexes),
("Val", self.validIndexes))
seqnum = 0
for split_name, split_index in splits:
#print 'processing %s' % split_name
for emo_name in sorted(self.emotionNames.keys()):
#print ' %s' % emo_name
# Directory containing the images for all clips of that
# emotion in that split
abs_img_dir = os.path.join(self.absolute_base_directory,
split_name, emo_name)
rel_img_dir = os.path.join(self.base_dir,
split_name, emo_name)
#print 'abs_img_dir:', abs_img_dir
if not os.path.isdir(abs_img_dir):
continue
# Directory containing the picasa bounding boxes for clips
# of that emotion in that split
picasa_bbox_dir = os.path.join(
self.absolute_picasa_boxes_base_directory,
split_name, emo_name)
# Find all image names
img_names = glob.glob(os.path.join(abs_img_dir, '*.png'))
#print '%s img_names' % len(img_names)
# Find all clips (sequences)
unique_seq = sorted(set([img.split('-')[0]
for img in img_names]))
#print '%s unique_seq' % len(unique_seq)
# For each clip
for seq in unique_seq:
# Load the Image Sequence object
# pdb.set_trace()
im_seq = afew.AFEWImageSequence("AFEW2_%d"%seqnum,
rel_img_dir,
"{0}-*.png".format(seq),
self.emotionNames[emo_name])
im_seq.cache_directory = os.path.join(self.absolute_base_directory,"cache_dir/seq_%04d"%seqnum)
im_seq.set_picasa_path_substitutions(
{self.base_dir:self.picasa_boxes_base_dir,
'.png':'.txt',
'.jpg':'.txt',
}, csv_delimiter=',')
im_seq.set_ramanan_path_substitutions( {
'EmotiW/images/Train/':'EmotiW/ramananExtract/matExtractTrain/',
'EmotiW/images/Val/':'EmotiW/ramananExtract/matExtractVal/',
'Angry/':'1_',
'Disgust/':'2_',
'Fear/':'3_',
'Happy/':'4_',
'Neutral/':'5_',
'Sad/':'6_',
'Surprise/':'7_',
'.jpg':'.mat',
'.png':'.mat'
} )
self.imagesequences.append(im_seq)
# Save (split, emotion, sequence ID) of sequence
seq_id = os.path.basename(seq)
self.seq_info.append((split_name, emo_name, seq_id))
# If needed, load facetubes
if self.preload_facetubes:
self.facetubes.append(self.load_facetubes(
split_name, emo_name, seq_id))
# Save label
self.labels.append(self.emotionNames[emo_name])
# Save split
split_index.append(idx)
idx += 1
seqnum += 1
