def _get_distance(model, data, load_from_cache=False, save_to_cache=False):
if load_from_cache:
with open(_cached_distmat, 'rb') as f:
D, G, P = cPickle.load(f)
else:
print "Computing distance matrix ..."
x = T.matrix('x')
y = model.get_output(x)
output_func = theano.function(inputs=[x], outputs=y)
X = [_preproc(image) for pid, image in data[0]]
Y = [_preproc(image) for pid, image in data[1]]
X = imageproc.images2mat(X).astype(theano.config.floatX)
Y = imageproc.images2mat(Y).astype(theano.config.floatX)
R = [0] * X.shape[0]
for i in xrange(X.shape[0]):
R[i] = output_func(X[i:i + 1, :]).ravel()
R = numpy.asarray(R)
D = cdist(R, Y, 'euclidean')
G = numpy.asarray([pid for pid, image in data[0]])
P = numpy.asarray([pid for pid, image in data[1]])
if save_to_cache:
with open(_cached_distmat, 'wb') as f:
cPickle.dump((D, G, P), f, protocol=cPickle.HIGHEST_PROTOCOL)
with open(_cached_output, 'wb') as f:
cPickle.dump((X, Y, R), f, protocol=cPickle.HIGHEST_PROTOCOL)
return (D, G, P)
def _get_distance(model, data, load_from_cache=False, save_to_cache=False):
if load_from_cache:
with open(_cached_distmat, 'rb') as f:
D, G, P = cPickle.load(f)
else:
print "Computing distance matrix ..."
x = T.matrix('x')
y = model.get_output(x)
output_func = theano.function(inputs=[x], outputs=y)
X = [_preproc(image) for pid, image in data[0]]
Y = [_preproc(image) for pid, image in data[1]]
X = imageproc.images2mat(X).astype(theano.config.floatX)
Y = imageproc.images2mat(Y).astype(theano.config.floatX)
R = [0] * X.shape[0]
for i in xrange(X.shape[0]):
R[i] = output_func(X[i:i+1, :]).ravel()
R = numpy.asarray(R)
D = cdist(R, Y, 'euclidean')
G = numpy.asarray([pid for pid, image in data[0]])
P = numpy.asarray([pid for pid, image in data[1]])
if save_to_cache:
with open(_cached_distmat, 'wb') as f:
cPickle.dump((D, G, P), f, protocol=cPickle.HIGHEST_PROTOCOL)
with open(_cached_output, 'wb') as f:
cPickle.dump((X, Y, R), f, protocol=cPickle.HIGHEST_PROTOCOL)
return (D, G, P)
def _select_group(images, attributes, group, gtype, load_from_cache=False, save_to_cache=False):
print "Selecting Group ..."
print "==================="
if load_from_cache:
with open(_cached_group, 'rb') as f:
selected_images, selected_attributes = cPickle.load(f)
else:
attr_id = [attribute_names.index(name) for name in group]
attributes = [attr[attr_id] for attr in attributes]
if gtype == 'unique':
judge_func = lambda x: x.sum() == 1
select_func = lambda x: numpy.where(x == 1)[0]
else:
judge_func = lambda x: x.sum() != 0
select_func = lambda x: x
selected_images = []
selected_attributes = []
for img, attr in zip(images, attributes):
if judge_func(attr): # Some data are mis-labeled
selected_images.append(img)
selected_attributes.append(select_func(attr))
selected_images = imageproc.images2mat(selected_images)
selected_attributes = imageproc.images2mat(selected_attributes)
if save_to_cache:
with open(_cached_group, 'wb') as f:
cPickle.dump((selected_images, selected_attributes), f,
protocol=cPickle.HIGHEST_PROTOCOL)
return (selected_images, selected_attributes)
def _select_group(images,
attributes,
group,
gtype,
load_from_cache=False,
save_to_cache=False):
print "Selecting Group ..."
print "==================="
if load_from_cache:
with open(_cached_group, 'rb') as f:
selected_images, selected_attributes = cPickle.load(f)
else:
attr_id = [attribute_names.index(name) for name in group]
attributes = [attr[attr_id] for attr in attributes]
if gtype == 'unique':
judge_func = lambda x: x.sum() == 1
select_func = lambda x: numpy.where(x == 1)[0]
else:
judge_func = lambda x: x.sum() != 0
select_func = lambda x: x
selected_images = []
selected_attributes = []
for img, attr in zip(images, attributes):
if judge_func(attr): # Some data are mis-labeled
selected_images.append(img)
selected_attributes.append(select_func(attr))
selected_images = imageproc.images2mat(selected_images)
selected_attributes = imageproc.images2mat(selected_attributes)
if save_to_cache:
with open(_cached_group, 'wb') as f:
cPickle.dump((selected_images, selected_attributes),
f,
protocol=cPickle.HIGHEST_PROTOCOL)
return (selected_images, selected_attributes)
def _mask_dataset():
# Load model and compile function
with open('../cache/foreground_model.pkl', 'rb') as f:
model, threshold = cPickle.load(f)
x = T.matrix('x')
y = model.get_output(x)
output_func = theano.function(inputs=[x], outputs=(y >= threshold))
# Load data
image_data = DataLoader('../data/cuhk_small.mat', verbose=True)
# Pre-processing
print "Pre-processing ..."
images = image_data.get_all_images()
images = [_input_preproc(image) for image in images]
images = imageproc.images2mat(images).astype(theano.config.floatX)
# Compute masks
print "Computing masks ..."
masks = output_func(images)
# Save masks
print "Saving data ..."
mask_data = DataSaver()
cur_index = 0
for gid in xrange(image_data.get_n_groups()):
m, v = image_data.get_n_pedes_views(gid)
mask_data.add_group(m, v)
for pid in xrange(m):
n_images = image_data.get_n_images(gid, pid)
for vid, n in enumerate(n_images):
view_masks = [0] * n
for k in xrange(n):
mask = masks[cur_index, :]
mask = mask.reshape(160, 80, 1)
orig_image = image_data.get_image(gid, pid, vid, k)
orig_image = imageproc.imresize(orig_image, (160, 80, 3))
view_masks[k] = (mask * orig_image).astype(numpy.uint8)
cur_index += 1
mask_data.set_images(gid, pid, vid, view_masks)
mask_data.save('../data/cuhk_small_masked.mat')
def _mask_dataset():
# Load model and compile function
with open('../cache/foreground_model.pkl', 'rb') as f:
model, threshold = cPickle.load(f)
x = T.matrix('x')
y = model.get_output(x)
output_func = theano.function(inputs=[x], outputs=(y >= threshold))
# Load data
image_data = DataLoader('../data/cuhk_small.mat', verbose=True)
# Pre-processing
print "Pre-processing ..."
images = image_data.get_all_images()
images = [_input_preproc(image) for image in images]
images = imageproc.images2mat(images).astype(theano.config.floatX)
# Compute masks
print "Computing masks ..."
masks = output_func(images)
# Save masks
print "Saving data ..."
mask_data = DataSaver()
cur_index = 0
for gid in xrange(image_data.get_n_groups()):
m, v = image_data.get_n_pedes_views(gid)
mask_data.add_group(m, v)
for pid in xrange(m):
n_images = image_data.get_n_images(gid, pid)
for vid, n in enumerate(n_images):
view_masks = [0] * n
for k in xrange(n):
mask = masks[cur_index, :]
mask = mask.reshape(160, 80, 1)
orig_image = image_data.get_image(gid, pid, vid, k)
orig_image = imageproc.imresize(orig_image, (160, 80, 3))
view_masks[k] = (mask * orig_image).astype(numpy.uint8)
cur_index += 1
mask_data.set_images(gid, pid, vid, view_masks)
mask_data.save('../data/cuhk_small_masked.mat')
def _prepare_data(load_from_cache=False, save_to_cache=False):
if load_from_cache:
with open(_cached_datasets, 'rb') as f:
datasets = cPickle.load(f)
else:
# Setup data files
input_data = DataLoader(
'../data/parse/cuhk_large_labeled_subsampled.mat',
verbose=True)
target_data = DataLoader(
'../data/parse/cuhk_large_labeled_subsampled_parse.mat',
verbose=True)
input_images = input_data.get_all_images()
target_images = target_data.get_all_images()
# Pre-processing
print "Pre-processing ..."
inputs = [_input_preproc(image) for image in input_images]
inputs = imageproc.images2mat(inputs)
targets = [_target_preproc(image) for image in target_images]
targets = imageproc.images2mat(targets)
# Prepare the datasets
print "Prepare the datasets ..."
datasets = Datasets(inputs, targets)
datasets.split(train_ratio=0.5, valid_ratio=0.3)
if save_to_cache:
with open(_cached_datasets, 'wb') as f:
cPickle.dump(datasets, f, protocol=cPickle.HIGHEST_PROTOCOL)
return datasets
def _prepare_data(load_from_cache=False, save_to_cache=False):
if load_from_cache:
with open(_cached_datasets, 'rb') as f:
datasets = cPickle.load(f)
else:
# Setup data files
input_data = DataLoader(
'../data/parse/cuhk_large_labeled_subsampled.mat', verbose=True)
target_data = DataLoader(
'../data/parse/cuhk_large_labeled_subsampled_parse.mat',
verbose=True)
input_images = input_data.get_all_images()
target_images = target_data.get_all_images()
# Pre-processing
print "Pre-processing ..."
inputs = [_input_preproc(image) for image in input_images]
inputs = imageproc.images2mat(inputs)
targets = [_target_preproc(image) for image in target_images]
targets = imageproc.images2mat(targets)
# Prepare the datasets
print "Prepare the datasets ..."
datasets = Datasets(inputs, targets)
datasets.split(train_ratio=0.5, valid_ratio=0.3)
if save_to_cache:
with open(_cached_datasets, 'wb') as f:
cPickle.dump(datasets, f, protocol=cPickle.HIGHEST_PROTOCOL)
return datasets
def _prepare_data(load_from_cache=False, save_to_cache=False):
if load_from_cache:
with open(_cached_datasets, 'rb') as f:
views_data, datasets = cPickle.load(f)
else:
image_data = DataLoader('../data/cuhk_small_masked.mat', verbose=True)
# Prepare the view-first order data representation
print "Preparing the view-first order data ..."
n_pedes, n_views = [], []
for gid in xrange(image_data.get_n_groups()):
m, v = image_data.get_n_pedes_views(gid)
n_pedes.append(m)
n_views.append(v)
assert min(n_views) == max(n_views), \
"The number of views in each group should be equal"
v = n_views[0]
views_data = [[] for __ in xrange(v)]
for gid in xrange(image_data.get_n_groups()):
bias = sum(n_pedes[0:gid])
group_data = data_manager.view_repr(image_data.get_pedes(gid))
for vid in xrange(v):
view_data = group_data[vid]
view_data = [(pid+bias, image) for pid, image in view_data]
views_data[vid].extend(view_data)
# Prepare the datasets
print "Prepare the datasets ..."
X, Y = [], []
for gid in xrange(image_data.get_n_groups()):
m, v = image_data.get_n_pedes_views(gid)
for pid in xrange(m):
n_images = image_data.get_n_images(gid, pid)
for vi in xrange(v):
for vj in xrange(vi+1, v):
for i in xrange(n_images[vi]):
for j in xrange(n_images[vj]):
X.append(_preproc(
image_data.get_image(gid, pid, vi, i)))
Y.append(_preproc(
image_data.get_image(gid, pid, vj, j)))
X = imageproc.images2mat(X).astype(theano.config.floatX)
Y = imageproc.images2mat(Y).astype(theano.config.floatX)
datasets = Datasets(X, Y)
datasets.split(train_ratio=0.8, valid_ratio=0.1)
if save_to_cache:
with open(_cached_datasets, 'wb') as f:
cPickle.dump((views_data, datasets), f,
protocol=cPickle.HIGHEST_PROTOCOL)
return (views_data, datasets)
def _prepare_data(load_from_cache=False, save_to_cache=False):
if load_from_cache:
with open(_cached_datasets, 'rb') as f:
views_data, datasets = cPickle.load(f)
else:
image_data = DataLoader('../data/cuhk_small_masked.mat', verbose=True)
# Prepare the view-first order data representation
print "Preparing the view-first order data ..."
n_pedes, n_views = [], []
for gid in xrange(image_data.get_n_groups()):
m, v = image_data.get_n_pedes_views(gid)
n_pedes.append(m)
n_views.append(v)
assert min(n_views) == max(n_views), \
"The number of views in each group should be equal"
v = n_views[0]
views_data = [[] for __ in xrange(v)]
for gid in xrange(image_data.get_n_groups()):
bias = sum(n_pedes[0:gid])
group_data = data_manager.view_repr(image_data.get_pedes(gid))
for vid in xrange(v):
view_data = group_data[vid]
view_data = [(pid + bias, image) for pid, image in view_data]
views_data[vid].extend(view_data)
# Prepare the datasets
print "Prepare the datasets ..."
X, Y = [], []
for gid in xrange(image_data.get_n_groups()):
m, v = image_data.get_n_pedes_views(gid)
for pid in xrange(m):
n_images = image_data.get_n_images(gid, pid)
for vi in xrange(v):
for vj in xrange(vi + 1, v):
for i in xrange(n_images[vi]):
for j in xrange(n_images[vj]):
X.append(
_preproc(
image_data.get_image(gid, pid, vi, i)))
Y.append(
_preproc(
image_data.get_image(gid, pid, vj, j)))
X = imageproc.images2mat(X).astype(theano.config.floatX)
Y = imageproc.images2mat(Y).astype(theano.config.floatX)
datasets = Datasets(X, Y)
datasets.split(train_ratio=0.8, valid_ratio=0.1)
if save_to_cache:
with open(_cached_datasets, 'wb') as f:
cPickle.dump((views_data, datasets),
f,
protocol=cPickle.HIGHEST_PROTOCOL)
return (views_data, datasets)
