def _form_nndata(images, attributes, load_from_cache=False, save_to_cache=False):
print "Forming NN-data ..."
print "==================="
if load_from_cache:
with open(_cached_nndata, 'rb') as f:
nndata = cPickle.load(f)
else:
nndata = Datasets(images, attributes)
nndata.split(0.8, 0.1)
if save_to_cache:
with open(_cached_nndata, 'wb') as f:
cPickle.dump(nndata, f, protocol=cPickle.HIGHEST_PROTOCOL)
return nndata
def _form_nndata(images,
attributes,
load_from_cache=False,
save_to_cache=False):
print "Forming NN-data ..."
print "==================="
if load_from_cache:
with open(_cached_nndata, 'rb') as f:
nndata = cPickle.load(f)
else:
nndata = Datasets(images, attributes)
nndata.split(0.8, 0.1)
if save_to_cache:
with open(_cached_nndata, 'wb') as f:
cPickle.dump(nndata, f, protocol=cPickle.HIGHEST_PROTOCOL)
return nndata
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)
from reid.models import cost_functions as costfuncs
from reid.models import active_functions as actfuncs
from reid.models.layers import FullConnLayer, ConvPoolLayer
from reid.models.neural_net import NeuralNet
from reid.models.evaluate import Evaluator
# Load the MNIST Dataset
with open(os.path.join('..', 'data', 'mnist', 'mnist.pkl'), 'rb') as f:
train_set, valid_set, test_set = cPickle.load(f)
train_set = (train_set[0], train_set[1].reshape(train_set[1].shape[0], 1))
valid_set = (valid_set[0], valid_set[1].reshape(valid_set[1].shape[0], 1))
test_set = (test_set[0], test_set[1].reshape(test_set[1].shape[0], 1))
datasets = Datasets(train_set=train_set,
valid_set=valid_set,
test_set=test_set)
# Build up the model and evaluator
layers = [
ConvPoolLayer((20, 1, 5, 5), (2, 2), (1, 28, 28), actfuncs.tanh, False),
ConvPoolLayer((50, 20, 5, 5), (2, 2), None, actfuncs.tanh, True),
FullConnLayer(800, 500, actfuncs.tanh),
FullConnLayer(500, 10, actfuncs.softmax)
]
model = NeuralNet(layers)
evaluator = Evaluator(model, costfuncs.mean_negative_loglikelihood,
costfuncs.mean_number_misclassified)
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)
