def test_image_load():
"""
Test utils.image.load
"""
assert_raises(AssertionError, load, 1)
path = os.path.join(pylearn2.__path__[0], 'utils',
'tests', 'example_image', 'mnist0.jpg')
img = load(path)
eq_(img.shape, (28, 28, 1))
def __init__(self, iterator, num_examples, image_shape):
assert len(image_shape) == 2
T = np.zeros((num_examples,image_shape[0],image_shape[1],3),dtype='float32')
for i in xrange(num_examples):
image_path = iterator.next()
img = image.load(image_path)
T[i,:] = make_letterboxed_thumbnail(img, image_shape)
super(DARPA_ImageNet, self).__init__(
topo_view = T,
view_converter = DefaultViewConverter(T.shape[1:]))
def __init__(self, iterator, num_examples, image_shape):
assert len(image_shape) == 2
T = np.zeros((num_examples, image_shape[0], image_shape[1], 3),
dtype='float32')
for i in xrange(num_examples):
image_path = iterator.next()
img = image.load(image_path)
T[i, :] = make_letterboxed_thumbnail(img, image_shape)
super(DARPA_ImageNet,
self).__init__(topo_view=T,
view_converter=DefaultViewConverter(T.shape[1:]))
from pylearn2.utils import image
import numpy as np
for i in xrange(5000):
print i
number = str(i)
while len(number) != 4:
number = '0' + number
img = image.load('/Tmp/video/' + number + '.png')
out = np.zeros((406, 406, 3))
for ofs_r in [0, 1]:
for ofs_c in [0, 1]:
out[ofs_r::2, ofs_c::2, :] = img
image.save('/Tmp/video_resized/' + number + '.png', out)
new_X = centered_X / T.maximum(1., divisor)
new_X = new_X.dimshuffle(0, 2, 3, 1)
from theano import function
f = function([orig_X], new_X)
j = 0
for path in paths:
if j % 100 == 0:
print j
try:
raw_path = path
path = base + '/' + path
img = image.load(path)
#image.show(img)
if len(img.shape) == 3 and img.shape[2] == 4:
img = img[:, :, 0:3]
img = img.reshape(*([1] + list(img.shape))).astype('float32')
channels = [f(img[:, :, :, i:i + 1]) for i in xrange(img.shape[3])]
if len(channels) != 3:
assert len(channels) == 1
channels = [channels[0]] * 3
img = np.concatenate(channels, axis=3)
img = img[0, :, :, :]
assert isfinite(img)
path = outdir + '/' + raw_path
def __init__(self,
lfw_path,
filelist_path,
embedding_file=None,
center=False,
scale=False,
start=None,
stop=None,
gcn=None,
shuffle=False,
rng=None,
seed=132987,
axes=('b', 0, 1, 'c'),
img_shape=(3, 250, 250)):
self.axes = axes
self.img_shape = img_shape
C, H, W = img_shape
self.img_size = np.prod(self.img_shape)
files = []
with open(filelist_path, 'r') as filelist_f:
files = [line.strip() for line in filelist_f]
# Load raw pixel integer values
dtype = 'uint8'
X = np.zeros((len(files), W, H, C), dtype=dtype)
img_ids = []
for i, line in enumerate(files):
if '\t' in line:
# New format: contains image IDs
img_path, img_id = line.strip().split()
img_ids.append(int(img_id))
else:
img_path = line.strip()
full_path = os.path.join(lfw_path, img_path)
im = image.load(full_path, rescale_image=False, dtype=dtype)
# Handle grayscale images which may not have RGB channels
if len(im.shape) == 2:
W, H = im.shape
# Repeat image 3 times across axis 2
im = im.reshape(W, H, 1).repeat(3, 2)
# Swap color channel to front
X[i] = im
# Cast to float32, center / scale if necessary
X = np.cast['float32'](X)
# Create dense design matrix from topological view
X = X.reshape(X.shape[0], -1)
# Prepare img_ids
if embedding_file is not None:
if len(img_ids) != len(files):
raise ValueError("You must provide a filelist with indexes "
"into the embedding array for each image.")
img_ids = np.array(img_ids, dtype='uint32')
if center and scale:
X[:] -= 127.5
X[:] /= 127.5
elif center:
X[:] -= 127.5
elif scale:
X[:] /= 255.
self.gcn = gcn
if gcn is not None:
gcn = float(gcn)
X = global_contrast_normalize(X, scale=gcn)
if shuffle:
rng = make_np_rng(rng, seed, which_method='permutation')
rand_idx = rng.permutation(len(X))
X = X[rand_idx]
img_ids = img_ids[rand_idx]
if start is not None:
assert start >= 0
assert stop > start
assert stop <= X.shape[0]
X = X[start:stop]
if len(img_ids) > 0:
img_ids = img_ids[start:stop]
# Load embeddings if provided
Y = None
if embedding_file is not None:
embeddings = np.load(embedding_file)['arr_0']
assert embeddings.shape[0] >= len(files)
Y = embeddings[img_ids].astype(theano.config.floatX)
# create view converting for retrieving topological view
self.view_converter = dense_design_matrix.DefaultViewConverter(
(W, H, C), axes)
# init super class
super(LFW, self).__init__(X=X, y=Y)
assert not contains_nan(self.X)
# Another hack: rename 'targets' to match model expectations
if embedding_file is not None:
space, (X_source, y_source) = self.data_specs
self.data_specs = (space, (X_source, 'condition'))
l2_path = '/data/lisatmp/goodfeli/esp/final_l2'
import numpy as np
from pylearn2.utils import image
imbase = '/data/lisatmp/goodfeli/esp/final_images'
ims = sorted(os.listdir(imbase))
for label, im in zip(labels, ims):
stem = label.split('.')[0]
assert stem in im
img = image.load(imbase + '/' + im)
image.show(img)
full_label_path = labels_dir + '/' + label
print 'True labels:'
fd = open(full_label_path,'r')
print fd.read()
fd.close()
full_l2_path = l2_path + '/' + label.split('.')[0] + '.npy'
l2 = np.load(full_l2_path)
y = f(l2)
f = function([X], y)
l2_path = '/data/lisatmp/goodfeli/esp/final_l2'
import numpy as np
from pylearn2.utils import image
imbase = '/data/lisatmp/goodfeli/esp/final_images'
ims = sorted(os.listdir(imbase))
for label, im in zip(labels, ims):
stem = label.split('.')[0]
assert stem in im
img = image.load(imbase + '/' + im)
image.show(img)
full_label_path = labels_dir + '/' + label
print 'True labels:'
fd = open(full_label_path, 'r')
print fd.read()
fd.close()
full_l2_path = l2_path + '/' + label.split('.')[0] + '.npy'
l2 = np.load(full_l2_path)
y = f(l2)
from pylearn2.utils import image
import numpy as np
for i in xrange(5000):
print i
number = str(i)
while len(number) != 4:
number = '0' + number
img = image.load('video/' + number + '.png')
out = np.zeros((480, 480, 3))
for j in range(32):
for k in xrange(32):
for l in xrange(3):
out[j * 15:(j + 1) * 15, k * 15:(k + 1) * 15, l] = img[j, k, l]
image.save('video_resized/' + number + '.png', out)
labels_dir = '/data/lisatmp/goodfeli/esp/word_labels'
from pylearn2.utils import image
while True:
candidates = os.listdir(images_path)
for path in candidates:
word = path.split('.')[0]
if word in labeled:
continue
label_path = labels_dir + '/' + word +'.txt'
if os.path.exists(label_path):
continue
image_path = images_path + '/' + path
img = image.load(image_path)
image.show(img)
f = open(label_path, 'w')
idx = 1
print 'Suggested label: ',word
x = ''
while x not in ['y', 'n']:
x = raw_input('ok? ')
if x == 'y':
idx += 1
f.write(word+'\n')
while True:
x = raw_input('label %d: ' %idx)
labels_dir = '/data/lisatmp/goodfeli/esp/word_labels'
from pylearn2.utils import image
while True:
candidates = os.listdir(images_path)
for path in candidates:
word = path.split('.')[0]
if word in labeled:
continue
label_path = labels_dir + '/' + word + '.txt'
if os.path.exists(label_path):
continue
image_path = images_path + '/' + path
img = image.load(image_path)
image.show(img)
f = open(label_path, 'w')
idx = 1
print 'Suggested label: ', word
x = ''
while x not in ['y', 'n']:
x = raw_input('ok? ')
if x == 'y':
idx += 1
f.write(word + '\n')
while True:
x = raw_input('label %d: ' % idx)
from pylearn2.utils import image
import numpy as np
for i in xrange(900):
print i
number = str(i)
while len(number) != 3:
number = '0' + number
img = image.load('video/' + number + '.png')
out = np.zeros((480, 480, 3))
for j in range(48):
for k in xrange(48):
for l in xrange(3):
out[j*10:(j+1)*10, k*10:(k+1)*10, l] = img[j,k,0]
image.save('video_resized/' + number + '.png', out)
def __init__(
self,
lfw_path,
filelist_path,
embedding_file=None,
center=False,
scale=False,
start=None,
stop=None,
gcn=None,
shuffle=False,
rng=None,
seed=132987,
axes=("b", 0, 1, "c"),
img_shape=(3, 250, 250),
):
self.axes = axes
self.img_shape = img_shape
C, H, W = img_shape
self.img_size = np.prod(self.img_shape)
files = []
with open(filelist_path, "r") as filelist_f:
files = [line.strip() for line in filelist_f]
# Load raw pixel integer values
dtype = "uint8"
X = np.zeros((len(files), W, H, C), dtype=dtype)
img_ids = []
for i, line in enumerate(files):
if "\t" in line:
# New format: contains image IDs
img_path, img_id = line.strip().split()
img_ids.append(int(img_id))
else:
img_path = line.strip()
full_path = os.path.join(lfw_path, img_path)
im = image.load(full_path, rescale_image=False, dtype=dtype)
# Handle grayscale images which may not have RGB channels
if len(im.shape) == 2:
W, H = im.shape
# Repeat image 3 times across axis 2
im = im.reshape(W, H, 1).repeat(3, 2)
# Swap color channel to front
X[i] = im
# Cast to float32, center / scale if necessary
X = np.cast["float32"](X)
# Create dense design matrix from topological view
X = X.reshape(X.shape[0], -1)
# Prepare img_ids
if embedding_file is not None:
if len(img_ids) != len(files):
raise ValueError("You must provide a filelist with indexes " "into the embedding array for each image.")
img_ids = np.array(img_ids, dtype="uint32")
if center and scale:
X[:] -= 127.5
X[:] /= 127.5
elif center:
X[:] -= 127.5
elif scale:
X[:] /= 255.0
self.gcn = gcn
if gcn is not None:
gcn = float(gcn)
X = global_contrast_normalize(X, scale=gcn)
if shuffle:
rng = make_np_rng(rng, seed, which_method="permutation")
rand_idx = rng.permutation(len(X))
X = X[rand_idx]
img_ids = img_ids[rand_idx]
if start is not None:
assert start >= 0
assert stop > start
assert stop <= X.shape[0]
X = X[start:stop]
if len(img_ids) > 0:
img_ids = img_ids[start:stop]
# Load embeddings if provided
Y = None
if embedding_file is not None:
embeddings = np.load(embedding_file)["arr_0"]
assert embeddings.shape[0] >= len(files)
Y = embeddings[img_ids].astype(theano.config.floatX)
# create view converting for retrieving topological view
self.view_converter = dense_design_matrix.DefaultViewConverter((W, H, C), axes)
# init super class
super(LFW, self).__init__(X=X, y=Y)
assert not contains_nan(self.X)
# Another hack: rename 'targets' to match model expectations
if embedding_file is not None:
space, (X_source, y_source) = self.data_specs
self.data_specs = (space, (X_source, "condition"))
