def preprocess_uwash_depth_dataset(attribs):
pipeline = preprocessing.Pipeline()
# rgbd : (num_examples, 72, 72, 4)
# labels: (num_examples, 1)
pipeline.items.append(
hdf5_data_preprocessors.ExtractRawUWashData(
attribs["raw_data_folder"],
data_labels=("rgbd_patches", "patch_labels")))
pipeline.items.append(
hdf5_data_preprocessors.PerChannelGlobalContrastNormalizePatches(
data_to_normalize_key='rgbd_patches',
normalized_data_key='normalized_rgbd_patches',
batch_size=100))
#this extracts a valid set and test set
pipeline.items.append(
hdf5_data_preprocessors.SplitData(
data_to_split_key=('rgbd_patches', 'patch_labels'),
sets=attribs["sets"],
patch_shape=attribs["patch_shape"],
num_patches_per_set=attribs["num_patches_per_set"]))
pipeline.items.append(hdf5_data_preprocessors.MakeC01B())
#now lets actually make a new dataset and run it through the pipeline
hd5f_dataset = h5py.File(attribs["output_filepath"])
pipeline.apply(hd5f_dataset)
def preprocess_nyu_depth_dataset(attribs):
pipeline = preprocessing.Pipeline()
# rgbd : (1449, 640, 480, 4)
# labels: (1449, 640, 480)
pipeline.items.append(
hdf5_data_preprocessors.ExtractRawNYUData(attribs["raw_filepath"],
data_labels=("rgbd",
"labels")))
#add the steps necessary to generate data for
# valid, test and training datasets
for i in range(len(attribs["sets"])):
which_set = attribs["sets"][i]
num_patches = attribs["num_patches_per_set"][i]
#labels for the hdf5 file
patch_label = which_set + "_patches"
patch_labels = (patch_label, which_set + "_patch_labels")
pipeline.items.append(
hdf5_data_preprocessors.ExtractPatches(
patch_shape=attribs["patch_shape"],
patch_labels=patch_labels,
patch_source_labels=("rgbd", "labels"),
num_patches=num_patches))
pipeline.items.append(hdf5_data_preprocessors.MakeC01B())
#now lets actually make a new dataset and run it through the pipeline
hd5f_dataset = h5py.File(attribs["output_filepath"])
pipeline.apply(hd5f_dataset)
def test1():
path_org = '/Tmp/gulcehrc/imagenet_256x256_filtered.h5'
path = '/Tmp/gulcehrc/imagenetTemp.h5'
train = Imagenet(which_set='train',
path=path,
path_org=path_org,
size_of_receptive_field=(8, 8),
center=True,
scale=True,
start=0,
stop=1000,
imageShape=(256, 256),
mode='a',
axes=('b', 0, 1, 'c'),
preprocessor=None)
pipeline = preprocessing.Pipeline()
pipeline.items.append(preprocessing.GlobalContrastNormalizationPyTables())
pipeline.items.append(
preprocessing.LeCunLCN((256, 256), channels=[0], kernel_size=7))
# apply preprocessing to train
train.apply_preprocessor(pipeline, can_fit=True)
train.view_shape()
#testing
batch_size = 10
num_batches = 1
mode = SequentialSubsetIterator
targets1 = []
targets2 = []
def main():
data_dir = string.preprocess('${PYLEARN2_DATA_PATH}/stl10')
print('Loading STL10-10 unlabeled and train datasets...')
downsampled_dir = data_dir + '/stl10_32x32'
data = serial.load(downsampled_dir + '/unlabeled.pkl')
supplement = serial.load(downsampled_dir + '/train.pkl')
print('Concatenating datasets...')
data.set_design_matrix(np.concatenate((data.X, supplement.X), axis=0))
del supplement
print("Preparing output directory...")
patch_dir = data_dir + '/stl10_patches_8x8'
serial.mkdir(patch_dir)
README = open(patch_dir + '/README', 'w')
README.write(textwrap.dedent("""
The .pkl files in this directory may be opened in python using
cPickle, pickle, or pylearn2.serial.load.
data.pkl contains a pylearn2 Dataset object defining an unlabeled
dataset of 2 million 6x6 approximately whitened, contrast-normalized
patches drawn uniformly at random from a downsampled (to 32x32)
version of the STL-10 train and unlabeled datasets.
preprocessor.pkl contains a pylearn2 Pipeline object that was used
to extract the patches and approximately whiten / contrast normalize
them. This object is necessary when extracting features for
supervised learning or test set classification, because the
extracted features must be computed using inputs that have been
whitened with the ZCA matrix learned and stored by this Pipeline.
They were created with the pylearn2 script make_stl10_patches.py.
All other files in this directory, including this README, were
created by the same script and are necessary for the other files
to function correctly.
"""))
README.close()
print("Preprocessing the data...")
pipeline = preprocessing.Pipeline()
pipeline.items.append(preprocessing.ExtractPatches(patch_shape=(8, 8),
num_patches=2*1000*1000))
pipeline.items.append(
preprocessing.GlobalContrastNormalization(sqrt_bias=10., use_std=True))
pipeline.items.append(preprocessing.ZCA())
data.apply_preprocessor(preprocessor=pipeline, can_fit=True)
data.use_design_loc(patch_dir + '/data.npy')
serial.save(patch_dir + '/data.pkl', data)
serial.save(patch_dir + '/preprocessor.pkl', pipeline)
def randomize_datasets(self, datasets):
center_shift = np.array(self._window_shape) / 2. - 0.5
tform_center = skimage.transform.SimilarityTransform(
translation=-center_shift)
tform_uncenter = skimage.transform.SimilarityTransform(
translation=center_shift)
if self._preprocess is not None:
pipeline = preprocessing.Pipeline()
#window the rotations to get rid of the uniform background
if self._central_window_shape is not None:
print 'adding window'
pipeline.items.append(CentralWindow(
self._central_window_shape))
for item in self._preprocess:
pipeline.items.append(item)
im_shape = (self._window_shape[0], self._window_shape[1], 1)
for d_idx, dataset in enumerate(datasets):
data = self._original[dataset]
#randomly window data
print data.shape
arr = np.empty((data.shape[0], self._window_shape[0],
self._window_shape[1], data.shape[3]),
dtype=np.float32)
for idx, example in enumerate(data):
scale_x = np.random.uniform(1 - self._scale_diff,
1 + self._scale_diff)
scale_y = np.random.uniform(1 - self._scale_diff,
1 + self._scale_diff)
translation_x = np.random.uniform(1 - self._translation,
1 + self._translation)
translation_y = np.random.uniform(1 - self._translation,
1 + self._translation)
shear = np.random.uniform(0. - self._shear, 0. + self._shear)
rotation = np.random.uniform(0, 360)
tform = AffineTransform(scale=(scale_x, scale_y),
rotation=np.deg2rad(rotation),
translation=(translation_x,
translation_y),
shear=shear)
tform = tform_center + tform + tform_uncenter
img = warp(example, tform, output_shape=self._window_shape)
arr[idx] = img
dataset.set_topological_view(arr, axes=dataset.view_converter.axes)
#assumes self._randomize in in order of [train, valid/test]
if self._preprocess is not None:
can_fit = True
if d_idx == 1:
can_fit = False
dataset.apply_preprocessor(preprocessor=pipeline,
can_fit=can_fit)
def main():
data_dir = string_utils.preprocess('${PYLEARN2_DATA_PATH}')
print('Loading CIFAR-100 train dataset...')
data = CIFAR100(which_set='train')
print("Preparing output directory...")
patch_dir = data_dir + '/cifar100/cifar100_patches'
serial.mkdir(patch_dir)
README = open(patch_dir + '/README', 'w')
README.write(
textwrap.dedent("""
The .pkl files in this directory may be opened in python using
cPickle, pickle, or pylearn2.serial.load.
data.pkl contains a pylearn2 Dataset object defining an unlabeled
dataset of 2 million 6x6 approximately whitened, contrast-normalized
patches drawn uniformly at random from the CIFAR-100 train set.
preprocessor.pkl contains a pylearn2 Pipeline object that was used
to extract the patches and approximately whiten / contrast normalize
them. This object is necessary when extracting features for
supervised learning or test set classification, because the
extracted features must be computed using inputs that have been
whitened with the ZCA matrix learned and stored by this Pipeline.
They were created with the pylearn2 script make_cifar100_patches.py.
All other files in this directory, including this README, were
created by the same script and are necessary for the other files
to function correctly.
"""))
README.close()
print("Preprocessing the data...")
pipeline = preprocessing.Pipeline()
pipeline.items.append(
preprocessing.ExtractPatches(patch_shape=(6, 6),
num_patches=2 * 1000 * 1000))
pipeline.items.append(
preprocessing.GlobalContrastNormalization(sqrt_bias=10., use_std=True))
pipeline.items.append(preprocessing.ZCA())
data.apply_preprocessor(preprocessor=pipeline, can_fit=True)
data.use_design_loc(patch_dir + '/data.npy')
serial.save(patch_dir + '/data.pkl', data)
serial.save(patch_dir + '/preprocessor.pkl', pipeline)
def get_pipeline(img_shape, patch_size, batch_size):
pipeline = preprocessing.Pipeline()
conf = get_config()
if conf['preprocessing']['remove_mean']:
pipeline.items.append(preprocessing.RemoveMean())
if conf['preprocessing']['gcn']:
pipeline.items.append(
preprocessing.GlobalContrastNormalization(batch_size=batch_size)
)
if conf['preprocessing']['lcn']:
# LCN requires uneven patch size
lcn_patch_size = patch_size + 1 - (patch_size % 2)
pipeline.items.append(
preprocessing.LeCunLCN(
img_shape, kernel_size=lcn_patch_size)
)
return pipeline
def get_processed_dataset():
train_path = 'pp_cifar10_train.pkl'
test_path = 'pp_cifar10_test.pkl'
if os.path.exists(train_path) and os.path.exists(
test_path) and not new_params:
print 'loading preprocessed data'
trainset = serial.load(train_path)
testset = serial.load(test_path)
else:
print 'loading raw data...'
pipeline = preprocessing.Pipeline()
pipeline.items.append(
preprocessing.ExtractPatchesWithPosition(
patch_shape=patch_shape, patches_per_image=patches_per_image))
pipeline.items.append(
preprocessing.GlobalContrastNormalization(sqrt_bias=10.,
use_std=True))
pipeline.items.append(
preprocessing.PCA(num_components=num_components,
keep_var_fraction=keep_var_fraction))
pipeline.items.append(
preprocessing.ExtractPatchPairs(
patches_per_image=patches_per_image,
num_images=train_size,
input_width=input_width))
trainset = cifar10.CIFAR10(which_set="train", start=start, stop=stop)
testset = cifar10.CIFAR10(which_set="test")
trainset.preprocessor = pipeline
trainset.apply_preprocessor(preprocessor=pipeline, can_fit=True)
# the pkl-ing is having issues, the dataset is maybe too big.
serial.save(train_path, trainset)
serial.save(test_path, testset)
# this path will be used for visualizing weights after training is done
trainset.yaml_src = '!pkl: "%s"' % train_path
testset.yaml_src = '!pkl: "%s"' % test_path
return trainset, testset
def main():
train = cifar10.CIFAR10(which_set="train", center=True)
pipeline = preprocessing.Pipeline()
pipeline.items.append(
preprocessing.GlobalContrastNormalization(subtract_mean=False,
sqrt_bias=0.0,
use_std=True))
pipeline.items.append(preprocessing.PCA(num_components=512))
test = cifar10.CIFAR10(which_set="test")
train.apply_preprocessor(preprocessor=pipeline, can_fit=True)
test.apply_preprocessor(preprocessor=pipeline, can_fit=False)
serial.save('cifar10_preprocessed_train.pkl', train)
serial.save('cifar10_preprocessed_test.pkl', test)
def get_dataset_cifar10():
"""
The orginal pipeline on cifar10 from pylearn2. Please refer to
pylearn2/scripts/train_example/make_dataset.py for details.
"""
train_path = 'cifar10_preprocessed_train.pkl'
test_path = 'cifar10_preprocessed_test.pkl'
if os.path.exists(train_path) and \
os.path.exists(test_path):
print 'loading preprocessed data'
trainset = serial.load(train_path)
testset = serial.load(test_path)
else:
print 'loading raw data...'
trainset = cifar10.CIFAR10(w5B5B5B5Bhich_set="train")
testset = cifar10.CIFAR10(which_set="test")
print 'preprocessing data...'
pipeline = preprocessing.Pipeline()
pipeline.items.append(
preprocessing.ExtractPatches(patch_shape=(8, 8), num_patches=150000))
pipeline.items.append(preprocessing.GlobalContrastNormalization())
pipeline.items.append(preprocessing.ZCA())
trainset.apply_preprocessor(preprocessor=pipeline, can_fit=True)
trainset.use_design_loc('train_design.npy')
testset.apply_preprocessor(preprocessor=pipeline, can_fit=True)
testset.use_design_loc('test_design.npy')
print 'saving preprocessed data...'
serial.save('cifar10_preprocessed_train.pkl', trainset)
serial.save('cifar10_preprocessed_test.pkl', testset)
trainset.yaml_src = '!pkl: "%s"' % train_path
testset.yaml_src = '!pkl: "%s"' % test_path
# this path will be used for visualizing weights after training is done
#global YAML
return trainset, testset
def process_data():
# pre-process unsupervised data
if not os.path.exists(DATA_DIR+'preprocess.pkl') \
or not os.path.exists(DATA_DIR+'unsup_prep_data.pkl') \
or not os.path.exists(DATA_DIR+'sup_prep_data.pkl'):
unsup_data = black_box_dataset.BlackBoxDataset('extra')
pipeline = preprocessing.Pipeline()
pipeline.items.append(
preprocessing.Standardize(global_mean=False, global_std=False))
#pipeline.items.append(preprocessing.ZCA(filter_bias=.1))
unsup_data.apply_preprocessor(preprocessor=pipeline, can_fit=True)
serial.save(DATA_DIR + 'preprocess.pkl', pipeline)
# why the hell do I get pickling errors if I use serial here? solve by pickling myself
#serial.save(DATA_DIR+'unsup_prep_data.pkl', unsup_data)
out = open(DATA_DIR + 'unsup_prep_data.pkl', 'w')
pickle.dump(unsup_data, out)
out.close()
# process supervised training data
sup_data = []
which_data = ['train'] * 3 + ['public_test']
starts = [0, 800, None, None]
stops = [800, 1000, None, None]
fits = [False, False, False, False]
for curstr, start, stop, fit in zip(which_data, starts, stops, fits):
sup_data.append(
black_box_dataset.BlackBoxDataset(which_set=curstr,
start=start,
stop=stop,
preprocessor=pipeline,
fit_preprocessor=fit))
serial.save(DATA_DIR + 'sup_prep_data.pkl', sup_data)
else:
pipeline = serial.load(DATA_DIR + 'preprocess.pkl')
#unsup_data = serial.load(DATA_DIR+'unsup_prep_data.pkl')
unsup_data = pickle.load(open(DATA_DIR + 'unsup_prep_data.pkl', 'r'))
sup_data = serial.load(DATA_DIR + 'sup_prep_data.pkl')
return unsup_data, sup_data
def generate_patches():
datasets = OrderedDict()
datasets['train'] = GenderWrite.gwdata.GWData(which_set='train',
start=1,
stop=201)
datasets['valid'] = GenderWrite.gwdata.GWData(which_set='train',
start=201,
stop=283)
datasets['test'] = GenderWrite.gwdata.GWData(which_set='test')
datasets['tottrain'] = GenderWrite.gwdata.GWData(which_set='train')
# preprocess patches
pipeline = preprocessing.Pipeline()
pipeline.items.append(preprocessing.GlobalContrastNormalization())
pipeline.items.append(preprocessing.ZCA())
for dstr, dset in datasets.iteritems():
print dstr
# only fit on train data
trainbool = dstr == 'train' or dstr == 'tottrain'
dset.apply_preprocessor(preprocessor=pipeline, can_fit=trainbool)
# save
dset.use_design_loc(DATA_DIR + dstr + '_design.npy')
serial.save(DATA_DIR + 'gw_preprocessed_' + dstr + '.pkl', dset)
def load_preprocessor(self, preprocess_array):
if preprocess_array is None:
self.preprocessor = None
return None
preprocess_list = []
for preprocess_id in preprocess_array:
row = self.db.executeSQL(
"""
SELECT preprocess_class
FROM hps3.preprocess
WHERE preprocess_id = %s
""", (preprocess_id, ), self.db.FETCH_ONE)
if not row or row is None:
raise HPSData("No preprocess for preprocess_id="\
+str(preprocess_id))
preprocess_class = row[0]
fn = getattr(self, 'get_preprocess_' + preprocess_class)
preprocess_list.append(fn(preprocess_id))
if len(preprocess_list) > 1:
preprocessor = pp.Pipeline(preprocess_list)
else:
preprocessor = preprocess_list[0]
self.preprocessor = preprocessor
def get_dataset(which_data, tot=False):
train_path = DATA_DIR + 'train' + which_data + '_preprocessed.pkl'
valid_path = DATA_DIR + 'valid' + which_data + '_preprocessed.pkl'
tottrain_path = DATA_DIR + 'tottrain' + which_data + '_preprocessed.pkl'
test_path = DATA_DIR + 'test' + which_data + '_preprocessed.pkl'
if os.path.exists(train_path) and os.path.exists(
valid_path) and os.path.exists(test_path):
print 'loading preprocessed data'
trainset = serial.load(train_path)
validset = serial.load(valid_path)
if tot:
tottrainset = serial.load(tottrain_path)
testset = serial.load(test_path)
else:
print 'loading raw data...'
trainset = Whales(which_set="train",
which_data=which_data,
start=0,
stop=56671)
validset = Whales(which_set="train",
which_data=which_data,
start=56671,
stop=66671)
tottrainset = Whales(which_set="train", which_data=which_data)
testset = Whales(which_set="test", which_data=which_data)
print 'preprocessing data...'
pipeline = preprocessing.Pipeline()
if which_data == 'melspectrum':
pipeline.items.append(
preprocessing.Standardize(global_mean=True, global_std=True))
# ZCA = zero-phase component analysis
# very similar to PCA, but preserves the look of the original image better
pipeline.items.append(preprocessing.ZCA())
else:
# global_mean/std=False voor per-feature standardization
pipeline.items.append(
preprocessing.Standardize(global_mean=False, global_std=False))
trainset.apply_preprocessor(preprocessor=pipeline, can_fit=True)
# this uses numpy format for storage instead of pickle, for memory reasons
trainset.use_design_loc(DATA_DIR + 'train_' + which_data +
'_design.npy')
# note the can_fit=False: no sharing between train and test data
validset.apply_preprocessor(preprocessor=pipeline, can_fit=False)
validset.use_design_loc(DATA_DIR + 'valid_' + which_data +
'_design.npy')
tottrainset.apply_preprocessor(preprocessor=pipeline, can_fit=True)
tottrainset.use_design_loc(DATA_DIR + 'tottrain_' + which_data +
'_design.npy')
# note the can_fit=False: no sharing between train and test data
testset.apply_preprocessor(preprocessor=pipeline, can_fit=False)
testset.use_design_loc(DATA_DIR + 'test_' + which_data + '_design.npy')
# this path can be used for visualizing weights after training is done
trainset.yaml_src = '!pkl: "%s"' % train_path
validset.yaml_src = '!pkl: "%s"' % valid_path
tottrainset.yaml_src = '!pkl: "%s"' % tottrain_path
testset.yaml_src = '!pkl: "%s"' % test_path
print 'saving preprocessed data...'
serial.save(DATA_DIR + 'train' + which_data + '_preprocessed.pkl',
trainset)
serial.save(DATA_DIR + 'valid' + which_data + '_preprocessed.pkl',
validset)
serial.save(DATA_DIR + 'tottrain' + which_data + '_preprocessed.pkl',
tottrainset)
serial.save(DATA_DIR + 'test' + which_data + '_preprocessed.pkl',
testset)
if tot:
return tottrainset, validset, testset
else:
return trainset, validset, testset
from pylearn2.utils import serial
from pylearn2.datasets import preprocessing
from pylearn2.datasets.tfd import TFD
train = TFD(which_set='train')
preprocessor = preprocessing.Pipeline()
preprocessor.items.append(preprocessing.GlobalContrastNormalization())
preprocessor.items.append(preprocessing.ZCA())
preprocessor.apply(train, can_fit=True)
serial.save('tfd_gcn_whitener.pkl', preprocessor)
def generate(opc):
"""
Summary (Generates a dataset with the chosen transformation).
Parameters
----------
opc: string
Only two options, shifts or rotations.
"""
dim = 19 # outer square
# A bigger image is used to avoid empty pixels in the
# borders.
reg = 13 # inner square
total = 20000 # Number of training examples
im1 = numpy.zeros((total, reg, reg, 1), dtype='float32')
im2 = numpy.zeros((total, reg, reg, 1), dtype='float32')
Y = numpy.zeros((total, 1), dtype='uint8')
rng = make_np_rng(9001, [1, 2, 3], which_method="uniform")
transformation = opc
if transformation == 'shifts':
# Shifts
# only shifts between [-3, +3] pixels
shifts = list(itertools.product(range(-3, 4), range(-3, 4)))
t = 0
while t < total:
x = rng.uniform(0, 1, (dim, dim))
x = numpy.ceil(x * 255)
im_x = x[3:16, 3:16][:, :, None]
ind = rng.randint(0, len(shifts))
Y[t] = ind
txy = shifts[ind]
tx, ty = txy
im_y = x[(3 + tx):(16 + tx), (3 + ty):(16 + ty)][:, :, None]
im1[t, :] = im_x
im2[t, :] = im_y
t += 1
else:
assert transformation == 'rotations'
# Rotations
import Image
# import cv2
angs = numpy.linspace(0, 359, 90)
t = 0
while t < total:
x = rng.uniform(0, 1, (dim, dim))
x = numpy.ceil(x * 255)
im_x = x[3:16, 3:16][:, :, None]
ind = rng.randint(0, len(angs))
Y[t] = ind
ang = angs[ind]
y = numpy.asarray(Image.fromarray(x).rotate(ang))
# scale = 1
# M1 = cv2.getRotationMatrix2D((dim/2, dim/2), ang, scale)
# y = cv2.warpAffine(x, M1, (dim, dim))
im_y = y[3:16, 3:16][:, :, None]
im1[t, :] = im_x
im2[t, :] = im_y
t += 1
view_converter = dense_design_matrix.DefaultViewConverter((reg, reg, 1))
design_X = view_converter.topo_view_to_design_mat(im1)
design_Y = view_converter.topo_view_to_design_mat(im2)
# Normalize data:
pipeline = preprocessing.Pipeline()
gcn = preprocessing.GlobalContrastNormalization(sqrt_bias=10.,
use_std=True)
pipeline.items.append(gcn)
XY = numpy.concatenate((design_X, design_Y), 0)
XY_ImP = dense_design_matrix.DenseDesignMatrix(X=XY)
XY_ImP.apply_preprocessor(preprocessor=pipeline, can_fit=True)
X1 = XY_ImP.X[0:design_X.shape[0], :]
X2 = XY_ImP.X[design_X.shape[0]:, :]
# As a Conv2DSpace
topo_X1 = view_converter.design_mat_to_topo_view(X1)
topo_X2 = view_converter.design_mat_to_topo_view(X2)
axes = ('b', 0, 1, 'c')
data_specs = (CompositeSpace([
Conv2DSpace((reg, reg), num_channels=1, axes=axes),
Conv2DSpace((reg, reg), num_channels=1, axes=axes),
VectorSpace(1)
]), ('featuresX', 'featuresY', 'targets'))
train = VectorSpacesDataset((topo_X1, topo_X2, Y), data_specs=data_specs)
# As a VectorSpace
# data_specs = (CompositeSpace(
# [VectorSpace(reg * reg),
# VectorSpace(reg * reg),
# VectorSpace(1)]),
# ('featuresX', 'featuresY', 'targets'))
# train = VectorSpacesDataset(data=(X1, X2, Y), data_specs=data_specs)
import os
save_path = os.path.dirname(os.path.realpath(__file__))
serial.save(os.path.join(save_path, 'train_preprocessed.pkl'), train)
def get_dataset(tot=False, preprocessor='normal'):
if not os.path.exists(DATA_DIR+'train.npy') or \
not os.path.exists(DATA_DIR+'test.npy') or \
not os.path.exists(DATA_DIR+'targets.npy'):
initial_read()
train_path = DATA_DIR+'train_'+preprocessor+'_preprocessed.pkl'
valid_path = DATA_DIR+'valid_'+preprocessor+'_preprocessed.pkl'
tottrain_path = DATA_DIR+'tottrain_'+preprocessor+'_preprocessed.pkl'
test_path = DATA_DIR+'test_'+preprocessor+'_preprocessed.pkl'
if os.path.exists(train_path) and os.path.exists(valid_path) and os.path.exists(test_path):
print 'loading preprocessed data'
trainset = serial.load(train_path)
validset = serial.load(valid_path)
if tot:
tottrainset = serial.load(tottrain_path)
testset = serial.load(test_path)
else:
print 'loading raw data...'
trainset = Digits(which_set='train', start=0, stop=34000)
validset = Digits(which_set='train', start=34000, stop=42000)
tottrainset = Digits(which_set='train')
testset = Digits(which_set='test')
print 'preprocessing data...'
pipeline = preprocessing.Pipeline()
pipeline.items.append(preprocessing.GlobalContrastNormalization(sqrt_bias=10., use_std=True))
if preprocessor != 'nozca':
# ZCA = zero-phase component analysis
# very similar to PCA, but preserves the look of the original image better
pipeline.items.append(preprocessing.ZCA())
# note the can_fit=False's: no sharing between train and valid data
trainset.apply_preprocessor(preprocessor=pipeline, can_fit=True)
validset.apply_preprocessor(preprocessor=pipeline, can_fit=False)
tottrainset.apply_preprocessor(preprocessor=pipeline, can_fit=True)
testset.apply_preprocessor(preprocessor=pipeline, can_fit=False)
if preprocessor not in ('normal','nozca'):
for data in (trainset, validset, tottrainset, testset):
for ii in range(data.X.shape[0]):
# normalize to [0,1]
dmax = np.max(data.X[ii,:])
dmin = np.min(data.X[ii,:])
dnorm = (data.X[ii,:] - dmin) / (dmax - dmin)
# and convert to PIL image
img = Image.fromarray(dnorm.reshape(28, 28) * 255.).convert('L')
# apply preprocessor
if preprocessor == 'rotate':
rot = rng.randint(-40, 41)
img = img.rotate(rot, Image.BILINEAR)
elif preprocessor == 'emboss':
img = emboss(img)
elif preprocessor == 'hshear':
# coef = 0 means unsheared
coef = -1 + np.random.rand()*2
# note: image is moved with (coef/2)*28 to center it after shearing
img = img.transform((28,28), Image.AFFINE, (1,coef,-(coef/2)*28,0,1,0), Image.BILINEAR)
elif preprocessor == 'vshear':
coef = -1 + np.random.rand()*2
img = img.transform((28,28), Image.AFFINE, (1,0,0,coef,1,-(coef/2)*28), Image.BILINEAR)
elif preprocessor == 'patch':
# negative values are not possible in PIL, so do a zoom only transform then
x1 = np.random.randint(0, 5)
y1 = np.random.randint(0, 5)
x2 = np.random.randint(0, 5)
y2 = np.random.randint(0, 5)
img = img.transform((28,28), Image.EXTENT, (x1, y1, 28-x2, 28-y2), Image.BILINEAR)
# convert back to numpy array
data.X[ii,:] = np.array(img.getdata()) / 255.
if preprocessor == 'noisy':
# add noise
data.X[ii,:] += np.random.randn(28*28) * 0.1
# bound between [0,1]
data.X[ii,:] = np.minimum(np.ones(28*28), np.maximum(np.zeros(28*28), data.X[ii,:]))
# this uses numpy format for storage instead of pickle, for memory reasons
trainset.use_design_loc(DATA_DIR+'train_'+preprocessor+'_design.npy')
validset.use_design_loc(DATA_DIR+'valid_'+preprocessor+'_design.npy')
tottrainset.use_design_loc(DATA_DIR+'tottrain_'+preprocessor+'_design.npy')
testset.use_design_loc(DATA_DIR+'test_'+preprocessor+'_design.npy')
# this path can be used for visualizing weights after training is done
trainset.yaml_src = '!pkl: "%s"' % train_path
validset.yaml_src = '!pkl: "%s"' % valid_path
tottrainset.yaml_src = '!pkl: "%s"' % tottrain_path
testset.yaml_src = '!pkl: "%s"' % test_path
print 'saving preprocessed data...'
serial.save(train_path, trainset)
serial.save(valid_path, validset)
serial.save(tottrain_path, tottrainset)
serial.save(test_path, testset)
if tot:
return tottrainset, validset, testset
else:
return trainset, validset, testset
def test_works():
load = True
if load == False:
ddmTrain = FacialKeypoint(which_set='train', start=0, stop=6000)
ddmValid = FacialKeypoint(which_set='train', start=6000, stop=7049)
# valid can_fit = false
pipeline = preprocessing.Pipeline()
stndrdz = preprocessing.Standardize()
stndrdz.apply(ddmTrain, can_fit=True)
#doubt, how about can_fit = False?
stndrdz.apply(ddmValid, can_fit=False)
GCN = preprocessing.GlobalContrastNormalization()
GCN.apply(ddmTrain, can_fit=True)
GCN.apply(ddmValid, can_fit=False)
pcklFile = open('kpd.pkl', 'wb')
obj = (ddmTrain, ddmValid)
pickle.dump(obj, pcklFile)
pcklFile.close()
return
else:
pcklFile = open('kpd.pkl', 'rb')
(ddmTrain, ddmValid) = pickle.load(pcklFile)
pcklFile.close()
#creating layers
#2 convolutional rectified layers, border mode valid
layer1 = ConvRectifiedLinear(layer_name='convRect1',
output_channels=64,
irange=.05,
kernel_shape=[5, 5],
pool_shape=[3, 3],
pool_stride=[2, 2],
max_kernel_norm=1.9365)
layer2 = ConvRectifiedLinear(layer_name='convRect2',
output_channels=64,
irange=.05,
kernel_shape=[5, 5],
pool_shape=[3, 3],
pool_stride=[2, 2],
max_kernel_norm=1.9365)
# Rectified linear units
layer3 = RectifiedLinear(dim=3000, sparse_init=15, layer_name='RectLin3')
#multisoftmax
n_groups = 30
n_classes = 98
irange = 0
layer_name = 'multisoftmax'
layerMS = MultiSoftmax(n_groups=n_groups,
irange=0.05,
n_classes=n_classes,
layer_name=layer_name)
#setting up MLP
MLPerc = MLP(batch_size=8,
input_space=Conv2DSpace(shape=[96, 96], num_channels=1),
layers=[layer1, layer2, layer3, layerMS])
#mlp_cost
missing_target_value = -1
mlp_cost = MLPCost(cost_type='default',
missing_target_value=missing_target_value)
#algorithm
# learning rate, momentum, batch size, monitoring dataset, cost, termination criteria
term_crit = MonitorBased(prop_decrease=0.00001,
N=30,
channel_name='validation_objective')
kpSGD = KeypointSGD(learning_rate=0.001,
init_momentum=0.5,
monitoring_dataset={
'validation': ddmValid,
'training': ddmTrain
},
batch_size=8,
batches_per_iter=750,
termination_criterion=term_crit,
train_iteration_mode='random_uniform',
cost=mlp_cost)
#train extension
train_ext = ExponentialDecayOverEpoch(decay_factor=0.998,
min_lr_scale=0.01)
#train object
train = Train(dataset=ddmTrain,
save_path='kpd_model2.pkl',
save_freq=1,
model=MLPerc,
algorithm=kpSGD,
extensions=[
train_ext,
MonitorBasedSaveBest(channel_name='validation_objective',
save_path='kpd_best.pkl'),
MomentumAdjustor(start=1, saturate=20, final_momentum=.9)
])
train.main_loop()
train.save()
to extract the patches and approximately whiten / contrast normalize
them. This object is necessary when extracting features for
supervised learning or test set classification, because the
extracted features must be computed using inputs that have been
whitened with the ZCA matrix learned and stored by this Pipeline.
They were created with the pylearn2 script make_cifar100_patches.py.
All other files in this directory, including this README, were
created by the same script and are necessary for the other files
to function correctly.
""")
README.close()
print("Preprocessing the data...")
pipeline = preprocessing.Pipeline()
pipeline.items.append(
preprocessing.ExtractPatches(patch_shape=(8, 8),
num_patches=2 * 1000 * 1000))
pipeline.items.append(
preprocessing.GlobalContrastNormalization(sqrt_bias=10., use_std=True))
pipeline.items.append(preprocessing.ZCA())
data.apply_preprocessor(preprocessor=pipeline, can_fit=True)
data.use_design_loc(patch_dir + '/data.npy')
serial.save(patch_dir + '/data.pkl', data)
serial.save(patch_dir + '/preprocessor.pkl', pipeline)
def get_data(tot=True, flatgrey=False):
tottrain_path = DATA_DIR+'gz_preprocessed_tottrain' + str(SUBMODEL) + '_64x.pkl'
test_path = DATA_DIR+'gz_preprocessed_test' + str(SUBMODEL) + '_64x.pkl'
if os.path.exists(test_path):
print 'loading preprocessed data'
datasets = OrderedDict()
# datasets['train'] = serial.load(train_path)
# datasets['valid'] = serial.load(valid_path)
if tot:
datasets['tottrain'] = serial.load(tottrain_path)
datasets['test'] = serial.load(test_path)
if tot:
return datasets['tottrain'], datasets['test']
else:
return datasets['train'], datasets['test']
else:
print 'preprocessing data...'
pipeline = preprocessing.Pipeline()
pipeline.items.append(preprocessing.GlobalContrastNormalization(use_std=True))
pipeline.items.append(preprocessing.ZCA())
# print 'traindata'
# data = GalaxyZoo.gzdeepdata.GZData(which_set='training', start=0, stop=39999)
# data.apply_preprocessor(preprocessor=pipeline, can_fit=True)
# # this path can be used for visualizing weights after training is done
# data.yaml_src = '!pkl: "%s"' % data
# # save
# data.use_design_loc(DATA_DIR+'train_design' + str(SUBMODEL) + '.npy')
# serial.save(DATA_DIR+'gz_preprocessed_train'+str(SUBMODEL) + '.pkl', data)
# print 'validdata'
# data = GalaxyZoo.gzdeepdata.GZData(which_set='training', start=40000, stop=61577)
# data.apply_preprocessor(preprocessor=pipeline, can_fit=False)
# # this path can be used for visualizing weights after training is done
# data.yaml_src = '!pkl: "%s"' % data
# # save
# data.use_design_loc(DATA_DIR+'valid_design' + str(SUBMODEL) + '.npy')
# serial.save(DATA_DIR+'gz_preprocessed_valid'+str(SUBMODEL) + '.pkl', data)
print 'tottraindata'
data = GalaxyZoo.gzdeepdata.GZData(which_set='training', flatgrey=flatgrey)
data.apply_preprocessor(preprocessor=pipeline, can_fit=True)
# this path can be used for visualizing weights after training is done
data.yaml_src = '!pkl: "%s"' % data
# save
data.use_design_loc(DATA_DIR + 'tottrain_design' + str(SUBMODEL) + '_64x.npy')
serial.save(DATA_DIR + 'gz_preprocessed_tottrain' + str(SUBMODEL) + '_64x.pkl', data)
print 'testdata'
data = GalaxyZoo.gzdeepdata.GZData(which_set='test', flatgrey=flatgrey)
data.apply_preprocessor(preprocessor=pipeline, can_fit=False)
# this path can be used for visualizing weights after training is done
data.yaml_src = '!pkl: "%s"' % data
# save
data.use_design_loc(DATA_DIR + 'test_design' + str(SUBMODEL) + '_64x.npy')
serial.save(DATA_DIR + 'gz_preprocessed_test' + str(SUBMODEL) + '_64x.pkl', data)
print 'Finished, now re-run for running model on GPU'
return None, None
