def load_images(ipl):
"""
These images are loaded:
paths_true (paths within single label objects)
paths_false (paths of merged objects which cross the merging site)
featureims_true
featureims_false
:param ipl:
:return:
"""
paths_true = IPL()
paths_false = IPL()
featureims_true = IPL()
featureims_false = IPL()
params = ipl.get_params()
ipl.logging('Loading true paths ...')
# Paths within labels (true paths)
paths_true.data_from_file(filepath=params['intermedfolder'] +
params['pathstruefile'],
skeys='path',
recursive_search=True,
nodata=True)
ipl.logging('Loading false paths ...')
# Paths of merges (false paths)
paths_false.data_from_file(filepath=params['intermedfolder'] +
params['pathsfalsefile'],
skeys='path',
recursive_search=True,
nodata=True)
ipl.logging('Loading features for true paths ...')
# Load features for true paths
featureims_true.data_from_file(filepath=params['intermedfolder'] +
params['featureimsfile'],
nodata=True)
featureims_true.delete_items(params['largeobjmnames'][0])
ipl.logging('Loading features for false paths ...')
# Load features for false paths
featureims_false.data_from_file(filepath=params['intermedfolder'] +
params['featureimsfile'],
nodata=True)
featureims_false.delete_items(params['largeobjname'])
return (paths_true, paths_false, featureims_true, featureims_false)
def split_in_xyz(ipl):
ipl.logging('Datastructure\n---\n{}', ipl.datastructure2string())
reskeys = ('0', '1')
ipl_split = IPL()
ipl_split['z'] = ipl.anytask(lib.split,
2,
axis=0,
result_keys=reskeys,
return_only=True,
rtrntype=IPL)
ipl_split['y'] = ipl.anytask(lib.split,
2,
axis=1,
result_keys=reskeys,
return_only=True,
rtrntype=IPL)
ipl_split['x'] = ipl.anytask(lib.split,
2,
axis=2,
result_keys=reskeys,
return_only=True,
rtrntype=IPL)
ipl_split = ipl_split.switch_levels(1, 2)
ipl.logging('Split sample datastructure\n---\n{}',
ipl_split.datastructure2string())
return ipl_split
def find_border_contacts_image_iteration(ipl):
params = ipl.get_params()
thisparams = params['find_border_contacts']
if thisparams['return_bordercontact_images']:
bordercontacts = IPL()
for d, k, v, kl in ipl.data_iterator(yield_short_kl=True):
if k == params['largeobjname']:
if thisparams['return_bordercontact_images']:
ipl[kl].setlogger(ipl.getlogger())
[ipl[kl], bordercontacts[kl]] = find_border_contacts(
ipl[kl],
(params['largeobjname'], params['largeobjmnames'][0]),
thisparams)
else:
ipl[kl].setlogger(ipl.getlogger())
ipl[kl] = find_border_contacts(
ipl[kl],
(params['largeobjname'], params['largeobjmnames'][0]),
thisparams)
if thisparams['return_bordercontact_images']:
return bordercontacts
else:
return None
def run_paths_of_merges(yamlfile, logging=True):
ipl = IPL(yaml=yamlfile)
ipl.set_indent(1)
params = rdict(data=ipl.get_params())
if logging:
ipl.startlogger(filename=params['resultfolder'] +
'paths_of_merges.log',
type='w',
name='PathsOfMerges')
else:
ipl.startlogger()
try:
# # Copy the script file and the parameters to the scriptsfolder
# copy(inspect.stack()[0][1], params['scriptsfolder'])
# copy(yamlfile, params['scriptsfolder'] + 'paths_of_merges.parameters.yml')
# ipl.logging('\nInitial datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
paths_of_merges(ipl, params['debug'])
# ipl.logging('\nFinal datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
# ipl.write(filepath=params['intermedfolder'] + params['largeobjfile'])
ipl.logging('')
ipl.stoplogger()
except:
ipl.errout('Unexpected error')
def paths_within_labels(hfp, key, locmaxkeys, disttransfkey, ignore=[]):
params = hfp.get_params()
thisparams = params['paths_within_labels']
if type(locmaxkeys) is str:
locmaxkeys = (locmaxkeys, )
# This results in the format:
# more_keys = (locmaxkeys[0], ..., locmaxkeys[n], disttransfkey)
more_keys = locmaxkeys + (disttransfkey, )
paths = IPL()
for k in locmaxkeys:
paths['pathsim', k] = np.zeros(hfp[key].shape)
for lbl, lblim, more_ims, bounds in hfp.label_image_bounds_iterator(
key=key, background=0, more_keys=more_keys, maskvalue=0, value=0):
if lbl in ignore:
continue
# The format of more_ims is:
# more_ims = {locmaxkeys[0]: locmax_1,
# ...
# locmaxkeys[n]: locmax_n,
# disttransfkey: disttransf}
hfp.logging('======================\nWorking on label = {}', lbl)
# hfp.logging('more_ims structure:\n---\n{}', more_ims.datastructure2string())
hfp.logging('bounds = {}', bounds)
for i in xrange(0, len(locmaxkeys)):
hfp.logging('locmaxkey = {}', locmaxkeys[i])
if np.amax(more_ims[locmaxkeys[i]]) > 0:
ps, pathsim = find_shortest_path(hfp,
thisparams['penaltypower'],
bounds,
more_ims[disttransfkey],
more_ims[locmaxkeys[i]])
# Only store the path if the path-calculation successfully determined a path
# Otherwise an empty list would be stored
if ps:
hfp.logging('Number of paths found: {}', len(ps))
paths[key, locmaxkeys[i], 'path', lbl] = ps
paths[key, locmaxkeys[i], 'pathsim'] = pathsim
paths['pathsim', locmaxkeys[i]][bounds][
pathsim > 0] = pathsim[pathsim > 0]
for k in locmaxkeys:
paths['overlay', k] = np.array([
paths['pathsim', k],
hfp[key].astype(np.float32) / np.amax(hfp[key]),
vigra.filters.multiBinaryDilation(hfp[k].astype(np.uint8), 5)
])
return paths
def make_feature_arrays(ipl):
params = ipl.get_params()
thisparams = rdict(params['random_forest'])
targetfile = params['resultfolder'] + params['resultsfile']
# Load the necessary images
load_images(ipl)
ipl.logging('\nInitial datastructure: \n\n{}',
ipl.datastructure2string(maxdepth=3))
result = IPL()
evaluation = rdict()
for d, k, v, kl in ipl.data_iterator(yield_short_kl=True):
if k == '0':
ipl.logging(
'===============================\nWorking on group: {}', kl)
# TODO: Implement copy full logger
ipl[kl].set_logger(ipl.get_logger())
# Load the image data into memory
ipl[kl].populate()
# def shp(x):
# return x.shape
# print ipl[kl]['0', 'true']
# print ipl[kl].dss(function=shp)
ipl[kl]['0', 'true'] = libip.rf_make_feature_array(ipl[kl]['0',
'true'])
ipl.logging(
"Computed feature array for ['0', 'true'] with shape {}",
ipl[kl]['0', 'true'].shape)
ipl[kl]['0',
'false'] = libip.rf_make_feature_array(ipl[kl]['0',
'false'])
ipl.logging(
"Computed feature array for ['0', 'false'] with shape {}",
ipl[kl]['0', 'false'].shape)
ipl[kl]['1', 'true'] = libip.rf_make_feature_array(ipl[kl]['1',
'true'])
ipl.logging(
"Computed feature array for ['1', 'true'] with shape {}",
ipl[kl]['1', 'true'].shape)
ipl[kl]['1',
'false'] = libip.rf_make_feature_array(ipl[kl]['1',
'false'])
ipl.logging(
"Computed feature array for ['1', 'false'] with shape {}",
ipl[kl]['1', 'false'].shape)
ipl.write(filepath=params['intermedfolder'] + 'feature_arrays.h5',
keys=[kl])
def get_features(paths, featureimage, featurelist, max_paths_per_label, ipl=None):
newfeats = IPL()
# TODO: Selection of a limited amount of paths should be random
keylist = range(0, max_paths_per_label)
keylist = [str(x) for x in keylist]
# Iterate over all paths, yielding a list of one path per label object until no paths are left
for i, keys, vals in paths.simultaneous_iterator(
max_count_per_item=max_paths_per_label,
keylist=keylist):
if ipl is not None:
ipl.logging('Working in iteration = {}', i)
# Create a working image
image = np.zeros(featureimage.shape, dtype=np.uint32)
# And fill it with one path per label object
c = 1
for curk, curv in (dict(zip(keys, vals))).iteritems():
curv = lib.swapaxes(curv, 0, 1)
lib.positions2value(image, curv, c)
c += 1
# Extract the region features of the working image
newnewfeats = IPL(
data=vigra.analysis.extractRegionFeatures(
featureimage,
image, ignoreLabel=0,
features=featurelist
)
)
for k, v in newnewfeats.iteritems():
newnewfeats[k] = newnewfeats[k][1:]
if k in newfeats:
try:
newfeats[k] = np.concatenate((newfeats[k], newnewfeats[k]))
except ValueError:
pass
else:
newfeats[k] = newnewfeats[k]
return newfeats
def merge_adjacent_objects_image_iteration(ipl):
params = ipl.get_params()
thisparams = params['merge_adjacent_objects']
merged = IPL()
for d, k, v, kl in ipl.data_iterator(yield_short_kl=True):
ipl.logging('Working on image: {}', kl + [k])
if k == params['largeobjname']:
data = IPL(data={k: v})
data.setlogger(ipl.getlogger())
merged[kl] = merge_adjacent_objects(data, k, thisparams)
return merged
def run_random_forest(yamlfile,
logging=True,
make_only_feature_array=False,
debug=False,
write=True):
ipl = IPL(yaml=yamlfile)
ipl.set_indent(1)
params = rdict(data=ipl.get_params())
if logging:
ipl.startlogger(filename=params['resultfolder'] + 'random_forest.log',
type='w',
name='RandomForest')
else:
ipl.startlogger()
try:
# # Copy the script file and the parameters to the scriptsfolder
# copy(inspect.stack()[0][1], params['scriptsfolder'])
# copy(yamlfile, params['scriptsfolder'] + 'random_forest.parameters.yml')
# ipl.logging('\nInitial datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
if make_only_feature_array:
make_feature_arrays(ipl)
else:
result = IPL()
result['result'], result['evaluation'] = random_forest(ipl,
debug=debug)
# ipl.logging('\nFinal datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
if write:
result.write(filepath=params['resultfolder'] +
params['resultsfile'])
ipl.logging('')
ipl.stoplogger()
except:
ipl.errout('Unexpected error')
def get_features(paths,
featureimage,
featurelist,
max_paths_per_label,
hfp=None):
newfeats = IPL()
keylist = range(0, max_paths_per_label)
keylist = [str(x) for x in keylist]
for i, keys, vals in paths.simultaneous_iterator(
max_count_per_item=max_paths_per_label, keylist=keylist):
if hfp is not None:
hfp.logging('Working in iteration = {}', i)
image = np.zeros(featureimage.shape, dtype=np.uint32)
c = 1
for curk, curv in (dict(zip(keys, vals))).iteritems():
curv = lib.swapaxes(curv, 0, 1)
lib.positions2value(image, curv, c)
c += 1
newnewfeats = IPL(data=vigra.analysis.extractRegionFeatures(
featureimage, image, ignoreLabel=0, features=featurelist))
for k, v in newnewfeats.iteritems():
newnewfeats[k] = newnewfeats[k][1:]
if k in newfeats:
try:
newfeats[k] = np.concatenate((newfeats[k], newnewfeats[k]))
except ValueError:
pass
else:
newfeats[k] = newnewfeats[k]
return newfeats
def load_images(filepath, skeys=None, recursive_search=False, logger=None):
if logger is not None:
logger.logging('Loading data from \n{}', filepath)
else:
print 'Loading data from \n{}'.format(filepath)
data = IPL()
data.data_from_file(filepath=filepath,
skeys=skeys,
recursive_search=recursive_search,
nodata=True)
return data
def random_forest_iteration(features):
result = IPL()
for k, v in features.iteritems():
# Make the feature arrays
v['0']['true'] = make_feature_array(v['0']['true'])
v['0']['false'] = make_feature_array(v['0']['false'])
v['1']['true'] = make_feature_array(v['1']['true'])
v['1']['false'] = make_feature_array(v['1']['false'])
result[k, '0'] = random_forest(v['0'], v['1'])
result[k, '1'] = random_forest(v['1'], v['0'])
return result
def make_features_paths(paths, disttransf_images, feature_images, features_out):
paths.astype(np.uint32)
feature_images.astype(np.float32)
# features_out = Hdf5ImageProcessing()
features_out['disttransf'] = IPL(data=paths)
features_out['disttransf'].anytask(vigra.analysis.extractRegionFeatures, ignoreLabel=0,
reverse_order=True, reciprocal=False,
keys=('paths_true', 'paths_false'),
indict=disttransf_images)
features_out['raw'] = paths
features_out['raw'].anytask(vigra.analysis.extractRegionFeatures, ignoreLabel=0,
reverse_order=True, reciprocal=False,
keys=('paths_true', 'paths_false'),
indict=feature_images)
def compute_features(image, general_params, subfeature_params):
ff = FeatureFunctions()
result = IPL()
for k, v in subfeature_params.iteritems():
if v:
result[k] = getattr(ff, v.pop('func'))(image, general_params,
v.pop('params'))
if len(v) > 0:
result[k] = compute_features(result[k], general_params, v)
else:
result[k] = image
return result
def run_remove_small_objects(yamlfile):
ipl = IPL(yaml=yamlfile,
yamlspec={
'path': 'datafolder',
'filename': 'labelsfile',
'skeys': 'labelsname'
},
recursive_search=True,
nodata=True)
# Set indentation of the logging
ipl.set_indent(1)
params = ipl.get_params()
ipl.startlogger(filename=params['resultfolder'] +
'remove_small_objects.log',
type='w',
name='RemoveSmallObjects')
try:
# # Copy the script file and the parameters to the scriptsfolder
# copy(inspect.stack()[0][1], params['scriptsfolder'])
# copy(yamlfile, params['scriptsfolder'] + 'remove_small_objects.parameters.yml')
ipl.logging('\nipl datastructure: \n\n{}',
ipl.datastructure2string(maxdepth=3))
remove_small_objects(ipl)
ipl.logging('\nFinal datastructure: \n\n{}',
ipl.datastructure2string(maxdepth=3))
# ipl.write(filepath=params['intermedfolder'] + params['largeobjfile'])
ipl.logging('')
ipl.stoplogger()
except:
ipl.errout('Unexpected error')
def features_of_paths_image_iteration(ipl, disttransf_images, feature_images):
params = ipl.get_params()
thisparams = params['features_of_paths']
features = IPL()
for d, k, v, kl in ipl.data_iterator(yield_short_kl=True):
if k == 'true':
ipl.logging('Key list: {}', kl)
ipl[kl].setlogger(ipl.getlogger())
features[kl] = features_of_paths(
ipl[kl], disttransf_images[kl], feature_images[kl],
thisparams
)
return features
def paths_within_labels_image_iteration(ipl):
params = ipl.get_params()
thisparams = params['paths_within_labels']
paths = IPL()
for d, k, v, kl in ipl.data_iterator(yield_short_kl=True):
if k == params['locmaxbordernames'][0]:
ipl[kl].setlogger(ipl.getlogger())
paths[kl] = paths_within_labels(
ipl[kl],
params['largeobjname'],
(params['locmaxbordernames'][0], params['locmaxnames'][0]),
params['locmaxbordernames'][2],
thisparams,
ignore=thisparams['ignore'])
return paths
def paths_of_partners_image_iteration(ipl):
params = ipl.get_params()
thisparams = params['paths_of_partners']
paths = IPL()
for d, k, v, kl in ipl.data_iterator(yield_short_kl=True):
if k == params['locmaxbordernames'][1]:
ipl[kl].setlogger(ipl.getlogger())
paths[kl] = paths_of_partners(
ipl[kl], params['largeobjmnames'][0], params['largeobjname'],
params['largeobjmnames'][4],
(params['locmaxbordernames'][1], params['locmaxnames'][1]),
params['locmaxbordernames'][3], thisparams,
thisparams['ignore'])
# (ipl, 'largeobjm', 'largeobj',
# 'change_hash', ('border_locmax_m', 'locmaxm'),
# 'disttransfm', thisparams['ignore'])
return paths
import matplotlib.pylab as lab
import processing_lib as lib
# TODO: Visualize Distancetransform along paths of true and false merges
# TODO: Also intensity values or raw data and probability map
# TODO: Do not forget to save the result for the thesis!
__author__ = 'jhennies'
if __name__ == '__main__':
yamlfile = os.path.dirname(os.path.abspath(__file__)) + '/parameters.yml'
hfp = IPL(yaml=yamlfile,
yamlspec={
'path': 'intermedfolder',
'filename': 'pathstruefile'
},
tkeys='true',
castkey=None)
params = hfp.get_params()
hfp.data_from_file(filepath=params['intermedfolder'] +
params['pathsfalsefile'],
tkeys='false',
castkey=None)
hfp.data_from_file(filepath=params['intermedfolder'] +
params['locmaxfile'],
skeys=('disttransf', 'disttransfm'),
tkeys=('disttransf', 'disttransfm'))
result[k, '0'] = random_forest(v['0'], v['1'])
result[k, '1'] = random_forest(v['1'], v['0'])
return result
if __name__ == '__main__':
resultsfolder = '/mnt/localdata02/jhennies/neuraldata/results/cremi_2016/161110_random_forest_of_paths/'
yamlfile = resultsfolder + '/parameters.yml'
features = IPL(yaml=yamlfile,
yamlspec={
'path': 'intermedfolder',
'filename': 'featurefile'
})
params = features.get_params()
thisparams = params['random_forest']
features.startlogger(filename=params['resultfolder'] + 'random_forest.log',
type='w')
try:
# Copy the script file and the parameters to the scriptsfolder
copy(inspect.stack()[0][1], params['scriptsfolder'])
copy(yamlfile,
params['scriptsfolder'] + 'random_forest.parameters.yml')
# Write script and parameters to the logfile
features.code2log(inspect.stack()[0][1])
# cremi = IPL(filepath='/mnt/localdata02/jhennies/neuraldata/cremi_2016/sample_B_20160501.hdf')
#
# cremi.logging('Datastructure:\n---\n{}', cremi.datastructure2string())
#
# images = IPL(data={
# 'raw': cremi['volumes', 'raw'],
# 'neuron_ids': cremi['volumes', 'labels', 'neuron_ids']
# })
#
# images.logging('Datastructure:\n---\n{}', images.datastructure2string())
#
# images.write('/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splB.raw_neurons.crop.h5')
cremi = IPL(
filepath=
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/sample_C_20160501.hdf'
)
cremi.logging('Datastructure:\n---\n{}', cremi.datastructure2string())
images = IPL(
data={
'raw': cremi['volumes', 'raw'],
'neuron_ids': cremi['volumes', 'labels', 'neuron_ids']
})
images.logging('Datastructure:\n---\n{}', images.datastructure2string())
images.write(
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splC.raw_neurons.crop.h5'
)
from hdf5_image_processing import Hdf5ImageProcessingLib as IPL
import os
import numpy as np
__author__ = 'jhennies'
if __name__ == '__main__':
yamlfile = os.path.dirname(os.path.abspath(__file__)) + '/parameters.yml'
ipl = IPL(yaml=yamlfile)
ipl.logging('Parameters: {}', ipl.get_params())
params = ipl.get_params()
ipl.data_from_file(filepath=params['datafolder'] +
'cremi.splA.raw_neurons.crop.h5',
skeys='raw',
tkeys='raw')
ipl.crop_bounding_rect(np.s_[10:110, 200:712, 200:712], keys='raw')
ipl.write(filepath=params['datafolder'] +
'cremi.splA.raw_neurons.crop.crop_10-200-200_110-712-712.h5')
keys=locmaxnames)
# Local maxima
hfp.logging('Discovering mountains ...')
hfp.extended_local_maxima(neighborhood=26, keys=locmaxnames)
if __name__ == '__main__':
yamlfile = os.path.dirname(os.path.abspath(__file__)) + '/parameters.yml'
hfp = IPL(yaml=yamlfile,
yamlspec={
'path': 'intermedfolder',
'filename': 'locmaxborderfile',
'skeys': {
'locmaxbordernames': (2, 3)
}
},
tkeys=('disttransf', 'disttransfm'),
castkey=None)
params = hfp.get_params()
thisparams = params['localmax_on_disttransf']
hfp.startlogger(filename=params['resultfolder'] +
'localmax_on_disttransf.log',
type='w')
try:
# Copy the script file and the parameters to the scriptsfolder
copy(inspect.stack()[0][1], params['scriptsfolder'])
copy(yamlfile,
'===============================\nWorking on image: {}',
kl + [k])
ipl[kl].setlogger(ipl.getlogger())
ipl[kl] = accumulate_small_objects(ipl[kl], k, thisparams)
if __name__ == '__main__':
resultsfolder = '/mnt/localdata02/jhennies/neuraldata/results/cremi_2016/161110_random_forest_of_paths/'
yamlfile = resultsfolder + '/parameters.yml'
ipl = IPL(yaml=yamlfile,
yamlspec={
'path': 'datafolder',
'filename': 'labelsfile'
})
params = ipl.get_params()
ipl.startlogger(filename=params['resultfolder'] +
'remove_small_objects.log',
type='a')
try:
# Create folder for scripts
if not os.path.exists(params['scriptsfolder']):
os.makedirs(params['scriptsfolder'])
else:
if params['overwriteresults']:
ipl.logging(
# sample_a.logging('Sample A datastructure\n---\n{}', sample_a.datastructure2string())
#
# reskeys = ('0', '1')
# split_sample_a = IPL()
# split_sample_a['z'] = sample_a.anytask(lib.split, 2, axis=0, result_keys=reskeys, return_only=True)
# split_sample_a['y'] = sample_a.anytask(lib.split, 2, axis=1, result_keys=reskeys, return_only=True)
# split_sample_a['x'] = sample_a.anytask(lib.split, 2, axis=2, result_keys=reskeys, return_only=True)
#
# split_sample_a = split_sample_a.switch_levels(1, 2)
# sample_a.logging('Split sample A datastructure\n---\n{}', split_sample_a.datastructure2string())
#
# split_sample_a.write('/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.raw_neurons.crop.split_xyz.h5')
# Sample B
sample = IPL(
filepath=
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splB.raw_neurons.crop.h5'
)
sample.logging('Sample B datastructure\n---\n{}',
sample.datastructure2string())
reskeys = ('0', '1')
split_sample = IPL()
split_sample['z'] = sample.anytask(lib.split,
2,
axis=0,
result_keys=reskeys,
return_only=True)
split_sample['y'] = sample.anytask(lib.split,
2,
axis=1,
(params['locmaxbordernames'][2],
params['locmaxbordernames'][3]),
thisparams)
if __name__ == '__main__':
resultsfolder = '/mnt/localdata02/jhennies/neuraldata/results/cremi_2016/161110_random_forest_of_paths/'
yamlfile = resultsfolder + '/parameters.yml'
ipl = IPL(yaml=yamlfile,
yamlspec={
'path': 'intermedfolder',
'filename': 'locmaxborderfile',
'skeys': {
'locmaxbordernames': (2, 3)
}
},
recursive_search=True)
params = ipl.get_params()
thisparams = params['localmax_on_disttransf']
ipl.startlogger(filename=params['resultfolder'] +
'localmax_on_disttransf.log',
type='w')
try:
# Copy the script file and the parameters to the scriptsfolder
copy(inspect.stack()[0][1], params['scriptsfolder'])
copy(yamlfile,
data = IPL(data={k: v})
data.setlogger(ipl.getlogger())
merged[kl] = merge_adjacent_objects(data, k, thisparams)
return merged
if __name__ == '__main__':
resultsfolder = '/mnt/localdata02/jhennies/neuraldata/results/cremi_2016/161110_random_forest_of_paths/'
yamlfile = resultsfolder + '/parameters.yml'
ipl = IPL(yaml=yamlfile,
yamlspec={
'path': 'intermedfolder',
'filename': 'largeobjfile'
})
params = ipl.get_params()
ipl.startlogger(filename=params['resultfolder'] +
'merge_adjacent_objects.log',
type='w')
try:
# Copy the script file and the parameters to the scriptsfolder
copy(inspect.stack()[0][1], params['scriptsfolder'])
copy(yamlfile,
params['scriptsfolder'] + 'merge_adjacent_objects.parameters.yml')
# Write script and parameters to the logfile
ipl.code2log(inspect.stack()[0][1])
hfp.rename_entry(key, targetnames[0])
for k, v in change_hash.iteritems():
for x in v:
if x != k:
hfp.logging('Setting {} to {}!', x, k)
hfp.filter_values(x, type='eq', setto=k, keys=targetnames[0])
if __name__ == '__main__':
yamlfile = os.path.dirname(os.path.abspath(__file__)) + '/parameters.yml'
hfp = IPL(yaml=yamlfile,
yamlspec={
'path': 'intermedfolder',
'filename': 'largeobjfile',
'skeys': 'largeobjname'
},
tkeys='largeobj',
castkey=None)
params = hfp.get_params()
hfp.startlogger(filename=params['resultfolder'] +
'merge_adjacent_objects.log',
type='w')
try:
# Copy the script file and the parameters to the scriptsfolder
copy(inspect.stack()[0][1], params['scriptsfolder'])
copy(yamlfile,
params['scriptsfolder'] + 'merge_adjacent_objects.parameters.yml')
# Write script and parameters to the logfile
def merge_adjacent_objects(ipl, key, thisparams):
"""
:param ipl:
ipl.get_params():
merge_adjacent_objects
seed
numberbysize
numberbyrandom
largeobjmnames
- 'largeobj_merged'
- 'mergeids_small'
- 'mergeids_random'
- 'mergeids_all'
- 'change_hash'
:param key: the source key for calculation
"""
numberbysize = thisparams['numberbysize']
numberbyrandom = thisparams['numberbyrandom']
targetnames = params['largeobjmnames']
# Get only the relevant labels
labels = lib.unique(ipl[key])
ipl.logging('labels = {}', labels)
# Seed the randomize function
random.seed(thisparams['seed'])
ipl.astype(np.uint32, keys=key)
(grag, rag) = graphs.gridRegionAdjacencyGraph(ipl[key], ignoreLabel=0)
edge_ids = rag.edgeIds()
# ipl.logging('Edge ids: {}', edge_ids)
# Type 1:
# Select edges by size (smallest edges)
ipl.logging('Number of edgeLengths = {}', len(rag.edgeLengths()))
edgelen_ids = dict(zip(edge_ids, rag.edgeLengths()))
# ifp.logging('edgelen_ids = {}', edgelen_ids)
sorted_edgelens = np.sort(rag.edgeLengths())
#
smallest_merge_lens = sorted_edgelens[0:numberbysize]
ipl.logging('Lengths selected for merging: {}', smallest_merge_lens)
#
smallest_merge_ids = []
for x in smallest_merge_lens:
edge_id = edgelen_ids.keys()[edgelen_ids.values().index(x)]
smallest_merge_ids.append(edge_id)
edgelen_ids.pop(edge_id)
#
edge_ids = edgelen_ids.keys()
ipl.logging('Edge IDs selected for merging due to size: {}',
smallest_merge_ids)
# Type 2:
# Randomly choose edges
random_merge_ids = random.sample(edge_ids, numberbyrandom)
ipl.logging('Edge IDs randomly selected for merging: {}', random_merge_ids)
# Now get the label ids
smallest_merge_labelids_u = [
rag.uId(rag.edgeFromId(x)) for x in smallest_merge_ids
]
smallest_merge_labelids_v = [
rag.vId(rag.edgeFromId(x)) for x in smallest_merge_ids
]
smallest_merge_labelids = list(
zip(smallest_merge_labelids_u, smallest_merge_labelids_v))
random_merge_labelids_u = [
rag.uId(rag.edgeFromId(x)) for x in random_merge_ids
]
random_merge_labelids_v = [
rag.vId(rag.edgeFromId(x)) for x in random_merge_ids
]
random_merge_labelids = list(
zip(random_merge_labelids_u, random_merge_labelids_v))
ipl.logging('Label IDs selected for merging by size: {}',
smallest_merge_labelids)
ipl.logging('Label IDs randomly selected for merging: {}',
random_merge_labelids)
# Concatenate
all_merge_labelids = smallest_merge_labelids + random_merge_labelids
# Sort
ipl.logging('all_merge_labelids = {}', all_merge_labelids)
all_merge_labelids = [sorted(x) for x in all_merge_labelids]
all_merge_labelids = sorted(all_merge_labelids)
ipl.logging('all_merge_labelids = {}', all_merge_labelids)
# Store this for later use
ipl[targetnames[1]] = smallest_merge_labelids
ipl[targetnames[2]] = random_merge_labelids
ipl[targetnames[3]] = all_merge_labelids
# Create change hash list
change_hash = IPL(data=dict(
zip(np.unique(all_merge_labelids), [[
x,
] for x in np.unique(all_merge_labelids)])))
for i in xrange(0, 3):
prev_change_hash = IPL(data=change_hash)
for x in all_merge_labelids:
ipl.logging('Adding {} and {}', *x)
change_hash[x[0]] += change_hash[x[1]]
change_hash[x[0]] = list(np.unique(change_hash[x[0]]))
change_hash[x[1]] += change_hash[x[0]]
change_hash[x[1]] = list(np.unique(change_hash[x[1]]))
# This removes the redundancy from the hash
def reduce(hash):
br = False
for k, v in hash.iteritems():
for x in v:
if x != k:
if x in hash.keys():
del hash[x]
reduce(hash)
br = True
break
else:
br = False
if br:
break
reduce(change_hash)
# Change the list in the hash to np-arrays for better storage in h5 files
for k, v in change_hash.iteritems():
change_hash[k] = np.array(v)
# And now we have a perfect change list which we just need to iterate over and change the labels in the image
ipl.logging('change_hash after change:')
ipl.logging(change_hash)
ipl[targetnames[4]] = change_hash
# Create the merged image
# ipl.deepcopy_entry('largeobj', targetnames[0])
ipl.rename_entry(key, targetnames[0])
for k, v in change_hash.iteritems():
for x in v:
if x != k:
ipl.logging('Setting {} to {}!', x, k)
ipl.filter_values(x, type='eq', setto=k, keys=targetnames[0])
return ipl
def random_forest(ipl, debug=False):
params = ipl.get_params()
thisparams = rdict(params['random_forest'])
targetfile = params['resultfolder'] + params['resultsfile']
# Load the necessary images
load_images(ipl)
ipl.logging('\nInitial datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
result = IPL()
new_eval = rdict()
evaluation = rdict()
for d, k, v, kl in ipl.data_iterator(yield_short_kl=True):
if k == '0':
ipl.logging('===============================\nWorking on group: {}', kl)
# TODO: Implement copy full logger
ipl[kl].set_logger(ipl.get_logger())
# Note:
# Due to the feature input being a dictionary organized by the feature images where
# the feature values come from
#
# [kl]
# '0'|'1'
# 'true'|'false'
# [featureims]
# 'Sum': [s1, ..., sN]
# 'Variance': [v1, ..., vN]
# ...
# [Pathlength]: [l1, ..., lN]
#
# the exact order in which items are iterated over by data_iterator() is not known.
#
# Solution:
# Iterate over it once and store the keylist in an array (which conserves the order)
# When accumulating the featrues for each of the four corresponding subsets, namely
# training and testing set with true and false paths each, i.e.
# ['0'|'1']['true'|'false'],
# the the keylist is used, thus maintaining the correct order in every subset.
#
# And that is what is happening here:
keylist = []
for d2, k2, v2, kl2 in ipl[kl]['0', 'true'].data_iterator():
if type(v2) is not type(ipl[kl]['0', 'true']):
keylist.append(kl2)
# Load the image data into memory
ipl[kl].populate()
# ipl[kl]['0', 'true'] = libip.rf_make_feature_array(ipl[kl]['0', 'true'])
# ipl.logging("Computed feature array for ['0', 'true'] with shape {}", ipl[kl]['0', 'true'].shape)
# ipl[kl]['0', 'false'] = libip.rf_make_feature_array(ipl[kl]['0', 'false'])
# ipl.logging("Computed feature array for ['0', 'false'] with shape {}", ipl[kl]['0', 'false'].shape)
# ipl[kl]['1', 'true'] = libip.rf_make_feature_array(ipl[kl]['1', 'true'])
# ipl.logging("Computed feature array for ['1', 'true'] with shape {}", ipl[kl]['1', 'true'].shape)
# ipl[kl]['1', 'false'] = libip.rf_make_feature_array(ipl[kl]['1', 'false'])
# ipl.logging("Computed feature array for ['1', 'false'] with shape {}", ipl[kl]['1', 'false'].shape)
ipl[kl]['0', 'true'] = libip.rf_make_feature_array_with_keylist(ipl[kl]['0', 'true'], keylist)
ipl.logging("Computed feature array for ['0', 'true'] with shape {}", ipl[kl]['0', 'true'].shape)
ipl[kl]['0', 'false'] = libip.rf_make_feature_array_with_keylist(ipl[kl]['0', 'false'], keylist)
ipl.logging("Computed feature array for ['0', 'false'] with shape {}", ipl[kl]['0', 'false'].shape)
ipl[kl]['1', 'true'] = libip.rf_make_feature_array_with_keylist(ipl[kl]['1', 'true'], keylist)
ipl.logging("Computed feature array for ['1', 'true'] with shape {}", ipl[kl]['1', 'true'].shape)
ipl[kl]['1', 'false'] = libip.rf_make_feature_array_with_keylist(ipl[kl]['1', 'false'], keylist)
ipl.logging("Computed feature array for ['1', 'false'] with shape {}", ipl[kl]['1', 'false'].shape)
# print '...'
# print ipl[kl]['0']
result[kl + ['0']] = libip.random_forest(ipl[kl]['0'], ipl[kl]['1'], debug=debug)
result[kl + ['1']] = libip.random_forest(ipl[kl]['1'], ipl[kl]['0'], debug=debug)
new_eval[kl + ['0']] = libip.new_eval([x[0] for x in result[kl]['0']], [x[1] for x in result[kl]['0']])
new_eval[kl + ['1']] = libip.new_eval([x[0] for x in result[kl]['1']], [x[1] for x in result[kl]['1']])
evaluation[kl + ['0']] = libip.evaluation(result[kl]['0'])
evaluation[kl + ['1']] = libip.evaluation(result[kl]['1'])
ipl.logging('+++ RESULTS +++')
ipl.logging("[kl]['0']")
for i in result[kl]['0']:
ipl.logging('{}', i)
# for key, value in evaluation[kl]['0'].iteritems():
# ipl.logging('{} = {}', key, value)
for key, value in new_eval[kl]['0'].iteritems():
ipl.logging('{} = {}', key, value)
ipl.logging('+++')
ipl.logging("[kl]['1']")
for i in result[kl]['1']:
ipl.logging('{}', i)
# for key, value in evaluation[kl]['1'].iteritems():
# ipl.logging('{} = {}', key, value)
for key, value in new_eval[kl]['1'].iteritems():
ipl.logging('{} = {}', key, value)
# # Write the result to file
# ipl.write(filepath=targetfile, keys=[kl])
# Free memory
ipl[kl] = None
return IPL(data=result), IPL(data=evaluation)
