def run_compute_feature_images(yamlfile):
ipl = IPL(yaml=yamlfile)
ipl.set_indent(1)
params = rdict(data=ipl.get_params())
ipl.startlogger(filename=params['resultfolder'] + 'compute_feature_images.log', type='w', name='ComputeFeatureImages')
try:
# # Copy the script file and the parameters to the scriptsfolder
# copy(inspect.stack()[0][1], params['scriptsfolder'])
# copy(yamlfile, params['scriptsfolder'] + 'compute_feature_images.parameters.yml')
# ipl.logging('\nInitial datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
compute_feature_images(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 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 run_find_border_contacts(yamlfile, logging=True):
ipl = IPL(yaml=yamlfile)
ipl.set_indent(1)
params = rdict(data=ipl.get_params())
if logging:
ipl.startlogger(filename=params['resultfolder'] + 'find_border_contacts.log', type='w', name='FindBorderContacts')
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'] + 'find_border_contacts.parameters.yml')
# ipl.logging('\nInitial datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
find_border_contacts(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 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 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 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 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')
# tkeys='true',
# castkey=None
# )
# params = hfp.get_params()
# hfp.logging('params = {}', params)
# hfp.data_from_file(
# filepath=params['intermedfolder'] + params['pathsfalsefile'],
# tkeys='false',
# castkey=None
# )
hfp.startlogger(filename=params["intermedfolder"] + "features_of_paths.log", type="a")
try:
hfp.code2log(inspect.stack()[0][1])
hfp.logging("")
hfp.yaml2log()
hfp.logging("")
hfp.logging("\nhfp datastructure: \n\n{}", hfp.datastructure2string(maxdepth=1))
# Done: Iterate over paths and accumulate features
# Done: Implement data iterator
# Done: Make path image (true)
# Done: Make path image (false)
# TODO: Get topological features
# Done: Topological feature: Length
# TODO: Topological feature: Statistics on curvature
# TODO: Get data features on path (raw, probabilities, distance transform)
# TODO: Get data features on end points (raw, probabilities, distance transform)
'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])
features.logging('')
features.yaml2log()
features.logging('')
features.logging('\nfeatures datastructure: \n---\n{}',
features.datastructure2string(maxdepth=2))
result = random_forest_iteration(features)
result.write(filepath=params['intermedfolder'] +
params['randforestfile'])
features.logging('\nFinal dictionary structure:\n---\n{}',
features.datastructure2string(maxdepth=2))
features.logging('')
features.stoplogger()
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')
skeys=params['locmaxnames'][0],
recursive_search=True,
integrate=True)
ipl.data_from_file(params['intermedfolder'] + params['locmaxborderfile'],
skeys=(params['locmaxbordernames'][0], params['locmaxbordernames'][2]),
recursive_search=True,
integrate=True)
try:
# Copy the script file and the parameters to the scriptsfolder
copy(inspect.stack()[0][1], params['scriptsfolder'])
copy(yamlfile, params['scriptsfolder'] + 'paths_within_labels.parameters.yml')
# Write script and parameters to the logfile
ipl.code2log(inspect.stack()[0][1])
ipl.logging('')
ipl.yaml2log()
ipl.logging('')
ipl.logging('\nipl datastructure: \n\n{}', ipl.datastructure2string(maxdepth=3))
paths = paths_within_labels_image_iteration(ipl)
paths.write(filepath=params['intermedfolder'] + params['pathstruefile'])
ipl.logging('\nFinal dictionary structure:\n---\n{}', ipl.datastructure2string())
ipl.logging('')
ipl.stoplogger()
except:
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,
params['scriptsfolder'] + 'localmax_on_disttransf.parameters.yml')
# Write script and parameters to the logfile
hfp.code2log(inspect.stack()[0][1])
hfp.logging('')
hfp.yaml2log()
hfp.logging('')
hfp.logging('\nhfp datastructure: \n\n{}',
hfp.datastructure2string(maxdepth=1))
localmax_on_disttransf(hfp, ('disttransf', 'disttransfm'))
hfp.write(filepath=params['intermedfolder'] + params['locmaxfile'])
hfp.logging('\nFinal dictionary structure:\n---\n{}',
hfp.datastructure2string())
hfp.logging('')
hfp.stoplogger()
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'))
hfp.startlogger()
try:
hfp.logging('hfp datastructure:\n---\n{}---',
hfp.datastructure2string(maxdepth=2))
hfp.anytask(lib.getvaluesfromcoords,
reciprocal=True,
keys='disttransfm',
indict=hfp['false', '6155_9552'],
tkeys='result_false')
hfp.logging('hfp datastructure:\n---\n{}---',
hfp.datastructure2string(maxdepth=2))
# y = []
# maxlen = 0
# for d, k, v, kl in hfp['result_false'].data_iterator():
# y.append(v)
# x = range(0, len(v))
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')
filepath=params['intermedfolder'] + params['locmaxborderfile'],
skeys=('disttransf', 'disttransfm'),
tkeys=('disttransf', 'disttransfm')
)
hfp.data_from_file(
filepath=params['datafolder'] + params['rawdatafile'],
skeys=params['rawdataname'],
tkeys='raw'
)
hfp.startlogger()
try:
hfp.logging('hfp datastructure:\n---\n{}---', hfp.datastructure2string(maxdepth=2))
# hfp.anytask(lib.getvaluesfromcoords,
# reciprocal=True,
# keys='disttransfm',
# indict=hfp['false', '6155_9552'],
# tkeys='result_false'
# )
# hfp.anytask(lib.getvaluesfromcoords,
# reciprocal=True,
# keys='disttransf',
# indict=hfp['true', 'border', '27'],
# tkeys='result_true')
# hfp.logging('hfp datastructure:\n---\n{}---', hfp.datastructure2string(maxdepth=2))
castkey=None
)
params = hfp.get_params()
thisparams = params['find_border_contacts']
hfp.data_from_file(params['intermedfolder'] + params['largeobjmfile'],
skeys=params['largeobjmnames'][0], tkeys='largeobjm')
hfp.startlogger(filename=params['resultfolder'] + 'find_orphans.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'] + 'find_orphans.parameters.yml')
# Write script and parameters to the logfile
hfp.code2log(inspect.stack()[0][1])
hfp.logging('')
hfp.yaml2log()
hfp.logging('')
hfp.logging('\nhfp datastructure: \n---\n{}', hfp.datastructure2string(maxdepth=1))
if thisparams['return_bordercontact_images']:
bordercontacts = find_border_contacts(hfp, ('largeobj', 'largeobjm'))
else:
find_border_contacts(hfp, ('largeobj', 'largeobjm'))
hfp.write(filepath=params['intermedfolder'] + params['locmaxborderfile'])
if thisparams['return_bordercontact_images']:
bordercontacts.write(filepath=params['intermedfolder'] + params['bordercontactsfile'])
hfp.logging('\nFinal hfp dictionary structure:\n---\n{}', hfp.datastructure2string())
yaml=yamlfile,
yamlspec={'path': 'datafolder', 'filename': 'labelsfile'},
tkeys='labels',
castkey=None
)
params = hfp.get_params()
hfp.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']:
hfp.logging('remove_small_objects: Warning: Scriptsfolder already exists and content will be overwritten...\n')
else:
raise IOError('remove_small_objects: Error: Scriptsfolder already exists!')
# Create folder for intermediate results
if not os.path.exists(params['intermedfolder']):
os.makedirs(params['intermedfolder'])
else:
if params['overwriteresults']:
hfp.logging('remove_small_objects: Warning: Intermedfolder already exists and content will be overwritten...\n')
else:
raise IOError('remove_small_objects: Error: Intermedfolder already exists!')
# 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')
recursive_search=True
)
params = ipl.get_params()
thisparams = params['find_border_contacts']
ipl.data_from_file(params['intermedfolder'] + params['largeobjmfile'],
skeys=params['largeobjmnames'][0], recursive_search=True, integrate=True)
ipl.startlogger(filename=params['resultfolder'] + 'find_border_contacts.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'] + 'find_border_contacts.parameters.yml')
# Write script and parameters to the logfile
ipl.code2log(inspect.stack()[0][1])
ipl.logging('')
ipl.yaml2log()
ipl.logging('')
ipl.logging('\nipl datastructure: \n---\n{}', ipl.datastructure2string(maxdepth=3))
bordercontacts = find_border_contacts_image_iteration(ipl)
ipl.write(filepath=params['intermedfolder'] + params['locmaxborderfile'])
if thisparams['return_bordercontact_images']:
bordercontacts.write(filepath=params['intermedfolder'] + params['bordercontactsfile'])
ipl.logging('\nFinal ipl dictionary structure:\n---\n{}', ipl.datastructure2string())
if thisparams['return_bordercontact_images']:
ipl.logging('\nFinal bordercontacts dictionary structure:\n---\n{}', bordercontacts.datastructure2string())
from hdf5_image_processing import Hdf5ImageProcessingLib as IPL
import processing_lib as lib
# Sample A probs
probs_a = IPL(
filepath=
'/mnt/localdata01/jhennies/neuraldata/cremi_2016/sample_A_train_betas/sample_A_train_mcseg_beta_0.5.h5'
)
probs_a.logging('Probs A datastructure\n---\n{}',
probs_a.datastructure2string())
probs_a.anytask(lib.swapaxes, 0, 2)
probs_a.write(
'/mnt/localdata01/jhennies/neuraldata/cremi_2016/sample_A_train_betas/cremi.splA.train.seg_beta_0.5.crop.h5'
)
reskeys = ('0', '1')
split_probs_a = IPL()
split_probs_a['z'] = probs_a.anytask(lib.split,
2,
axis=0,
result_keys=reskeys,
return_only=True,
rtrntype=IPL)
split_probs_a['y'] = probs_a.anytask(lib.split,
2,
axis=1,
result_keys=reskeys,
return_only=True,
infiles = [
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.probs.crop.h5',
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.raw_neurons.crop.h5'
]
outfiles = [
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.probs.crop.crop_x10_110_y200_712_z200_712.split_xyz.h5',
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.raw_neurons.crop.crop_x10_110_y200_712_z200_712.split_xyz.h5'
]
for i in xrange(0, len(infiles)):
ipl = IPL(
filepath=infiles[i]
)
ipl.logging('Datastructure\n---\n{}', ipl.datastructure2string())
ipl.crop_bounding_rect(bounds=np.s_[10:110, 200:712, 200:712])
def shape(image):
return image.shape
print ipl.datastructure2string(function=shape)
ipl_split = split_in_xyz(ipl)
ipl_split.write(filepath=outfiles[i])
# # Sample A
# sample_a = IPL(
# filepath='/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.raw_neurons.crop.h5'
# )
skeys=params['largeobjmnames'][0],
recursive_search=True,
integrate=True)
ipl.startlogger(filename=params['resultfolder'] +
'find_border_contacts.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'] + 'find_border_contacts.parameters.yml')
# Write script and parameters to the logfile
ipl.code2log(inspect.stack()[0][1])
ipl.logging('')
ipl.yaml2log()
ipl.logging('')
ipl.logging('\nipl datastructure: \n---\n{}',
ipl.datastructure2string(maxdepth=3))
bordercontacts = find_border_contacts_image_iteration(ipl)
ipl.write(filepath=params['intermedfolder'] +
params['locmaxborderfile'])
if thisparams['return_bordercontact_images']:
bordercontacts.write(filepath=params['intermedfolder'] +
params['bordercontactsfile'])
ipl.logging('\nFinal ipl dictionary structure:\n---\n{}',
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,
params['scriptsfolder'] + 'localmax_on_disttransf.parameters.yml')
# Write script and parameters to the logfile
ipl.code2log(inspect.stack()[0][1])
ipl.logging('')
ipl.yaml2log()
ipl.logging('')
ipl.logging('\nipl datastructure: \n\n{}',
ipl.datastructure2string(maxdepth=3))
localmax_on_disttransf_image_iteration(ipl)
ipl.write(filepath=params['intermedfolder'] + params['locmaxfile'])
ipl.logging('\nFinal dictionary structure:\n---\n{}',
ipl.datastructure2string())
ipl.logging('')
ipl.stoplogger()
if __name__ == "__main__":
# 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')
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])
features.logging('')
features.yaml2log()
features.logging('')
features.logging('\nfeatures datastructure: \n---\n{}', features.datastructure2string(maxdepth=2))
result = random_forest_iteration(features)
result.write(filepath=params['intermedfolder'] + params['randforestfile'])
features.logging('\nFinal dictionary structure:\n---\n{}', features.datastructure2string(maxdepth=2))
features.logging('')
features.stoplogger()
except:
raise
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('remove_small_objects: Warning: Scriptsfolder already exists and content will be overwritten...\n')
else:
raise IOError('remove_small_objects: Error: Scriptsfolder already exists!')
# Create folder for intermediate results
if not os.path.exists(params['intermedfolder']):
os.makedirs(params['intermedfolder'])
else:
if params['overwriteresults']:
ipl.logging('remove_small_objects: Warning: Intermedfolder already exists and content will be overwritten...\n')
else:
raise IOError('remove_small_objects: Error: Intermedfolder already exists!')
# 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')
'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(
'remove_small_objects: Warning: Scriptsfolder already exists and content will be overwritten...\n'
)
else:
raise IOError(
'remove_small_objects: Error: Scriptsfolder already exists!'
)
# Create folder for intermediate results
if not os.path.exists(params['intermedfolder']):
os.makedirs(params['intermedfolder'])
else:
if params['overwriteresults']:
ipl.logging(
'remove_small_objects: Warning: Intermedfolder already exists and content will be overwritten...\n'
)
else:
# 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, result_keys=reskeys, return_only=True)
split_sample['x'] = sample.anytask(lib.split, 2, axis=2, result_keys=reskeys, return_only=True)
split_sample = split_sample.switch_levels(1, 2)
sample.logging('Split sample B datastructure\n---\n{}', split_sample.datastructure2string())
split_sample.write('/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splB.raw_neurons.crop.split_xyz.h5')
# Sample C
sample = IPL(
filepath='/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splC.raw_neurons.crop.h5'
# )
# params = hfp.get_params()
# hfp.logging('params = {}', params)
# hfp.data_from_file(
# filepath=params['intermedfolder'] + params['pathsfalsefile'],
# tkeys='false',
# castkey=None
# )
hfp.startlogger(filename=params['intermedfolder'] +
'features_of_paths.log',
type='a')
try:
hfp.code2log(inspect.stack()[0][1])
hfp.logging('')
hfp.yaml2log()
hfp.logging('')
hfp.logging('\nhfp datastructure: \n\n{}',
hfp.datastructure2string(maxdepth=1))
# Done: Iterate over paths and accumulate features
# Done: Implement data iterator
# Done: Make path image (true)
# Done: Make path image (false)
# TODO: Get topological features
# Done: Topological feature: Length
# TODO: Topological feature: Statistics on curvature
# TODO: Get data features on path (raw, probabilities, distance transform)
ipl.rename_layer('largeobjm', 'false')
ipl.remove_layer('path')
# ipl['false', 'border'] = IPL(data=ipl['largeobjm', 'border_locmax_m', 'path'])
# ipl['false', 'locmax'] = IPL(data=ipl['largeobjm', 'locmaxm', 'path'])
# ipl.pop('largeobjm')
#
# ipl.pop('pathsim')
# ipl.pop('overlay')
ipl.startlogger(filename=params['resultfolder']+'features_of_paths.log', type='w')
try:
ipl.code2log(inspect.stack()[0][1])
ipl.logging('')
ipl.yaml2log()
ipl.logging('')
ipl.logging('\nipl datastructure: \n\n{}', ipl.datastructure2string(maxdepth=4))
# Done: Make path image (true)
# Done: Make path image (false)
# TODO: Get topological features
# TODO: Topological feature: Length (with respect to anisotropy!)
# TODO: Topological feature: Statistics on curvature
# TODO: Get data features on path (raw, probabilities, distance transform)
# TODO: Get data features on end points (raw, probabilities, distance transform)
# Done: Cross-computation of two ImageProcessing instances
# Done: This is total bullshit! I need to iterate over all paths and extract the region features individually!
yaml=yamlfile,
yamlspec={'path': 'datafolder', '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
hfp.code2log(inspect.stack()[0][1])
hfp.logging('')
hfp.yaml2log()
hfp.logging('')
hfp.logging('\nhfp datastructure: \n\n{}', hfp.datastructure2string(maxdepth=1))
merge_adjacent_objects(hfp)
hfp.write(filepath=params['intermedfolder'] + params['largeobjmfile'])
hfp.logging('\nFinal dictionary structure:\n---\n{}', hfp.datastructure2string())
hfp.logging('')
hfp.stoplogger()
except:
if __name__ == "__main__":
infiles = [
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.probs.crop.h5',
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.raw_neurons.crop.h5'
]
outfiles = [
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.probs.crop.crop_x10_110_y200_712_z200_712.split_xyz.h5',
'/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.raw_neurons.crop.crop_x10_110_y200_712_z200_712.split_xyz.h5'
]
for i in xrange(0, len(infiles)):
ipl = IPL(filepath=infiles[i])
ipl.logging('Datastructure\n---\n{}', ipl.datastructure2string())
ipl.crop_bounding_rect(bounds=np.s_[10:110, 200:712, 200:712])
def shape(image):
return image.shape
print ipl.datastructure2string(function=shape)
ipl_split = split_in_xyz(ipl)
ipl_split.write(filepath=outfiles[i])
# # Sample A
# sample_a = IPL(
# filepath='/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.raw_neurons.crop.h5'
# 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'
)
# 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,
result_keys=reskeys,
return_only=True)
split_sample['x'] = sample.anytask(lib.split,
2,
tkeys='labels',
castkey=None)
params = hfp.get_params()
hfp.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']:
hfp.logging(
'remove_small_objects: Warning: Scriptsfolder already exists and content will be overwritten...\n'
)
else:
raise IOError(
'remove_small_objects: Error: Scriptsfolder already exists!'
)
# Create folder for intermediate results
if not os.path.exists(params['intermedfolder']):
os.makedirs(params['intermedfolder'])
else:
if params['overwriteresults']:
hfp.logging(
'remove_small_objects: Warning: Intermedfolder already exists and content will be overwritten...\n'
)
else:
from hdf5_image_processing import Hdf5ImageProcessingLib as IPL
import processing_lib as lib
# Sample A probs
probs_a = IPL(
filepath='/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.probs_cantorV1.h5'
)
probs_a.logging('Probs A datastructure\n---\n{}', probs_a.datastructure2string())
probs_a.anytask(lib.swapaxes, 0, 2)
probs_a.write('/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.probs.crop.h5')
reskeys = ('0', '1')
split_probs_a = IPL()
split_probs_a['z'] = probs_a.anytask(lib.split, 2, axis=0, result_keys=reskeys, return_only=True, rtrntype=IPL)
split_probs_a['y'] = probs_a.anytask(lib.split, 2, axis=1, result_keys=reskeys, return_only=True, rtrntype=IPL)
split_probs_a['x'] = probs_a.anytask(lib.split, 2, axis=2, result_keys=reskeys, return_only=True, rtrntype=IPL)
split_probs_a = split_probs_a.switch_levels(1, 2)
probs_a.logging('Split sample A datastructure\n---\n{}', split_probs_a.datastructure2string())
split_probs_a.write('/mnt/localdata02/jhennies/neuraldata/cremi_2016/cremi.splA.train.probs.crop.split_xyz.h5')