def __init__(self, cytomine, software_id, project_id, job_parameters,
tile_overlap, tile_width, tile_height, n_jobs, threshold,
min_area, model_path, rseed, working_path):
"""An example job implementing an sldc workflow.
Parameters
----------
cytomine: Cytomine
Cytomine client
software_id: int
Cytomine software id
project_id: int
Cytomine project id
job_parameters: dict
Job parameters
tile_overlap: int
Number of pixel of overlap between the tiles
tile_width: int
Maximum width of the tiles
tile_height: int
Maximum height of the tiles
n_jobs: int
Number of available jobs
threshold: int
Segmentation threshold in [0, 255]
min_area: int
Minimum area of the valid objects in pixel squared
model_path: str
Path to the pickled pyxit model
rseed: int
Random seed
working_path: str
Working path of the workflow (for temporary files)
"""
CytomineJob.__init__(self, cytomine, software_id, project_id, parameters=job_parameters)
Loggable.__init__(self, logger=StandardOutputLogger(Logger.INFO))
self._cytomine = cytomine
# create workflow component
random_state = check_random_state(rseed)
tile_builder = CytomineTileBuilder(cytomine, working_path=working_path)
segmenter = DemoSegmenter(threshold)
area_rule = ValidAreaRule(min_area)
classifier = PyxitClassifierAdapter.build_from_pickle(
model_path, tile_builder, self.logger,
random_state=random_state,
n_jobs=n_jobs,
working_path=working_path
)
builder = WorkflowBuilder()
builder.set_n_jobs(n_jobs)
builder.set_logger(self.logger)
builder.set_overlap(tile_overlap)
builder.set_tile_size(tile_width, tile_height)
builder.set_tile_builder(tile_builder)
builder.set_segmenter(segmenter)
builder.add_classifier(area_rule, classifier, dispatching_label="valid")
self._workflow = builder.get()
def __init__(self, cytomine, software_id, project_id, job_parameters,
fix_image_id, moving_image_id, nb_spatial_sample,
nb_iterations, storage_id, annotation_fix_id,
annotation_moving_id, working_path, cytomine_host,
cytomine_upload, pk, prk, export_overlay_images,
number_of_resolutions, result_file_name):
print("After init")
# call init from parent classes #
print("project id = " + str(project_id))
if (cytomine == None):
print "Cytomine obj null"
print("soft_id =" + str(software_id))
CytomineJob.__init__(self,
cytomine,
software_id,
project_id,
parameters=None)
Loggable.__init__(self, logger=StandardOutputLogger(Logger.INFO))
# keep var from parameters #
self._fix_image_id = fix_image_id
self._moving_image_id = moving_image_id
self._nb_spatial_sample = nb_spatial_sample
self._nb_iterations = nb_iterations
self._storage_id = storage_id
self._id_annotation_fix = annotation_fix_id
self._id_annotation_moving = annotation_moving_id
self._working_path = working_path
self._cytomine_upload = cytomine_upload
self._cytomine_host = cytomine_host
self._cytomine = cytomine
self._project_id = project_id
self._pk = pk
self._prk = prk
self._overlayed_images = export_overlay_images
self._job_parameters = job_parameters
self._number_of_resolutions = number_of_resolutions
self._result_file_name = result_file_name
def predict(argv):
parser = ArgumentParser(prog="CNN Object Counter Predictor")
# Cytomine
parser.add_argument('--cytomine_host',
dest='cytomine_host',
default='demo.cytomine.be',
help="The Cytomine host")
parser.add_argument('--cytomine_public_key',
dest='cytomine_public_key',
help="The Cytomine public key")
parser.add_argument('--cytomine_private_key',
dest='cytomine_private_key',
help="The Cytomine private key")
parser.add_argument('--cytomine_base_path',
dest='cytomine_base_path',
default='/api/',
help="The Cytomine base path")
parser.add_argument('--cytomine_working_path',
dest='cytomine_working_path',
default=None,
help="The working directory (eg: /tmp)")
parser.add_argument('--cytomine_id_software',
dest='cytomine_software',
type=int,
help="The Cytomine software identifier")
parser.add_argument('--cytomine_id_project',
dest='cytomine_project',
type=int,
help="The Cytomine project identifier")
# Objects
parser.add_argument('--cytomine_object_term',
dest='cytomine_object_term',
type=int,
help="The Cytomine identifier of object term")
# Post-processing
parser.add_argument('--post_threshold',
dest='post_threshold',
type=float,
help="Post-processing discarding threshold")
parser.add_argument(
'--post_sigma',
dest='post_sigma',
type=float,
help="Std-dev of Gauss filter applied to smooth prediction")
parser.add_argument('--post_min_dist',
dest='post_min_dist',
type=int,
help="Minimum distance between two peaks")
# ROI
parser.add_argument('--annotation',
dest='annotation',
type=int,
default=None)
parser.add_argument('--image',
dest='image',
type=int,
action='append',
default=None)
# Execution
parser.add_argument('--n_jobs',
dest='n_jobs',
type=int,
default=1,
help="Number of jobs")
parser.add_argument('--verbose',
'-v',
dest='verbose',
default=0,
help="Level of verbosity")
parser.add_argument('--model_id_job',
dest='model_id_job',
type=int,
default=None,
help="Model job ID")
params, other = parser.parse_known_args(argv)
if params.cytomine_working_path is None:
params.cytomine_working_path = os.path.join(tempfile.gettempdir(),
"cytomine")
make_dirs(params.cytomine_working_path)
# Initialize logger
logger = StandardOutputLogger(params.verbose)
for key, val in sorted(vars(params).iteritems()):
logger.info("[PARAMETER] {}: {}".format(key, val))
# Initialize Cytomine client
cytomine = Cytomine(params.cytomine_host,
params.cytomine_public_key,
params.cytomine_private_key,
working_path=params.cytomine_working_path,
base_path=params.cytomine_base_path,
verbose=(params.verbose >= Logger.DEBUG))
# Start job
with CytomineJob(cytomine,
params.cytomine_software,
params.cytomine_project,
parameters=vars(params_remove_none(params))) as job:
cytomine.update_job_status(job.job,
status_comment="Starting...",
progress=0)
cytomine.update_job_status(job.job,
status_comment="Loading model...",
progress=1)
model_job = cytomine.get_job(params.model_id_job)
model_file = os.path.join(params.cytomine_working_path, "models",
str(model_job.software),
"{}.h5".format(model_job.id))
estimator = FCRN()
estimator.model = load_model(model_file)
cytomine.update_job_status(
job.job,
status_comment="Dumping annotations/images to predict...",
progress=3)
if params.annotation is not None:
if not isinstance(params.annotation, list):
params.annotation = list(params.annotation)
annots = [cytomine.get_annotation(id) for id in params.annotation]
annots_collection = AnnotationCollection()
annots_collection._data = annots
crops = cytomine.dump_annotations(
annotations=annots_collection,
dest_path=os.path.join(params.cytomine_working_path, "crops",
str(params.cytomine_project)),
desired_zoom=0,
get_image_url_func=Annotation.get_annotation_alpha_crop_url)
X = crops.data()
elif params.image is not None:
if not isinstance(params.image, list):
params.image = list(params.image)
image_instances = [
cytomine.get_image_instance(id) for id in params.image
]
image_instances = cytomine.dump_project_images(
id_project=params.cytomine_project,
dest_path="/imageinstances/",
image_instances=image_instances)
X = image_instances
else:
X = []
logger.d("X size: {} samples".format(len(X)))
for i, x in enumerate(X):
cytomine.update_job_status(
job.job,
status_comment="Predicting ID {}...".format(x.id),
progress=5 + np.ceil(i / len(X)) * 95)
y = estimator.predict([x.filename])
cytomine.update_job_status(
job.job, status_comment="Uploading annotations...")
upload_annotations(cytomine,
x,
y,
term=params.cytomine_object_term)
cytomine.update_job_status(job.job,
status_comment="Finished.",
progress=100)
def train(argv):
parser = ArgumentParser(prog="Extra-Trees Object Counter Model Builder")
# Cytomine
parser.add_argument('--cytomine_host', dest='cytomine_host',
default='demo.cytomine.be', help="The Cytomine host")
parser.add_argument('--cytomine_public_key', dest='cytomine_public_key',
help="The Cytomine public key")
parser.add_argument('--cytomine_private_key', dest='cytomine_private_key',
help="The Cytomine private key")
parser.add_argument('--cytomine_base_path', dest='cytomine_base_path',
default='/api/', help="The Cytomine base path")
parser.add_argument('--cytomine_working_path', dest='cytomine_working_path',
default=None, help="The working directory (eg: /tmp)")
parser.add_argument('--cytomine_id_software', dest='cytomine_software', type=int,
help="The Cytomine software identifier")
parser.add_argument('--cytomine_id_project', dest='cytomine_project', type=int,
help="The Cytomine project identifier")
parser.add_argument('--cytomine_force_download', dest='cytomine_force_download', type=bool, default=True,
help="Force download from Cytomine or not")
# Objects
parser.add_argument('--cytomine_object_term', dest='cytomine_object_term', type=int,
help="The Cytomine identifier of object term")
parser.add_argument('--cytomine_object_user', dest='cytomine_object_user', type=int,
help="The Cytomine identifier of object owner")
parser.add_argument('--cytomine_object_reviewed_only', dest='cytomine_object_reviewed_only', type=bool,
help="Whether objects have to be reviewed or not")
# ROI
parser.add_argument('--cytomine_roi_term', dest='cytomine_roi_term', type=int, default=None,
help="The Cytomine identifier of region of interest term")
parser.add_argument('--cytomine_roi_user', dest='cytomine_roi_user', type=int,
help="The Cytomine identifier of ROI owner")
parser.add_argument('--cytomine_roi_reviewed_only', dest='cytomine_roi_reviewed_only', type=bool,
help="Whether ROIs have to be reviewed or not")
# Pre-processing
parser.add_argument('--mean_radius', dest='mean_radius', type=int, required=True,
help="The mean radius of object to detect")
parser.add_argument('--pre_transformer', dest='pre_transformer',
default=None, choices=['edt', 'euclidean_distance_transform', 'density', None, 'None'],
help="Scoremap transformer (None, edt, euclidean_distance_transform, density)")
parser.add_argument('--pre_alpha', dest='pre_alpha', action='append', type=int,
help="Exponential decrease rate of distance (if EDT)")
# Subwindows
parser.add_argument('--sw_input_size', dest='sw_input_size', action='append', type=int,
help="Size of input subwindow")
parser.add_argument('--sw_output_size', dest='sw_output_size', action='append', type=int,
help="Size of output subwindow (ignored for FCRN)")
parser.add_argument('--sw_extr_mode', dest='sw_extr_mode', choices=['random', 'sliding', 'scoremap_constrained'],
help="Mode of extraction (random, scoremap_constrained)")
parser.add_argument('--sw_extr_score_thres', dest='sw_extr_score_thres', action='append', type=float,
help="Minimum threshold to be foreground in subwindows extraction"
"(if 'scoremap_constrained' mode)")
parser.add_argument('--sw_extr_ratio', dest='sw_extr_ratio', action='append', type=float,
help="Ratio of background subwindows extracted in subwindows "
"extraction (if 'scoremap_constrained' mode)")
parser.add_argument('--sw_extr_npi', dest="sw_extr_npi", action='append', type=int,
help="Number of extracted subwindows per image (if 'random' mode)")
parser.add_argument('--sw_colorspace', dest="sw_colorspace", type=str, default='RGB__rgb',
help="List of colorspace features")
# Forest
parser.add_argument('--forest_method', dest='forest_method', type=str,
action='append', choices=['ET-clf', 'ET-regr', 'RF-clf', 'RF-regr'],
help="Type of forest method")
parser.add_argument('--forest_n_estimators', dest='forest_n_estimators', action='append', type=int,
help="Number of trees in forest")
parser.add_argument('--forest_min_samples_split', dest='forest_min_samples_split', action='append', type=int,
help="Minimum number of samples for further splitting")
parser.add_argument('--forest_max_features', dest='forest_max_features', action='append',
help="Max features")
# Dataset augmentation
parser.add_argument('--augmentation', dest='augmentation', type=bool)
parser.add_argument('--aug_rotation_range', dest='rotation_range', type=float)
parser.add_argument('--aug_width_shift_range', dest='width_shift_range', type=float)
parser.add_argument('--aug_height_shift_range', dest='height_shift_range', type=float)
parser.add_argument('--aug_zoom_range', dest='zoom_range', type=float)
parser.add_argument('--aug_fill_mode', dest='fill_mode', type=str)
parser.add_argument('--aug_horizontal_flip', dest='horizontal_flip', type=bool)
parser.add_argument('--aug_vertical_flip', dest='vertical_flip', type=bool)
parser.add_argument('--aug_featurewise_center', dest='featurewise_center', type=bool)
parser.add_argument('--aug_featurewise_std_normalization', dest='featurewise_std_normalization', type=bool)
# Execution
parser.add_argument('--n_jobs', dest='n_jobs', type=int, default=1, help="Number of jobs")
parser.add_argument('--verbose', '-v', dest='verbose', default=0, help="Level of verbosity")
params, other = parser.parse_known_args(argv)
if params.cytomine_working_path is None:
params.cytomine_working_path = os.path.join(tempfile.gettempdir(), "cytomine")
make_dirs(params.cytomine_working_path)
params.pre_transformer = check_default(params.pre_transformer, None, return_list=False)
params.pre_alpha = check_default(params.pre_alpha, 5)
params.forest_method = check_default(params.forest_method, 'ET-regr')
params.forest_n_estimators = check_default(params.forest_n_estimators, 1)
params.forest_min_samples_split = check_default(params.forest_min_samples_split, 2)
params.forest_max_features = check_default(params.forest_max_features, 'sqrt')
params.forest_max_features = check_max_features(params.forest_max_features)
params.sw_input_size = check_default(params.sw_input_size, 4)
params.sw_input_size = [(s, s) for s in params.sw_input_size]
params.sw_output_size = check_default(params.sw_output_size, 1)
params.sw_output_size = [(s, s) for s in params.sw_output_size]
params.sw_extr_mode = check_default(params.sw_extr_mode, 'scoremap_constrained', return_list=False)
params.sw_extr_ratio = check_default(params.sw_extr_ratio, 0.5)
params.sw_extr_score_thres = check_default(params.sw_extr_score_thres, 0.4)
params.sw_extr_npi = check_default(params.sw_extr_npi, 100)
params.sw_colorspace = params.sw_colorspace.split(' ')
params.augmentation = check_default(params.augmentation, False, return_list=False)
if params.augmentation:
params.rotation_range = check_default(params.rotation_range, 30., return_list=False)
params.width_shift_range = check_default(params.width_shift_range, 0.3, return_list=False)
params.height_shift_range = check_default(params.height_shift_range, 0.3, return_list=False)
params.zoom_range = check_default(params.zoom_range, 0.3, return_list=False)
params.fill_mode = check_default(params.fill_mode, 'constant', return_list=False)
params.horizontal_flip = check_default(params.horizontal_flip, True, return_list=False)
params.vertical_flip = check_default(params.vertical_flip, True, return_list=False)
params.featurewise_center = check_default(params.featurewise_center, False, return_list=False)
params.featurewise_std_normalization = check_default(params.featurewise_std_normalization, False,
return_list=False)
else:
params.rotation_range = 0.
params.width_shift_range = 0.
params.height_shift_range = 0.
params.zoom_range = 0.
params.fill_mode = 'reflect'
params.horizontal_flip = False
params.vertical_flip = False
params.featurewise_center = False
params.featurewise_std_normalization = False
params = params_remove_list(params)
# Initialize logger
logger = StandardOutputLogger(params.verbose)
for key, val in sorted(vars(params).iteritems()):
logger.info("[PARAMETER] {}: {}".format(key, val))
# Initialize Cytomine client
cytomine = Cytomine(
params.cytomine_host,
params.cytomine_public_key,
params.cytomine_private_key,
working_path=params.cytomine_working_path,
base_path=params.cytomine_base_path,
verbose=(params.verbose >= Logger.DEBUG)
)
# Start job
with CytomineJob(cytomine,
params.cytomine_software,
params.cytomine_project,
parameters=vars(params_remove_none(params))) as job:
cytomine.update_job_status(job.job, status_comment="Starting...", progress=0)
cytomine.update_job_status(job.job, status_comment="Loading training set...", progress=1)
X, y = get_dataset(cytomine, params.cytomine_working_path, params.cytomine_project, params.cytomine_object_term,
params.cytomine_roi_term, params.cytomine_object_user, params.cytomine_object_reviewed_only,
params.cytomine_roi_user, params.cytomine_roi_reviewed_only, params.cytomine_force_download)
logger.d("X size: {} samples".format(len(X)))
logger.d("y size: {} samples".format(len(y)))
cytomine.update_job_status(job.job, status_comment="Training forest...", progress=5)
estimator = CellCountRandomizedTrees(logger=logger, **vars(params))
estimator.fit(np.asarray(X), np.asarray(y))
cytomine.update_job_status(job.job, status_comment="Saving (best) model", progress=95)
model_path = os.path.join(params.cytomine_working_path, "models", str(params.cytomine_software))
model_file = os.path.join(model_path, "{}.pkl".format(job.job.id))
make_dirs(model_path)
estimator.save(model_file)
cytomine.update_job_status(job.job, status_comment="Finished.", progress=100)
def train(argv):
parser = ArgumentParser(prog="CNN Object Counter Model Builder")
# Cytomine
parser.add_argument('--cytomine_host',
dest='cytomine_host',
default='demo.cytomine.be',
help="The Cytomine host")
parser.add_argument('--cytomine_public_key',
dest='cytomine_public_key',
help="The Cytomine public key")
parser.add_argument('--cytomine_private_key',
dest='cytomine_private_key',
help="The Cytomine private key")
parser.add_argument('--cytomine_base_path',
dest='cytomine_base_path',
default='/api/',
help="The Cytomine base path")
parser.add_argument('--cytomine_working_path',
dest='cytomine_working_path',
default=None,
help="The working directory (eg: /tmp)")
parser.add_argument('--cytomine_id_software',
dest='cytomine_software',
type=int,
help="The Cytomine software identifier")
parser.add_argument('--cytomine_id_project',
dest='cytomine_project',
type=int,
help="The Cytomine project identifier")
parser.add_argument('--cytomine_force_download',
dest='cytomine_force_download',
type=bool,
default=True,
help="Force download from Cytomine or not")
# Objects
parser.add_argument('--cytomine_object_term',
dest='cytomine_object_term',
type=int,
help="The Cytomine identifier of object term")
parser.add_argument('--cytomine_object_user',
dest='cytomine_object_user',
type=int,
help="The Cytomine identifier of object owner")
parser.add_argument('--cytomine_object_reviewed_only',
dest='cytomine_object_reviewed_only',
type=bool,
help="Whether objects have to be reviewed or not")
# ROI
parser.add_argument(
'--cytomine_roi_term',
dest='cytomine_roi_term',
type=int,
default=None,
help="The Cytomine identifier of region of interest term")
parser.add_argument('--cytomine_roi_user',
dest='cytomine_roi_user',
type=int,
help="The Cytomine identifier of ROI owner")
parser.add_argument('--cytomine_roi_reviewed_only',
dest='cytomine_roi_reviewed_only',
type=bool,
help="Whether ROIs have to be reviewed or not")
# Pre-processing
parser.add_argument('--mean_radius',
dest='mean_radius',
type=int,
required=True,
help="The mean radius of object to detect")
parser.add_argument(
'--pre_transformer',
dest='pre_transformer',
default=None,
choices=[
'edt', 'euclidean_distance_transform', 'density', None, 'None'
],
help=
"Scoremap transformer (None, edt, euclidean_distance_transform, density)"
)
parser.add_argument('--pre_alpha',
dest='pre_alpha',
action='append',
type=int,
help="Exponential decrease rate of distance (if EDT)")
# Subwindows for training
parser.add_argument('--sw_input_size',
dest='sw_input_size',
action='append',
type=int,
help="Size of input subwindow")
parser.add_argument('--sw_colorspace',
dest="sw_colorspace",
type=str,
default='RGB__rgb',
help="List of colorspace features")
parser.add_argument('--sw_extr_npi',
dest="sw_extr_npi",
action='append',
type=int,
help="Number of extracted subwindows per image "
"(if 'random' mode)")
# CNN
parser.add_argument('--cnn_architecture',
'--architecture',
dest='architecture',
type=str,
choices=['FCRN-A', 'FCRN-B', 'FCRN-test'])
parser.add_argument('--cnn_initializer',
'--initializer',
dest='initializer',
action='append',
type=str)
parser.add_argument('--cnn_regularizer',
'--regularizer',
dest='regularizer',
action='append',
type=str)
parser.add_argument('--cnn_batch_normalization',
'--batch_normalization',
dest='batch_normalization',
action='append',
type=bool)
parser.add_argument('--cnn_learning_rate',
'--learning_rate',
'--lr',
dest='learning_rate',
action='append',
type=float)
parser.add_argument('--cnn_momentum',
'--momentum',
dest='momentum',
action='append',
type=float)
parser.add_argument('--cnn_nesterov',
'--nesterov',
dest='nesterov',
action='append',
type=bool)
parser.add_argument('--cnn_decay',
'--decay',
dest='decay',
action='append',
type=float)
parser.add_argument('--cnn_epochs',
'--epochs',
dest='epochs',
action='append',
type=int)
parser.add_argument('--cnn_batch_size',
'--batch_size',
dest='batch_size',
action='append',
type=int)
# Dataset augmentation
parser.add_argument('--augmentation', dest='augmentation', type=bool)
parser.add_argument('--aug_rotation_range',
dest='rotation_range',
type=float)
parser.add_argument('--aug_width_shift_range',
dest='width_shift_range',
type=float)
parser.add_argument('--aug_height_shift_range',
dest='height_shift_range',
type=float)
parser.add_argument('--aug_zoom_range', dest='zoom_range', type=float)
parser.add_argument('--aug_fill_mode', dest='fill_mode', type=str)
parser.add_argument('--aug_horizontal_flip',
dest='horizontal_flip',
type=bool)
parser.add_argument('--aug_vertical_flip', dest='vertical_flip', type=bool)
parser.add_argument('--aug_featurewise_center',
dest='featurewise_center',
type=bool)
parser.add_argument('--aug_featurewise_std_normalization',
dest='featurewise_std_normalization',
type=bool)
# Execution
parser.add_argument('--n_jobs',
dest='n_jobs',
type=int,
default=1,
help="Number of jobs")
parser.add_argument('--verbose',
'-v',
dest='verbose',
default=0,
action='count',
help="Level of verbosity")
params, other = parser.parse_known_args(argv)
if params.working_path is None:
params.working_path = os.path.join(tempfile.gettempdir(), "cytomine")
make_dirs(params.working_path)
params.pre_transformer = check_default(params.pre_transformer,
None,
return_list=False)
params.pre_alpha = check_default(params.pre_alpha, 5)
params.architecture = check_default(params.architecture,
'FCRN-A',
return_list=False)
params.initializer = check_default(params.initializer, 'orthogonal')
params.regularizer = check_default(params.regularizer, None)
params.batch_normalization = check_default(params.batch_normalization,
True)
params.learning_rate = check_default(params.learning_rate, 0.02)
params.momentum = check_default(params.momentum, 0.9)
params.nesterov = check_default(params.nesterov, True)
params.decay = check_default(params.decay, 0.)
params.epochs = check_default(params.epochs, 3)
params.batch_size = check_default(params.batch_size, 2)
d = 8 if params.architecture == 'FCRN-A' else 4
params.sw_input_size = check_default(params.sw_input_size, 4)
params.sw_input_size = [((s // d * d + d), (s // d * d + d))
for s in params.sw_input_size]
params.sw_output_size = params.sw_input_size
params.sw_size = params.sw_input_size
params.sw_colorspace = params.sw_colorspace.split(' ')
params.sw_extr_npi = check_default(params.sw_extr_npi, 100)
params.sw_extr_mode = ['random']
params.augmentation = check_default(params.augmentation,
True,
return_list=False)
if params.augmentation:
params.rotation_range = check_default(params.rotation_range,
30.,
return_list=False)
params.width_shift_range = check_default(params.width_shift_range,
0.3,
return_list=False)
params.height_shift_range = check_default(params.height_shift_range,
0.3,
return_list=False)
params.zoom_range = check_default(params.zoom_range,
0.3,
return_list=False)
params.fill_mode = check_default(params.fill_mode,
'constant',
return_list=False)
params.horizontal_flip = check_default(params.horizontal_flip,
True,
return_list=False)
params.vertical_flip = check_default(params.vertical_flip,
True,
return_list=False)
params.featurewise_center = check_default(params.featurewise_center,
False,
return_list=False)
params.featurewise_std_normalization = check_default(
params.featurewise_std_normalization, False, return_list=False)
else:
params.rotation_range = 0.
params.width_shift_range = 0.
params.height_shift_range = 0.
params.zoom_range = 0.
params.fill_mode = 'reflect'
params.horizontal_flip = False
params.vertical_flip = False
params.featurewise_center = False
params.featurewise_std_normalization = False
params = params_remove_list(params)
# Callbacks
checkpoint_callback = ModelCheckpoint(params.model_file,
monitor='loss',
save_best_only=True)
lr_callback = LearningRateScheduler(lr_scheduler)
callbacks = [checkpoint_callback, lr_callback]
# Initialize logger
logger = StandardOutputLogger(params.verbose)
for key, val in sorted(vars(params).iteritems()):
logger.info("[PARAMETER] {}: {}".format(key, val))
# Initialize Cytomine client
cytomine = Cytomine(params.cytomine_host,
params.cytomine_public_key,
params.cytomine_private_key,
working_path=params.cytomine_working_path,
base_path=params.cytomine_base_path,
verbose=(params.verbose >= Logger.DEBUG))
# Start job
with CytomineJob(cytomine,
params.cytomine_software,
params.cytomine_project,
parameters=vars(params)) as job:
cytomine.update_job_status(job.job,
status_comment="Starting...",
progress=0)
cytomine.update_job_status(job.job,
status_comment="Loading training set...",
progress=1)
X, y = get_dataset(
cytomine, params.working_path, params.cytomine_project,
params.cytomine_object_term, params.cytomine_roi_term,
params.cytomine_object_user, params.cytomine_object_reviewed_only,
params.cytomine_roi_user, params.cytomine_roi_reviewed_only,
params.cytomine_force_download)
logger.d("X size: {} samples".format(len(X)))
logger.d("y size: {} samples".format(len(y)))
cytomine.update_job_status(job.job,
status_comment="Training FCRN...",
progress=5)
estimator = FCRN(FCRN.build_fcrn, callbacks, **vars(params))
estimator.fit(np.asarray(X), np.asarray(y))
cytomine.update_job_status(job.job,
status_comment="Saving (best) model",
progress=95)
model_path = os.path.join(params.cytomine_working_path, "models",
str(params.cytomine_software))
model_file = os.path.join(model_path, "{}.h5".format(job.job.id))
make_dirs(model_path)
estimator.save(model_file)
cytomine.update_job_status(job.job,
status_comment="Finished.",
progress=100)