def testSSLWorkflowBuilder(self):
segmenter = DumbSegmenter()
builder = SSLWorkflowBuilder()
builder.set_n_jobs(5)
builder.set_tile_size(512, 768)
builder.set_overlap(3)
builder.set_distance_tolerance(7)
builder.set_background_class(5)
builder.set_logger(StandardOutputLogger(Logger.DEBUG))
with self.assertRaises(MissingComponentException):
builder.get()
builder.set_segmenter(segmenter)
builder.set_default_tile_builder()
workflow = builder.get()
self.assertIsInstance(workflow, SSLWorkflow)
self.assertEqual(workflow._n_jobs, 5)
self.assertEqual(workflow._tile_overlap, 3)
self.assertEqual(workflow._tile_max_height, 512)
self.assertEqual(workflow._tile_max_width, 768)
self.assertIsInstance(workflow._tile_builder, DefaultTileBuilder)
self.assertIsInstance(workflow.logger, StandardOutputLogger)
self.assertEqual(workflow._locator._background, 5)
def __init__(self,
build_fn=None,
logger=StandardOutputLogger(Logger.INFO),
**sk_params):
super(CellCountRandomizedTrees, self).__init__(build_fn, logger,
**sk_params)
self.__forest = None
def __init__(self,
build_fn=None,
logger=StandardOutputLogger(Logger.INFO),
**sk_params):
self.build_fn = build_fn
self.sk_params = sk_params
self.logger = logger
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 main(argv):
with CytomineJob.from_cli(argv) as job:
if not os.path.exists(job.parameters.working_path):
os.makedirs(job.parameters.working_path)
# create workflow component
logger = StandardOutputLogger(Logger.INFO)
random_state = check_random_state(int(job.parameters.rseed))
tile_builder = CytomineTileBuilder(
working_path=job.parameters.working_path)
segmenter = DemoSegmenter(job.parameters.threshold)
area_rule = ValidAreaRule(job.parameters.min_area)
classifier = PyxitClassifierAdapter.build_from_pickle(
job.parameters.pyxit_model_path,
tile_builder,
logger,
random_state=random_state,
n_jobs=job.parameters.n_jobs,
working_path=job.parameters.working_path)
builder = SLDCWorkflowBuilder()
builder.set_n_jobs(job.parameters.n_jobs)
builder.set_logger(logger)
builder.set_overlap(job.parameters.sldc_tile_overlap)
builder.set_tile_size(job.parameters.sldc_tile_width,
job.parameters.sldc_tile_height)
builder.set_tile_builder(tile_builder)
builder.set_segmenter(segmenter)
builder.add_classifier(area_rule,
classifier,
dispatching_label="valid")
workflow = builder.get()
slide = CytomineSlide(job.parameters.cytomine_image_id)
results = workflow.process(slide)
# Upload results
for polygon, label, proba, dispatch in results:
if label is not None:
# if image is a window, the polygon must be translated
if isinstance(slide, ImageWindow):
polygon = translate(polygon, slide.abs_offset_x,
slide.abs_offset_y)
# upload the annotation
polygon = affine_transform(
polygon, [1, 0, 0, -1, 0, slide.image_instance.height])
annotation = Annotation(
location=polygon.wkt,
id_image=slide.image_instance.id).save()
AlgoAnnotationTerm(id_annotation=annotation.id,
id_term=label,
rate=float(proba)).save()
def testSLDCWorkflowWithOneShotDispatcher(self):
# pre build components
segmenter = DumbSegmenter()
dispatcher = DumbDispatcher()
classifier = DumbClassifier()
rule = DumbRule()
logger = StandardOutputLogger(Logger.DEBUG)
builder = SLDCWorkflowBuilder()
builder.set_tile_size(512, 768)
builder.set_overlap(3)
builder.set_distance_tolerance(5)
builder.set_n_jobs(5)
builder.set_logger(logger)
builder.set_parallel_dc(True)
builder.set_tile_builder(None)
with self.assertRaises(MissingComponentException):
builder.get()
builder.set_segmenter(segmenter)
with self.assertRaises(MissingComponentException):
builder.get()
builder.set_default_tile_builder()
with self.assertRaises(MissingComponentException):
builder.get()
builder.set_one_shot_dispatcher(dispatcher, {"default": classifier})
with self.assertRaises(InvalidBuildingException):
builder.add_classifier(rule, classifier, dispatching_label="default")
with self.assertRaises(InvalidBuildingException):
builder.add_catchall_classifier(classifier, dispatching_label="default")
workflow = builder.get()
self.assertIsInstance(workflow, SLDCWorkflow)
self.assertEqual(workflow._segmenter, segmenter)
self.assertEqual(workflow._n_jobs, 5)
self.assertEqual(workflow._tile_overlap, 3)
self.assertEqual(workflow._tile_max_height, 512)
self.assertEqual(workflow._tile_max_width, 768)
self.assertEqual(workflow.logger, logger)
self.assertIsInstance(workflow._tile_builder, DefaultTileBuilder)
self.assertEqual(workflow._dispatch_classifier._dispatcher, dispatcher)
self.assertEqual(len(workflow._dispatch_classifier._classifiers), 1)
self.assertEqual(workflow._dispatch_classifier._classifiers[0], classifier)
def __init__(self, colorspaces, dtype=np.float16, logger=StandardOutputLogger(Logger.INFO)):
if colorspaces is None:
raise ValueError("Colorspace cannot be None")
self.logger = logger
self.dtype = dtype
self.features = None
self.colorspaces = list()
colorspaces_dict = split_list_to_dict(colorspaces, splitter='__')
for colorspace, features in colorspaces_dict.items():
if colorspace in ('rgb', 'RGB', 'color'):
self.colorspaces.append(ColorspaceRGB(features))
elif colorspace in ('gray', 'grayscale', 'L'):
self.colorspaces.append(ColorspaceGrayscale(features))
def __init__(self, default_estimator, param_grid, cv, me, untrainable_param_grid=None,
scoring_rank='f1_score', refit=False, iid=True, n_jobs=1, pre_dispatch='2*n_jobs',
logger=StandardOutputLogger(Logger.INFO)):
self.default_estimator = default_estimator
self.param_grid = param_grid
self.untrainable_param_grid = untrainable_param_grid
self.cv = cv
self.me = me
self.scoring_rank = scoring_rank
self.n_jobs = n_jobs
self.pre_dispatch = pre_dispatch
self.logger = logger
self.refit = refit
self.iid = iid
_check_param_grid(param_grid)
_check_param_grid(untrainable_param_grid)
def testMerge(self):
timing1 = WorkflowTiming()
timing2 = WorkflowTiming()
timing1.start("root1")
timing1.end("root1")
timing1.start("root")
timing1.end("root")
timing1.start("root1.adj")
timing1.end("root1.adj")
timing2.start("root2")
timing2.end("root2")
timing2.start("root")
timing2.end("root")
timing2.start("root1.adj")
timing2.end("root1.adj")
# merge without update of initial objects
merged = merge_timings(timing1, timing2)
self.assertEqual(len(merged["root1"]), 1)
self.assertEqual(len(merged["root2"]), 1)
self.assertEqual(len(merged["root"]), 2)
self.assertEqual(len(merged["root1.adj"]), 2)
# merge with update of timing1
timing1.merge(timing2)
self.assertEqual(len(timing1["root1"]), 1)
self.assertEqual(len(timing1["root2"]), 1)
self.assertEqual(len(timing1["root"]), 2)
self.assertEqual(len(timing1["root1.adj"]), 2)
with self.assertRaises(TypeError):
timing1.merge(StandardOutputLogger(level=Logger.DEBUG))
timing1.merge(timing1)
self.assertEqual(len(timing1["root1"]), 1)
self.assertEqual(len(timing1["root2"]), 1)
self.assertEqual(len(timing1["root"]), 2)
self.assertEqual(len(timing1["root1.adj"]), 2)
def main():
""" (4) build the workflow """
logger = StandardOutputLogger(Logger.INFO)
builder = SLDCWorkflowBuilder()
builder.set_n_jobs(4)
builder.set_logger(logger)
builder.set_default_tile_builder()
builder.set_tile_size(256, 256)
builder.set_segmenter(BasicSegmenter())
builder.add_classifier(ShapeRule(ShapeRule.CIRCLE), ColorClassifier(), "circle")
builder.add_classifier(ShapeRule(ShapeRule.SQUARE), ColorClassifier(), "square")
workflow = builder.get()
""" (5) build a (fake) image """
np_image = np.zeros([2000, 2000], dtype=np.uint8)
np_image = draw_circle(np_image, 100, (500, 1500), 255)
np_image = draw_circle(np_image, 100, (1500, 600), 127)
np_image = draw_square(np_image, 200, (500, 500), 255)
np_image = draw_square(np_image, 200, (1500, 1500), 127)
np_image = draw_square(np_image, 300, (1000, 1000), 255)
image = NumpyImage(np_image)
""" (6) process the image """
results = workflow.process(image)
""" (7) report execution times """
report_timing(results.timing, logger)
""" (8) explore the results """
for i, object_info in enumerate(results):
print(
"Object {}:".format(i + 1) + os.linesep +
"> area : {}".format(object_info.polygon.area) + os.linesep +
"> label : '{}'".format(object_info.label) + os.linesep +
"> proba : {}".format(object_info.proba) + os.linesep +
"> dispatch: '{}'".format(object_info.dispatch)
)
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 testWorkflowChainBuilder(self):
segmenter = DumbSegmenter()
dispatcher = DumbDispatcher()
classifier = DumbClassifier()
builder = SLDCWorkflowBuilder()
builder.set_segmenter(segmenter)
builder.set_default_tile_builder()
builder.set_one_shot_dispatcher(dispatcher, {"default": classifier})
workflow1 = builder.get()
builder2 = SSLWorkflowBuilder()
builder2.set_segmenter(segmenter)
builder2.set_default_tile_builder()
workflow2 = builder2.get()
_filter = DefaultFilter()
logger = StandardOutputLogger(Logger.DEBUG)
chain_builder = WorkflowChainBuilder()
chain_builder.set_logger(logger)
with self.assertRaises(MissingComponentException):
chain_builder.get()
chain_builder.set_first_workflow(workflow1, label="first")
chain_builder.add_executor(workflow2, label="second", filter=_filter, n_jobs=2, logger=logger)
chain = chain_builder.get()
self.assertIsInstance(chain, WorkflowChain)
self.assertEqual(chain.logger, logger)
self.assertEqual(chain._first_workflow, workflow1)
self.assertEqual(len(chain._executors), 1)
self.assertEqual(chain._executors[0]._workflow, workflow2)
self.assertEqual(len(chain._labels), 2)
self.assertEqual(tuple(chain._labels), ("first", "second"))
self.assertEqual(len(chain._filters), 1)
self.assertEqual(chain._filters[0], _filter)
def main(argv):
with CytomineJob.from_cli(argv) as cj:
# use only images from the current project
cj.job.update(progress=1, statusComment="Preparing execution")
# extract images to process
if cj.parameters.cytomine_zoom_level > 0 and (
cj.parameters.cytomine_tile_size != 256
or cj.parameters.cytomine_tile_overlap != 0):
raise ValueError(
"when using zoom_level > 0, tile size should be 256 "
"(given {}) and overlap should be 0 (given {})".format(
cj.parameters.cytomine_tile_size,
cj.parameters.cytomine_tile_overlap))
cj.job.update(
progress=1,
statusComment="Preparing execution (creating folders,...).")
# working path
root_path = str(Path.home())
working_path = os.path.join(root_path, "images")
os.makedirs(working_path, exist_ok=True)
# load training information
cj.job.update(progress=5,
statusComment="Extract properties from training job.")
train_job = Job().fetch(cj.parameters.cytomine_id_job)
properties = PropertyCollection(train_job).fetch().as_dict()
binary = str2bool(properties["binary"].value)
classes = parse_domain_list(properties["classes"].value)
cj.job.update(progress=10, statusComment="Download the model file.")
attached_files = AttachedFileCollection(train_job).fetch()
model_file = attached_files.find_by_attribute("filename",
"model.joblib")
model_filepath = os.path.join(root_path, "model.joblib")
model_file.download(model_filepath, override=True)
pyxit = joblib.load(model_filepath)
# set n_jobs
pyxit.base_estimator.n_jobs = cj.parameters.n_jobs
pyxit.n_jobs = cj.parameters.n_jobs
cj.job.update(progress=45, statusComment="Build workflow.")
builder = SSLWorkflowBuilder()
builder.set_tile_size(cj.parameters.cytomine_tile_size,
cj.parameters.cytomine_tile_size)
builder.set_overlap(cj.parameters.cytomine_tile_overlap)
builder.set_tile_builder(
CytomineTileBuilder(working_path, n_jobs=cj.parameters.n_jobs))
builder.set_logger(StandardOutputLogger(level=Logger.INFO))
builder.set_n_jobs(1)
builder.set_background_class(0)
# value 0 will prevent merging but still requires to run the merging check
# procedure (inefficient)
builder.set_distance_tolerance(2 if cj.parameters.union_enabled else 0)
builder.set_segmenter(
ExtraTreesSegmenter(
pyxit=pyxit,
classes=classes,
prediction_step=cj.parameters.pyxit_prediction_step,
background=0,
min_std=cj.parameters.tile_filter_min_stddev,
max_mean=cj.parameters.tile_filter_max_mean))
workflow = builder.get()
area_checker = AnnotationAreaChecker(
min_area=cj.parameters.min_annotation_area,
max_area=cj.parameters.max_annotation_area)
def get_term(label):
if binary:
if "cytomine_id_predict_term" not in cj.parameters:
return []
else:
return [int(cj.parameters.cytomine_id_predict_term)]
# multi-class
return [label]
zones = extract_images_or_rois(cj.parameters)
for zone in cj.monitor(zones,
start=50,
end=90,
period=0.05,
prefix="Segmenting images/ROIs"):
results = workflow.process(zone)
annotations = AnnotationCollection()
for obj in results:
if not area_checker.check(obj.polygon):
continue
polygon = obj.polygon
if isinstance(zone, ImageWindow):
polygon = affine_transform(
polygon,
[1, 0, 0, 1, zone.abs_offset_x, zone.abs_offset_y])
polygon = change_referential(polygon, zone.base_image.height)
if cj.parameters.cytomine_zoom_level > 0:
zoom_mult = (2**cj.parameters.cytomine_zoom_level)
polygon = affine_transform(
polygon, [zoom_mult, 0, 0, zoom_mult, 0, 0])
annotations.append(
Annotation(location=polygon.wkt,
id_terms=get_term(obj.label),
id_project=cj.project.id,
id_image=zone.base_image.image_instance.id))
annotations.save()
cj.job.update(status=Job.TERMINATED,
status_comment="Finish",
progress=100)
def flip(m, axis):
indexer = [slice(None)] * m.ndim
indexer[axis] = slice(None, None, -1)
return m[tuple(indexer)]
filename = sys.argv[1]
if not os.path.exists(filename):
raise IOError("File " + filename + " does not exist !")
img = cv2.imread(filename, cv2.IMREAD_COLOR)
img = img[250:,250:,...]
colorspaces = ['RGB__rgb', 'RGB__luv', 'RGB__hsv', 'L__normalized',
'L__sobel1', 'L__sobel_gradmagn', 'L__sobel2']
fe = FeaturesExtractor(colorspaces, logger=StandardOutputLogger(Logger.DEBUG))
fe.build(img)
titles = ['Red', 'Green', 'Blue', 'L*', 'u*', 'v*', 'Hue', 'Saturation', 'Value',
'Eq. grayscale', '1st-Sobel x', '1st-Sobel y', 'Sobel grad. magn.',
'2st-Sobel x', '2st-Sobel y']
n_rows = 4
n_cols = 4
fig = plt.figure()
a = fig.add_subplot(n_rows, n_cols, 1)
plt.imshow(flip(img, 2))
a.set_title('Original RGB image')
a.set_axis_off()
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 predict(argv):
parser = ArgumentParser(prog="Extra-Trees 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=str, action='append', default=[])
parser.add_argument('--image', dest='image', type=str, action='append', default=[])
# Execution
parser.add_argument('--n_jobs', dest='n_jobs', type=int, default=1, help="Number of jobs")
parser.add_argument('--verbose', '-v', dest='verbose', type=int, default=0, help="Level of verbosity")
parser.add_argument('--model_id_job', dest='model_id_job', type=str, default=None, help="Model job ID")
parser.add_argument('--model_file', dest="model_file", type=str, default=None, help="Model file")
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.model_id_job = str2int(params.model_id_job)
params.image = [str2int(i) for i in params.image]
params.annotation = [str2int(i) for i in params.annotation]
# Initialize logger
logger = StandardOutputLogger(params.verbose)
for key, val in sorted(vars(params).iteritems()):
logger.info("[PARAMETER] {}: {}".format(key, val))
# Start job
with CytomineJob(params.cytomine_host,
params.cytomine_public_key,
params.cytomine_private_key,
params.cytomine_software,
params.cytomine_project,
parameters=vars(params),
working_path=params.cytomine_working_path,
base_path=params.cytomine_base_path,
verbose=(params.verbose >= Logger.DEBUG)) as job:
cytomine = job
cytomine.update_job_status(job.job, status_comment="Starting...", progress=0)
cytomine.update_job_status(job.job, status_comment="Loading model...", progress=1)
logger.i("Loading model...")
if params.model_file:
model_file = params.model_file
else:
model_job = cytomine.get_job(params.model_id_job)
model_file = os.path.join(params.cytomine_working_path, "models", str(model_job.software),
"{}.pkl".format(model_job.id))
with open(model_file, 'rb') as f:
estimator = pickle.load(f)
predict_params = vars(params).copy()
predict_params.pop("image", None)
predict_params.pop("annotation", None)
estimator.set_params(**predict_params)
cytomine.update_job_status(job.job, status_comment="Dumping annotations/images to predict...", progress=3)
logger.i("Dumping annotations/images to predict...")
if params.annotation[0] is not None:
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[0] is not None:
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,
max_size=True)
X = image_instances
else:
X = []
logger.d("X size: {} samples".format(len(X)))
for i, x in enumerate(X):
logger.i("Predicting ID {}...".format(x.id))
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])
y = estimator.postprocessing([y], **estimator.filter_sk_params(estimator.postprocessing))
logger.i("Uploading annotations...")
cytomine.update_job_status(job.job, status_comment="Uploading annotations...")
upload_annotations(cytomine, x, y, term=params.cytomine_object_term)
logger.i("Finished.")
cytomine.update_job_status(job.job, status_comment="Finished.", progress=100)
def create_from_parameters(cls, parameters, logger=StandardOutputLogger(Logger.INFO)):
kwargs = parameters if isinstance(parameters, dict) else vars(parameters)
kwargs.update({'logger': logger})
return cls(**kwargs)
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=str, 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=str,
help="The Cytomine identifier of object owner")
parser.add_argument('--cytomine_object_reviewed_only', dest='cytomine_object_reviewed_only', type=str,
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=str,
help="The Cytomine identifier of ROI owner")
parser.add_argument('--cytomine_roi_reviewed_only', dest='cytomine_roi_reviewed_only', type=str,
help="Whether ROIs have to be reviewed or not")
# Pre-processing
parser.add_argument('--pre_transformer', dest='pre_transformer',
default='density', 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', type=int, default=3,
help="Exponential decrease rate of distance (if EDT)")
# Subwindows for training
parser.add_argument('--sw_input_size', dest='sw_input_size', type=int, default=128,
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", type=int, default=100,
help="Number of extracted subwindows per image (if 'random' mode)")
# CNN
parser.add_argument('--cnn_architecture', '--architecture', dest='cnn_architecture',
type=str, choices=['FCRN-A', 'FCRN-B'], default='FCRN-A')
parser.add_argument('--cnn_initializer', '--initializer', dest='cnn_initializer', type=str, default='orthogonal')
parser.add_argument('--cnn_batch_normalization', '--batch_normalization', dest='cnn_batch_normalization', type=str,
default=True)
parser.add_argument('--cnn_learning_rate', '--learning_rate', '--lr', dest='cnn_learning_rate', type=float,
default=0.01)
parser.add_argument('--cnn_momentum', '--momentum', dest='cnn_momentum', type=float, default=0.9)
parser.add_argument('--cnn_nesterov', '--nesterov', dest='cnn_nesterov', type=str, default=True)
parser.add_argument('--cnn_decay', '--decay', dest='cnn_decay', type=float, default=0.0)
parser.add_argument('--cnn_epochs', '--epochs', dest='cnn_epochs', type=int, default=24)
parser.add_argument('--cnn_batch_size', '--batch_size', dest='cnn_batch_size', type=int, default=16)
# Dataset augmentation
parser.add_argument('--augmentation', dest='augmentation', type=str, default=True)
parser.add_argument('--aug_rotation_range', dest='rotation_range', type=float, default=0.)
parser.add_argument('--aug_width_shift_range', dest='width_shift_range', type=float, default=0.)
parser.add_argument('--aug_height_shift_range', dest='height_shift_range', type=float, default=0.)
parser.add_argument('--aug_zoom_range', dest='zoom_range', type=float, default=0.)
parser.add_argument('--aug_fill_mode', dest='fill_mode', type=str, default="reflect")
parser.add_argument('--aug_horizontal_flip', dest='horizontal_flip', type=bool, default=False)
parser.add_argument('--aug_vertical_flip', dest='vertical_flip', type=bool, default=False)
parser.add_argument('--aug_featurewise_center', dest='featurewise_center', type=bool, default=False)
parser.add_argument('--aug_featurewise_std_normalization', dest='featurewise_std_normalization', type=bool,
default=False)
# Execution
parser.add_argument('--n_jobs', dest='n_jobs', type=int, default=1, help="Number of jobs")
parser.add_argument('--verbose', '-v', dest='verbose', type=int, 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.cytomine_force_download = str2bool(params.cytomine_force_download)
params.cytomine_object_reviewed_only = str2bool(params.cytomine_object_reviewed_only)
params.cytomine_roi_reviewed_only = str2bool(params.cytomine_roi_reviewed_only)
params.cnn_batch_normalization = str2bool(params.cnn_batch_normalization)
params.cnn_nesterov = str2bool(params.cnn_nesterov)
params.augmentation = str2bool(params.augmentation)
d = 8. if params.cnn_architecture == 'FCRN-A' else 4.
params.sw_size = (int(np.ceil(params.sw_input_size / d) * d), int(np.ceil(params.sw_input_size / d) * d))
params.sw_input_size = params.sw_size
params.sw_output_size = params.sw_size
params.sw_colorspace = params.sw_colorspace.split(' ')
params.sw_extr_mode = 'random'
params.cnn_regularizer = None
params.mean_radius = 2
params.k_factor = 100
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)
# Initialize logger
logger = StandardOutputLogger(params.verbose)
for key, val in sorted(vars(params).iteritems()):
logger.info("[PARAMETER] {}: {}".format(key, val))
# Start job
with CytomineJob(params.cytomine_host,
params.cytomine_public_key,
params.cytomine_private_key,
params.cytomine_software,
params.cytomine_project,
parameters=vars(params),
working_path=params.cytomine_working_path,
base_path=params.cytomine_base_path,
verbose=(params.verbose >= Logger.DEBUG)) as job:
cytomine = 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)
logger.i("Loading training set...")
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)))
# Rename parameters
params.architecture = params.cnn_architecture
params.initializer = params.cnn_initializer
params.regularizer = params.cnn_regularizer
params.batch_normalization = params.cnn_batch_normalization
params.learning_rate = params.cnn_learning_rate
params.momentum = params.cnn_momentum
params.nesterov = params.cnn_nesterov
params.decay = params.cnn_decay
params.epochs = params.cnn_epochs
params.batch_size = params.cnn_batch_size
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)
# Callbacks
# checkpoint_callback = ModelCheckpoint(model_file, monitor='loss', save_best_only=True)
lr_callback = LearningRateScheduler(lr_scheduler)
callbacks = [lr_callback]
logger.i("Training FCRN...")
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))
logger.i("Saving model...")
cytomine.update_job_status(job.job, status_comment="Saving (best) model", progress=95)
estimator.save(model_file)
logger.i("Finished.")
cytomine.update_job_status(job.job, status_comment="Finished.", progress=100)