def testSquareIncluded(self):
# generate the image to be processed
w, h = 2000, 2000
image = np.zeros((h, w), dtype=np.uint8)
# locations of the 9 multi-squares
positions = [(w // 7, h // 7), (3 * w // 7, h // 7),
(5 * w // 7, h // 7), (w // 7, 3 * h // 7),
(3 * w // 7, 3 * h // 7), (5 * w // 7, 3 * h // 7),
(w // 7, 5 * h // 7), (3 * w // 7, 5 * h // 7),
(5 * w // 7, 5 * h // 7)]
for position in positions:
image = draw_multisquare(image, position, w // 7, color_in=127)
# Build workflow
builder = SLDCWorkflowBuilder()
# Build workflow 1
builder.set_segmenter(BigShapeSegmenter())
builder.add_catchall_classifier(DumbClassifier())
builder.set_tile_size(512, 512)
workflow1 = builder.get()
# Build workflow 2
builder.set_segmenter(SmallSquareSegmenter())
builder.add_catchall_classifier(DumbClassifier())
workflow2 = builder.get()
# Build chaining
chain_builder = WorkflowChainBuilder()
chain_builder.set_first_workflow(workflow1, label="big_squares")
chain_builder.add_executor(workflow2, label="small_squares")
chain = chain_builder.get()
# Launch
chain_info = chain.process(NumpyImage(image))
# check results
big_area = (w // 7)**2
small_area = (w / 35)**2
info1 = chain_info["big_squares"]
self.assertEqual(9, len(info1))
for object_info in info1:
self.assertTrue(
relative_error(object_info.polygon.area, big_area) < 0.005)
self.assertEqual("catchall", object_info.dispatch)
self.assertEqual(1, object_info.label)
self.assertAlmostEqual(1.0, object_info.proba)
info2 = chain_info["small_squares"]
self.assertEqual(36, len(info2))
for object_info in info2:
self.assertTrue(
relative_error(object_info.polygon.area, small_area) < 0.005)
self.assertEqual("catchall", object_info.dispatch)
self.assertEqual(1, object_info.label)
self.assertAlmostEqual(1.0, object_info.proba)
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 testSquareAndCircleIncluded(self):
w, h = 2000, 2000
image = np.zeros((h, w), dtype=np.uint8)
# locations of the 9 multi-squares
shapes = [("c", (w // 7, h // 7)), ("s", (3 * w // 7, h // 7)),
("s", (5 * w // 7, h // 7)), ("s", (w // 7, 3 * h // 7)),
("c", (3 * w // 7, 3 * h // 7)),
("s", (5 * w // 7, 3 * h // 7)), ("c", (w // 7, 5 * h // 7)),
("s", (3 * w // 7, 5 * h // 7)),
("c", (5 * w // 7, 5 * h // 7))]
for shape, position in shapes:
if shape == "c":
image = draw_multicircle(image, position, w // 7, color_in=87)
elif shape == "s":
image = draw_multisquare(image, position, w // 7, color_in=187)
# Build workflows
# 1st: find big shapes and dispatch them as circle or square
# 2nd: find small circles in found circle shapes
# 3rd: find small squares in found square shape
builder = SLDCWorkflowBuilder()
builder.set_segmenter(BigShapeSegmenter())
builder.add_classifier(CircleDispatch(),
DumbClassifier(),
dispatching_label="circle")
builder.add_classifier(SquareDispatch(),
DumbClassifier(),
dispatching_label="square")
builder.set_tile_size(512, 512)
workflow1 = builder.get()
builder.set_segmenter(SmallCircleSegmenter())
builder.add_catchall_classifier(DumbClassifier())
workflow2 = builder.get()
builder.set_segmenter(SmallSquareSegmenter())
builder.add_catchall_classifier(DumbClassifier())
workflow3 = builder.get()
# Build chain
chain_builder = WorkflowChainBuilder()
chain_builder.set_first_workflow(workflow1)
chain_builder.add_executor(workflow2, filter=CircleShapeFilter())
chain_builder.add_executor(workflow3,
filter=SquareShapeFilter(),
n_jobs=2)
chain = chain_builder.get()
chain_info = chain.process(NumpyImage(image))
info1 = chain_info[0]
self.assertEqual(9, len(info1))
self.assertEqual(4,
len([d for d in info1.dispatches if d == "circle"]))
self.assertEqual(5,
len([d for d in info1.dispatches if d == "square"]))
info2 = chain_info[1]
self.assertEqual(16, len(info2))
info3 = chain_info[2]
self.assertEqual(20, len(info3))
def testSquareIncluded(self):
# generate the image to be processed
w, h = 2000, 2000
image = np.zeros((h, w), dtype=np.uint8)
# locations of the 9 multi-squares
positions = [
(w // 7, h // 7),
(3 * w // 7, h // 7),
(5 * w // 7, h // 7),
(w // 7, 3 * h // 7),
(3 * w // 7, 3 * h // 7),
(5 * w // 7, 3 * h // 7),
(w // 7, 5 * h // 7),
(3 * w // 7, 5 * h // 7),
(5 * w // 7, 5 * h // 7)
]
for position in positions:
image = draw_multisquare(image, position, w // 7, color_in=127)
# Build workflow
builder = SLDCWorkflowBuilder()
# Build workflow 1
builder.set_segmenter(BigShapeSegmenter())
builder.add_catchall_classifier(DumbClassifier())
builder.set_tile_size(512, 512)
workflow1 = builder.get()
# Build workflow 2
builder.set_segmenter(SmallSquareSegmenter())
builder.add_catchall_classifier(DumbClassifier())
workflow2 = builder.get()
# Build chaining
chain_builder = WorkflowChainBuilder()
chain_builder.set_first_workflow(workflow1, label="big_squares")
chain_builder.add_executor(workflow2, label="small_squares")
chain = chain_builder.get()
# Launch
chain_info = chain.process(NumpyImage(image))
# check results
big_area = (w // 7) ** 2
small_area = (w / 35) ** 2
info1 = chain_info["big_squares"]
self.assertEqual(9, len(info1))
for object_info in info1:
self.assertTrue(relative_error(object_info.polygon.area, big_area) < 0.005)
self.assertEqual("catchall", object_info.dispatch)
self.assertEqual(1, object_info.label)
self.assertAlmostEqual(1.0, object_info.proba)
info2 = chain_info["small_squares"]
self.assertEqual(36, len(info2))
for object_info in info2:
self.assertTrue(relative_error(object_info.polygon.area, small_area) < 0.005)
self.assertEqual("catchall", object_info.dispatch)
self.assertEqual(1, object_info.label)
self.assertAlmostEqual(1.0, object_info.proba)
def testSquareAndCircleIncluded(self):
w, h = 2000, 2000
image = np.zeros((h, w), dtype=np.uint8)
# locations of the 9 multi-squares
shapes = [
("c", (w // 7, h // 7)),
("s", (3 * w // 7, h // 7)),
("s", (5 * w // 7, h // 7)),
("s", (w // 7, 3 * h // 7)),
("c", (3 * w // 7, 3 * h // 7)),
("s", (5 * w // 7, 3 * h // 7)),
("c", (w // 7, 5 * h // 7)),
("s", (3 * w // 7, 5 * h // 7)),
("c", (5 * w // 7, 5 * h // 7))
]
for shape, position in shapes:
if shape == "c":
image = draw_multicircle(image, position, w // 7, color_in=87)
elif shape == "s":
image = draw_multisquare(image, position, w // 7, color_in=187)
# Build workflows
# 1st: find big shapes and dispatch them as circle or square
# 2nd: find small circles in found circle shapes
# 3rd: find small squares in found square shape
builder = SLDCWorkflowBuilder()
builder.set_segmenter(BigShapeSegmenter())
builder.add_classifier(CircleDispatch(), DumbClassifier(), dispatching_label="circle")
builder.add_classifier(SquareDispatch(), DumbClassifier(), dispatching_label="square")
builder.set_tile_size(512, 512)
workflow1 = builder.get()
builder.set_segmenter(SmallCircleSegmenter())
builder.add_catchall_classifier(DumbClassifier())
workflow2 = builder.get()
builder.set_segmenter(SmallSquareSegmenter())
builder.add_catchall_classifier(DumbClassifier())
workflow3 = builder.get()
# Build chain
chain_builder = WorkflowChainBuilder()
chain_builder.set_first_workflow(workflow1)
chain_builder.add_executor(workflow2, filter=CircleShapeFilter())
chain_builder.add_executor(workflow3, filter=SquareShapeFilter(), n_jobs=2)
chain = chain_builder.get()
chain_info = chain.process(NumpyImage(image))
info1 = chain_info[0]
self.assertEqual(9, len(info1))
self.assertEqual(4, len([d for d in info1.dispatches if d == "circle"]))
self.assertEqual(5, len([d for d in info1.dispatches if d == "square"]))
info2 = chain_info[1]
self.assertEqual(16, len(info2))
info3 = chain_info[2]
self.assertEqual(20, len(info3))