def testUsingPreloadedArryasWhenScriptingBatchProcessing(self):
args = app.parse_args([])
args.headless = True
args.project = self.PROJECT_FILE
shell = app.main(args)
assert isinstance(shell.workflow, PixelClassificationWorkflow)
# Obtain the training operator
opPixelClassification = shell.workflow.pcApplet.topLevelOperator
# Sanity checks
assert len(opPixelClassification.InputImages) > 0
assert opPixelClassification.Classifier.ready()
input_data1 = numpy.random.randint(0, 255, (2, 20, 20, 5, 1)).astype(numpy.uint8)
input_data2 = numpy.random.randint(0, 255, (2, 20, 20, 5, 1)).astype(numpy.uint8)
role_data_dict = {
"Raw Data": [
PreloadedArrayDatasetInfo(preloaded_array=input_data1, axistags=vigra.AxisTags("tzyxc")),
PreloadedArrayDatasetInfo(preloaded_array=input_data2, axistags=vigra.AxisTags("tzyxc")),
]
}
predictions = shell.workflow.batchProcessingApplet.run_export(role_data_dict, export_to_array=True)
for result in predictions:
assert result.shape == (2, 20, 20, 5, 2)
def analyze(conn, images, model, new_dataset, extension=".tar", resolution=0):
# Prepare ilastik
# temporary directory where to download files
path = tempfile.mkdtemp()
if not os.path.exists(path):
os.makedirs(path)
os.environ["LAZYFLOW_THREADS"] = "2"
os.environ["LAZYFLOW_TOTAL_RAM_MB"] = "2000"
args = app.parse_args([])
args.headless = True
args.project = model
args.readonly = True
shell = app.main(args)
start = time.time()
for image in images:
input_data = load_from_s3(image, path)
# run ilastik headless
print('running ilastik using %s and %s' % (model, image.getName()))
data = OrderedDict([(
"Raw Data",
[PreloadedArrayDatasetInfo(preloaded_array=input_data)],
)])
shell.workflow.batchProcessingApplet.run_export(
data, export_to_array=True) # noqa
elapsed = time.time() - start
print(elapsed)
def analyze(image_id, model):
args = app.parse_args([])
args.headless = True
args.project = model
args.readonly = True
shell = app.main(args)
input_data = load_from_s3(image_id)
# run ilastik headless
data = [{
"Raw Data":
PreloadedArrayDatasetInfo(preloaded_array=input_data,
axistags=vigra.defaultAxistags("tzyxc"))
}] # noqa
return shell.workflow.batchProcessingApplet.run_export(
data, export_to_array=True) # noqa
def analyze(conn, images, model, new_dataset):
# Prepare ilastik
os.environ["LAZYFLOW_THREADS"] = "2"
os.environ["LAZYFLOW_TOTAL_RAM_MB"] = "2000"
args = app.parse_args([])
args.headless = True
args.project = model
shell = app.main(args)
for image in images:
input_data = load_numpy_array(image)
# run ilastik headless
print('running ilastik using %s and %s' % (model, image.getName()))
data = [ {"Raw Data": PreloadedArrayDatasetInfo(preloaded_array=input_data, axistags=vigra.defaultAxistags("tzyxc"))}] # noqa
predictions = shell.workflow.batchProcessingApplet.run_export(data,
export_to_array=True) # noqa
for d in predictions:
save_results(conn, image, d, new_dataset)
def test_fake_data_source(self):
graph = lazyflow.graph.Graph()
reader = OperatorWrapper(OpDataSelection, graph=graph, operator_kwargs={"forceAxisOrder": False})
reader.ProjectFile.setValue(self.projectFile)
reader.WorkingDirectory.setValue(os.getcwd())
reader.ProjectDataGroup.setValue("DataSelection/local_data")
info = PreloadedArrayDatasetInfo(preloaded_array=self.imgData, axistags=vigra.defaultAxistags("tczyx"))
reader.Dataset.setValues([info])
# Verify that now data selection operator returns fake data
# with expected shape and type
imgData = reader.Image[0][...].wait()
assert imgData.shape == self.imgData.shape
assert imgData.dtype == self.imgData.dtype
numpy.testing.assert_array_equal(imgData, imgData)
# In case you're curious about which label class is which,
# let's read the label names from the project file.
label_names = opPixelClassification.LabelNames.value
label_colors = opPixelClassification.LabelColors.value
probability_colors = opPixelClassification.PmapColors.value
print(label_names, label_colors, probability_colors)
# Construct an OrderedDict of role-names -> DatasetInfos
# (See PixelClassificationWorkflow.ROLE_NAMES)
role_data_dict = OrderedDict(
[
(
"Raw Data",
[
PreloadedArrayDatasetInfo(preloaded_array=input_data1),
PreloadedArrayDatasetInfo(preloaded_array=input_data2),
],
)
]
)
## Note: If you want to pull your data from disk instead of in-memory, just provide filepaths like so:
# role_data_dict = OrderedDict([ ("Raw Data", [ '/path/to/input-file-1.png',
# '/path/to/input-file-2.h5/mydata' ]) ])
# Run the export via the BatchProcessingApplet
# Note: If you don't provide export_to_array, then the results will
# be exported to disk accordering to your project's DataExport settings.
# In that case, run_export() returns None.
predictions = shell.workflow.batchProcessingApplet.run_export(role_data_dict, export_to_array=True)