def predict_many_tasks(self, tasks):
self.update_state()
if self.not_ready:
logger.debug(f'ML backend {self} is not ready')
return
if isinstance(tasks, list):
from tasks.models import Task
tasks = Task.objects.filter(id__in=[task.id for task in tasks])
tasks_ser = TaskSimpleSerializer(tasks, many=True).data
ml_api_result = self.api.make_predictions(tasks_ser,
self.model_version,
self.project)
if ml_api_result.is_error:
logger.error(
f'Prediction not created for project {self}: {ml_api_result.error_message}'
)
return
responses = ml_api_result.response['results']
if len(responses) == 0:
logger.error(
f'ML backend returned empty prediction for project {self}')
return
# ML Backend doesn't support batch of tasks, do it one by one
elif len(responses) == 1:
logger.warning(
f"'ML backend '{self.title}' doesn't support batch processing of tasks, "
f"switched to one-by-one task retrieving")
for task in tasks:
self.predict_one_task(task)
return
# wrong result number
elif len(responses) != len(tasks_ser):
logger.error(
f'ML backend returned response number {len(responses)} != task number {len(tasks_ser)}'
)
predictions = []
for task, response in zip(tasks_ser, responses):
predictions.append({
'task': task['id'],
'result': response['result'],
'score': response.get('score'),
'model_version': self.model_version
})
with conditional_atomic():
prediction_ser = PredictionSerializer(data=predictions, many=True)
prediction_ser.is_valid(raise_exception=True)
prediction_ser.save()
def _scan_and_create_links(self, link_class):
tasks_created = 0
maximum_annotations = self.project.maximum_annotations
task = self.project.tasks.order_by('-inner_id').first()
max_inner_id = (task.inner_id + 1) if task else 1
for key in self.iterkeys():
logger.debug(f'Scanning key {key}')
# skip if task already exists
if link_class.exists(key, self):
logger.debug(
f'{self.__class__.__name__} link {key} already exists')
continue
logger.debug(f'{self}: found new key {key}')
try:
data = self.get_data(key)
except (UnicodeDecodeError, json.decoder.JSONDecodeError) as exc:
logger.error(exc, exc_info=True)
raise ValueError(
f'Error loading JSON from file "{key}".\nIf you\'re trying to import non-JSON data '
f'(images, audio, text, etc.), edit storage settings and enable '
f'"Treat every bucket object as a source file"')
# predictions
predictions = data.get('predictions', [])
if predictions:
if 'data' not in data:
raise ValueError(
'If you use "predictions" field in the task, '
'you must put "data" field in the task too')
# annotations
annotations = data.get('annotations', [])
if annotations:
if 'data' not in data:
raise ValueError(
'If you use "annotations" field in the task, '
'you must put "data" field in the task too')
if 'data' in data and isinstance(data['data'], dict):
data = data['data']
with transaction.atomic():
task = Task.objects.create(
data=data,
project=self.project,
overlap=maximum_annotations,
is_labeled=len(annotations) >= maximum_annotations,
inner_id=max_inner_id)
max_inner_id += 1
link_class.create(task, key, self)
logger.debug(
f'Create {self.__class__.__name__} link with key={key} for task={task}'
)
tasks_created += 1
# add predictions
logger.debug(
f'Create {len(predictions)} predictions for task={task}')
for prediction in predictions:
prediction['task'] = task.id
prediction_ser = PredictionSerializer(data=predictions,
many=True)
prediction_ser.is_valid(raise_exception=True)
prediction_ser.save()
# add annotations
logger.debug(
f'Create {len(annotations)} annotations for task={task}')
for annotation in annotations:
annotation['task'] = task.id
annotation_ser = AnnotationSerializer(data=annotations,
many=True)
annotation_ser.is_valid(raise_exception=True)
annotation_ser.save()
self.last_sync = timezone.now()
self.last_sync_count = tasks_created
self.save()
self.project.update_tasks_states(
maximum_annotations_changed=False,
overlap_cohort_percentage_changed=False,
tasks_number_changed=True)
