def __init__(self, cfg):
self.cfg = cfg
self.model = build_model(self.cfg)
self.model.eval()
self.metadata = MetadataCatalog.get(cfg.DATASETS.TEST[0])
checkpointer = DetectionCheckpointer(self.model)
print('try load weights from: {}'.format(cfg.MODEL.WEIGHTS))
checkpointer.load(cfg.MODEL.WEIGHTS)
self.transform_gen = T.ResizeShortestEdge(
[cfg.INPUT.MIN_SIZE_TEST, cfg.INPUT.MIN_SIZE_TEST], cfg.INPUT.MAX_SIZE_TEST
)
self.input_format = cfg.INPUT.FORMAT
assert self.input_format in ["RGB", "BGR"], self.input_format
def build_evaluator(cls, cfg, dataset_name, output_folder=None):
if output_folder is None:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference")
evaluator_list = []
evaluator_type = MetadataCatalog.get(dataset_name).evaluator_type
if evaluator_type in ["coco", "coco_panoptic_seg"]:
evaluator_list.append(
COCOEvaluator(dataset_name,
cfg,
True,
output_folder,
dump=cfg.GLOBAL.DUMP_TRAIN))
elif evaluator_type == "pascal_voc":
return PascalVOCDetectionEvaluator(dataset_name)
if len(evaluator_list) == 0:
raise NotImplementedError(
"no Evaluator for the dataset {} with the type {}".format(
dataset_name, evaluator_type))
elif len(evaluator_list) == 1:
return evaluator_list[0]
return DatasetEvaluators(evaluator_list)
from alfred.vis.image.get_dataset_label_map import coco_label_map_list
import glob
from models.data.custom_datasets.nuscenes import get_nuscenes_dicts
from models.data.datasets import register_coco_instances
categories = [
"trafficlight_red",
"trafficlight_green",
"trafficlight_black",
"trafficlight_yellow",
]
register_coco_instances(
'coco_tl', {}, './datasets/coco_tl/annotations/instances_train2017.json',
'./datasets/coco_tl/images')
MetadataCatalog.get("coco_tl").thing_classes = categories
force_color = [(0, 0, 255), (0, 255, 0), (255, 82, 12), (0, 255, 255)]
class DefaultPredictor:
def __init__(self, cfg):
self.cfg = cfg
self.model = build_model(self.cfg)
self.model.eval()
self.metadata = MetadataCatalog.get(cfg.DATASETS.TRAIN[0])
checkpointer = DetectionCheckpointer(self.model)
print('try load weights from: {}'.format(cfg.MODEL.WEIGHTS))
checkpointer.load(cfg.MODEL.WEIGHTS)
categories = [
'human.pedestrian.adult', 'human.pedestrian.child',
'human.pedestrian.wheelchair', 'human.pedestrian.stroller',
'human.pedestrian.personal_mobility', 'human.pedestrian.police_officer',
'human.pedestrian.construction_worker', 'vehicle.car', 'vehicle.bus.bendy',
'vehicle.bus.rigid', 'vehicle.truck', 'vehicle.construction',
'vehicle.emergency.ambulance', 'vehicle.emergency.police',
'vehicle.trailer'
]
path = "datasets/nuScenes"
get_dicts = lambda p=path, c=categories: get_nuscenes_dicts(
path=p, version='v1.0-trainval', categories=c)
DatasetCatalog.register("nusc_v1.0_trainval01", get_dicts)
MetadataCatalog.get("nusc_v1.0_trainval01").thing_classes = categories
class DefaultPredictor:
def __init__(self, cfg):
self.cfg = cfg
self.model = build_model(self.cfg)
self.model.eval()
self.metadata = MetadataCatalog.get(cfg.DATASETS.TEST[0])
checkpointer = DetectionCheckpointer(self.model)
print('try load weights from: {}'.format(cfg.MODEL.WEIGHTS))
checkpointer.load(cfg.MODEL.WEIGHTS)
self.transform_gen = T.ResizeShortestEdge(
[cfg.INPUT.MIN_SIZE_TEST, cfg.INPUT.MIN_SIZE_TEST],