from detectron2.structures import Instances
from detectron2.utils.logger import setup_logger
from detectron2.utils.visualizer import (
Visualizer,
_create_text_labels,
GenericMask,
ColorMode,
VisImage,
random_color,
_SMALL_OBJECT_AREA_THRESH,
)
from fvcore.common.file_io import PathManager
from indiscapes_dataset import register_dataset
register_dataset(combined_train_val=False)
class CustomVisualizer(Visualizer):
def __init__(self,
img_rgb,
metadata=None,
scale=1.0,
instance_mode=ColorMode.IMAGE):
"""
Args:
img_rgb: a numpy array of shape (H, W, C), where H and W correspond to
the height and width of the image respectively. C is the number of
color channels. The image is required to be in RGB format since that
is a requirement of the Matplotlib library. The image is also expected
to be in the range [0, 255].
import detectron2.utils.comm as comm
from d2.detr import DetrDatasetMapper, add_detr_config
from detectron2.checkpoint import DetectionCheckpointer
from detectron2.config import get_cfg
from detectron2.data import MetadataCatalog, build_detection_train_loader
from detectron2.engine import DefaultTrainer, default_argument_parser, default_setup, launch
from detectron2.evaluation import COCOEvaluator, verify_results
from detectron2.evaluation import DatasetEvaluators
from detectron2.solver.build import maybe_add_gradient_clipping
from hd.evaluator import HDEvaluator
from indiscapes_dataset import register_dataset
from validation_hooks import EvalHook
register_dataset(combined_train_val=True)
class Trainer(DefaultTrainer):
"""
Extension of the Trainer class adapted to DETR.
"""
@classmethod
def build_evaluator(cls, cfg, dataset_name, output_folder=None):
"""
Create evaluator(s) for a given dataset.
This uses the special metadata "evaluator_type" associated with each builtin dataset.
For your own dataset, you can simply create an evaluator manually in your
script and do not have to worry about the hacky if-else logic here.
"""
if output_folder is None: