def mapper(dataset_dict):
# Implement a mapper, similar to the default DatasetMapper, but with your own customizations
dataset_dict = copy.deepcopy(
dataset_dict) # it will be modified by code below
image = utils.read_image(dataset_dict["file_name"], format="BGR")
image, transforms = T.apply_transform_gens([
T.RandomFlip(prob=0.50, horizontal=True, vertical=False),
T.RandomApply(tfm_or_aug=T.RandomBrightness(intensity_min=0.7,
intensity_max=1.1),
prob=0.40),
T.RandomApply(tfm_or_aug=T.RandomSaturation(intensity_min=0.7,
intensity_max=1.1),
prob=0.40)
], image)
dataset_dict["image"] = torch.as_tensor(
image.transpose(2, 0, 1).astype("float32"))
annos = [
utils.transform_instance_annotations(obj, transforms, image.shape[:2])
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
]
instances = utils.annotations_to_instances(annos, image.shape[:2])
dataset_dict["instances"] = utils.filter_empty_instances(instances)
return dataset_dict
def bulb_traffic_light_augmentation(cfg, is_train):
if is_train:
min_size = cfg.INPUT.MIN_SIZE_TRAIN
max_size = cfg.INPUT.MAX_SIZE_TRAIN
sample_style = cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING
else:
min_size = cfg.INPUT.MIN_SIZE_TEST
max_size = cfg.INPUT.MAX_SIZE_TEST
sample_style = "choice"
if sample_style == "range":
assert len(min_size) == 2, "more than 2 ({}) min_size(s) are provided for ranges".format(
len(min_size)
)
logger = logging.getLogger(__name__)
augmentation = []
augmentation.append(T.ResizeShortestEdge(min_size, max_size, sample_style))
if is_train:
train_augmentation = [
# T.RandomFlip(),
# T.RandomApply(T.RandomFlip(prob=0.5, horizontal=False, vertical=True), prob=0.3),
# T.RandomApply(T.RandomRotation(angle=[-5, 5]), prob=0.15),
T.RandomApply(T.RandomContrast(intensity_min=0.8, intensity_max=1.2), prob=0.15),
T.RandomApply(T.RandomBrightness(intensity_min=0.8, intensity_max=1.2), prob=0.15),
T.RandomApply(T.RandomSaturation(intensity_min=0.8, intensity_max=1.2), prob=0.15),
T.RandomApply(T.RandomLighting(0.8), prob=0.15)
]
augmentation.extend(train_augmentation)
logger.info("Augmentations used in training: " + str(augmentation))
return augmentation
def test_random_apply_wrapping_std_transform_probability_occured_evaluation(self):
transform_mock = mock.MagicMock(name="MockTransform", spec=T.Transform)
image_mock = mock.MagicMock(name="MockImage")
random_apply = T.RandomApply(transform_mock, prob=0.001)
with mock.patch.object(random_apply, "_rand_range", return_value=0.0001):
transform = random_apply.get_transform(image_mock)
self.assertIs(transform, transform_mock)
def test_random_apply_prob_out_of_range_check(self):
test_probabilities = {0.0: True, 0.5: True, 1.0: True, -0.01: False, 1.01: False}
for given_probability, is_valid in test_probabilities.items():
if not is_valid:
self.assertRaises(AssertionError, T.RandomApply, None, prob=given_probability)
else:
T.RandomApply(T.NoOpTransform(), prob=given_probability)
def test_random_apply_probability_not_occured_evaluation(self):
transform_mock = mock.MagicMock(name="MockTransform", spec=T.Augmentation)
image_mock = mock.MagicMock(name="MockImage")
random_apply = T.RandomApply(transform_mock, prob=0.001)
with mock.patch.object(random_apply, "_rand_range", return_value=0.9):
transform = random_apply.get_transform(image_mock)
transform_mock.get_transform.assert_not_called()
self.assertIsInstance(transform, T.NoOpTransform)
def test_random_apply_wrapping_aug_probability_occured_evaluation(self):
transform_mock = mock.MagicMock(name="MockTransform", spec=T.Augmentation)
image_mock = mock.MagicMock(name="MockImage")
random_apply = T.RandomApply(transform_mock, prob=0.001)
with mock.patch.object(random_apply, "_rand_range", return_value=0.0001):
transform = random_apply.get_transform(image_mock)
transform_mock.get_transform.assert_called_once_with(image_mock)
self.assertIsNot(transform, transform_mock)
def build_train_loader(cls, cfg):
dataloader = build_detection_train_loader(
cfg,
mapper=DatasetMapper(
cfg,
is_train=True,
augmentations=[
T.RandomApply(tfm_or_aug=T.RandomBrightness(0.8, 1.2),
prob=0.2),
T.RandomApply(tfm_or_aug=T.RandomContrast(0.8, 1.2),
prob=0.1),
T.RandomFlip(prob=0.25, horizontal=True, vertical=False),
T.RandomRotation(angle=[0, 90, 180, 270],
expand=True,
center=None,
sample_style='choice',
interp=None)
]))
return dataloader
def build_train_aug(cfg):
augs = [
T.ResizeShortestEdge(cfg.INPUT.MIN_SIZE_TRAIN, cfg.INPUT.MAX_SIZE_TRAIN, cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING),
T.RandomContrast(0.5, 1.5),
T.RandomBrightness(0.5, 1.5),
T.RandomSaturation(0.5, 1.5),
T.RandomFlip(),
T.RandomApply(T.RandomExtent([1.0, 2.0], [0.2, 0.2])),
]
if cfg.INPUT.CROP.ENABLED:
augs.insert(0, T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
return augs
def build_aug_transforms(
cfg: detectron2.config.CfgNode,
flip_horiz: bool = True,
flip_vert: bool = False,
max_rotate: int = 10,
brightness_limits: Tuple[int, int] = (0.8, 1.4),
contrast_limits: Tuple[int, int] = (0.8, 1.4),
saturation_limits: Tuple[int, int] = (0.8, 1.4),
p_lighting: float = 0.75
) -> detectron2.data.transforms.AugmentationList:
"Build a list of detectron2 augmentations"
augs = []
augs.append(
T.ResizeShortestEdge(cfg.INPUT.MIN_SIZE_TRAIN,
cfg.INPUT.MAX_SIZE_TRAIN,
cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING))
if flip_horiz:
augs.append(T.RandomFlip(prob=0.5, horizontal=True, vertical=False))
if flip_vert:
augs.append(T.RandomFlip(prob=0.5, horizontal=False, vertical=True))
if max_rotate:
augs.append(
T.RandomRotation(angle=[-max_rotate, max_rotate], expand=False))
if brightness_limits:
augs.append(
T.RandomApply(prob=p_lighting,
tfm_or_aug=T.RandomBrightness(*brightness_limits)))
if contrast_limits:
augs.append(
T.RandomApply(prob=p_lighting,
tfm_or_aug=T.RandomContrast(*contrast_limits)))
if saturation_limits:
augs.append(
T.RandomApply(prob=p_lighting,
tfm_or_aug=T.RandomSaturation(*saturation_limits)))
return augs
def build_augmentations(cfg):
# augs = [
# T.ResizeShortestEdge(cfg.INPUT.MIN_SIZE_TRAIN, cfg.INPUT.MAX_SIZE_TRAIN, cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING),
# T.RandomBrightness(0.7, 0.9),
# T.RandomFlip(prob=0.5),
# T.RandomApply(T.RandomRotation(angle=[-25, 25]), prob=0.5),
# T.RandomApply(prob=0.2, tfm_or_aug=T.RandomLighting(scale=0.5))
# ]
augs = [
T.RandomFlip(prob=0.5),
T.RandomApply(T.RandomRotation(angle=[-25, 25]), prob=0.9)
]
if cfg.INPUT.CROP.ENABLED:
#instead of appending, putting cropping in front
augs = [
T.RandomCrop_CategoryAreaConstraint(cfg.INPUT.CROP.TYPE,
cfg.INPUT.CROP.SIZE)
] + augs
return augs
from detectron2.data import MetadataCatalog
from detectron2.data import DatasetCatalog
from detectron2 import model_zoo
from detectron2.engine import DefaultTrainer
from detectron2.engine import DefaultPredictor
from detectron2.evaluation import COCOEvaluator
from detectron2.config import get_cfg
from detectron2.data import build_detection_train_loader, build_detection_test_loader, DatasetMapper, detection_utils
from detectron2.data.samplers import GroupedBatchSampler, TrainingSampler, InferenceSampler, RepeatFactorTrainingSampler
import detectron2.data.transforms as T
augmentations = [
T.RandomFlip(prob=0.25, horizontal=True, vertical=False),
T.RandomFlip(prob=0.25, horizontal=False, vertical=True),
T.RandomApply(tfm_or_aug=T.RandomBrightness(intensity_min=0.75, intensity_max=1.25),
prob=0.25),
T.RandomApply(tfm_or_aug=T.RandomContrast(intensity_min=0.75, intensity_max=1.25),
prob=0.25),
T.RandomApply(tfm_or_aug=T.RandomCrop(crop_type="relative_range", crop_size=(0.75, 0.75)),
prob=0.25),
T.RandomApply(tfm_or_aug=T.RandomSaturation(intensity_min=0.75, intensity_max=1.25),
prob=0.25),
T.RandomApply(tfm_or_aug=T.RandomRotation(angle=[-30,30], expand=True, center=None, sample_style="range", interp=None),
prob=0.25)
]
def mapper(dataset_dict):
# Implement a mapper, similar to the default DatasetMapper, but with your own customizations
dataset_dict = copy.deepcopy(dataset_dict) # it will be modified by code below
image = detection_utils.read_image(dataset_dict["file_name"], format="BGR")
def do_train(cfg, model, resume=False):
model.train()
optimizer = build_optimizer(cfg, model)
scheduler = build_lr_scheduler(cfg, optimizer)
checkpointer = DetectionCheckpointer(
model, cfg.OUTPUT_DIR, optimizer=optimizer, scheduler=scheduler
)
start_iter = (
checkpointer.resume_or_load(cfg.MODEL.WEIGHTS, resume=resume).get("iteration", -1) + 1
)
max_iter = cfg.SOLVER.MAX_ITER
writers = (
[
CommonMetricPrinter(max_iter),
JSONWriter(os.path.join(cfg.OUTPUT_DIR, "metrics.json")),
TensorboardXWriter(cfg.OUTPUT_DIR),
]
if comm.is_main_process()
else []
)
min_size = cfg.INPUT.MIN_SIZE_TRAIN
max_size = cfg.INPUT.MAX_SIZE_TRAIN,
sample_style = cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING
data_loader = build_detection_train_loader(cfg, mapper=DatasetMapper(cfg,
is_train=True,
augmentations=[
T.ResizeShortestEdge(min_size, max_size, sample_style),
T.RandomApply(T.RandomFlip(prob = 1, vertical = False), prob = 0.5),
T.RandomApply(T.RandomRotation(angle = [180], sample_style = 'choice'), prob = 0.1),
T.RandomApply(T.RandomRotation(angle = [-10,10], sample_style = 'range'), prob = 0.9),
T.RandomApply(T.RandomBrightness(0.5,1.5), prob = 0.5),
T.RandomApply(T.RandomContrast(0.5,1.5), prob = 0.5)
]))
best_model_weight = copy.deepcopy(model.state_dict())
best_val_loss = None
data_val_loader = build_detection_test_loader(cfg,
cfg.DATASETS.TEST[0],
mapper = DatasetMapper(cfg, True))
logger.info("Starting training from iteration {}".format(start_iter))
with EventStorage(start_iter) as storage:
for data, iteration in zip(data_loader, range(start_iter, max_iter)):
iteration += 1
start = time.time()
storage.step()
loss_dict = model(data)
losses = sum(loss_dict.values())
assert torch.isfinite(losses).all(), loss_dict
loss_dict_reduced = {k: v.item() for k, v in comm.reduce_dict(loss_dict).items()}
losses_reduced = sum(loss for loss in loss_dict_reduced.values())
if comm.is_main_process():
storage.put_scalars(total_loss=losses_reduced, **loss_dict_reduced)
optimizer.zero_grad()
losses.backward()
optimizer.step()
storage.put_scalar("lr", optimizer.param_groups[0]["lr"], smoothing_hint=False)
scheduler.step()
if (
cfg.TEST.EVAL_PERIOD > 0
and iteration % cfg.TEST.EVAL_PERIOD == 0
and iteration != max_iter
):
logger.setLevel(logging.CRITICAL)
print('validating')
val_total_loss = do_val_monitor(cfg, model, data_val_loader)
logger.setLevel(logging.DEBUG)
logger.info(f"validation loss of iteration {iteration}th: {val_total_loss}")
storage.put_scalar(name = 'val_total_loss', value = val_total_loss)
if best_val_loss is None or val_total_loss < best_val_loss:
best_val_loss = val_total_loss
best_model_weight = copy.deepcopy(model.state_dict())
comm.synchronize()
# สร้าง checkpointer เพิ่มให้ save best model โดยดูจาก val loss
if iteration - start_iter > 5 and (iteration % 20 == 0 or iteration == max_iter):
for writer in writers:
writer.write()
model.load_state_dict(best_model_weight)
experiment_name = os.getenv('MLFLOW_EXPERIMENT_NAME')
checkpointer.save(f'model_{experiment_name}')
return model