def from_config(cls, cfg, is_train: bool = True):
augs = utils.build_augmentation(cfg, is_train)
if cfg.INPUT.CROP.ENABLED and is_train:
augs.insert(0, T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
recompute_boxes = cfg.MODEL.MASK_ON
else:
recompute_boxes = False
ret = {
"is_train": is_train,
"augmentations": augs,
"image_format": cfg.INPUT.FORMAT,
"use_instance_mask": cfg.MODEL.MASK_ON,
"instance_mask_format": cfg.INPUT.MASK_FORMAT,
"use_keypoint": cfg.MODEL.KEYPOINT_ON,
"recompute_boxes": recompute_boxes,
}
if cfg.MODEL.KEYPOINT_ON:
ret["keypoint_hflip_indices"] = utils.create_keypoint_hflip_indices(cfg.DATASETS.TRAIN)
if cfg.MODEL.LOAD_PROPOSALS:
ret["precomputed_proposal_topk"] = (
cfg.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TRAIN
if is_train
else cfg.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TEST
)
return ret
def __init__(self, cfg, is_train=True):
if cfg.INPUT.CROP.ENABLED and is_train:
self.crop_aug = T.RandomCrop(cfg.INPUT.CROP.TYPE,
cfg.INPUT.CROP.SIZE)
logging.getLogger(__name__).info("CropGen used in training: " +
str(self.crop_aug))
else:
self.crop_aug = None
self.augmentation = utils.build_augmentation(cfg, is_train)
if cfg.INPUT.COLOR_AUG_SSD:
self.augmentation.append(
ColorAugSSDTransform(img_format=cfg.INPUT.FORMAT))
logging.getLogger(
__name__).info("Color augmnetation used in training: " +
str(self.augmentation[-1]))
# fmt: off
self.img_format = cfg.INPUT.FORMAT
self.single_category_max_area = cfg.INPUT.CROP.SINGLE_CATEGORY_MAX_AREA
self.ignore_value = cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE
# fmt: on
self.is_train = is_train
def __init__(self, cfg, is_train=True):
self.augmentation = utils.build_augmentation(cfg, is_train)
if cfg.INPUT.CROP.ENABLED and is_train:
self.augmentation.insert(
0, T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
logging.getLogger(__name__).info("Cropping used in training: " +
str(self.augmentation[0]))
self.compute_tight_boxes = True
else:
self.compute_tight_boxes = False
# fmt: off
self.img_format = cfg.INPUT.FORMAT
self.mask_on = cfg.MODEL.MASK_ON
self.mask_format = cfg.INPUT.MASK_FORMAT
self.keypoint_on = cfg.MODEL.KEYPOINT_ON
self.load_proposals = cfg.MODEL.LOAD_PROPOSALS
# fmt: on
if self.keypoint_on and is_train:
# Flip only makes sense in training
self.keypoint_hflip_indices = utils.create_keypoint_hflip_indices(
cfg.DATASETS.TRAIN)
else:
self.keypoint_hflip_indices = None
if self.load_proposals:
self.proposal_min_box_size = cfg.MODEL.PROPOSAL_GENERATOR.MIN_SIZE
self.proposal_topk = (cfg.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TRAIN
if is_train else
cfg.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TEST)
self.is_train = is_train
def build_augmentation(self):
result = dutils.build_augmentation(self.cfg, is_train=self.is_train)
if self.is_train:
# resize = T.Resize((800, 800))
# result.extend([resize, ])
pass
return result
def build_augmentation(cfg, is_train):
logger = logging.getLogger(__name__)
result = utils.build_augmentation(cfg, is_train)
if is_train:
random_rotation = T.RandomRotation(
cfg.INPUT.ROTATION_ANGLES, expand=False, sample_style="choice"
)
result.append(random_rotation)
logger.info("DensePose-specific augmentation used in training: " + str(random_rotation))
return result
def from_config(cls, cfg, is_train: bool = True):
augs = utils.build_augmentation(cfg, is_train)
if cfg.INPUT.CROP.ENABLED and is_train:
raise ValueError("Crop augmentation not supported to point supervision.")
ret = {
"is_train": is_train,
"augmentations": augs,
"image_format": cfg.INPUT.FORMAT,
"sample_points": cfg.INPUT.SAMPLE_POINTS,
}
return ret
def build_mapper(cls, cfg, is_train=True):
augs = detection_utils.build_augmentation(cfg, is_train)
#if cfg.INPUT.CROP.ENABLED and is_train:
# augs.insert(0, T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
# Define a sequence of augmentations: TODO
augs.append(T.RandomBrightness(0.9, 1.1))
augs.append(MyColorAugmentation())
# augs.append(T.RandomRotation([5,10,15,20,25,30], expand=True, center=None))
# T.RandomCrop("absolute", (640, 640)),
# MyCustomResize()
# type: T.Augmentation
return DatasetMapper(cfg, is_train=is_train, augmentations=augs)
def build_augmentation(cfg, is_train):
logger = logging.getLogger(__name__)
result = utils.build_augmentation(cfg, is_train)
if is_train:
random_rotation = T.RandomRotation(cfg.INPUT.ROTATION_ANGLES,
expand=False,
sample_style="choice")
# if cfg.MODEL.CONDINST.RAND_FLIP:
# random_hflip = T.HFlipTransform(width=0)
# result.append(random_hflip)
logger.info("DensePose-specific augmentation used in training: " +
str(random_rotation))
return result
def test_apply_rotated_boxes(self):
np.random.seed(125)
cfg = get_cfg()
is_train = True
augs = detection_utils.build_augmentation(cfg, is_train)
image = np.random.rand(200, 300)
image, transforms = T.apply_augmentations(augs, image)
image_shape = image.shape[:2] # h, w
assert image_shape == (800, 1200)
annotation = {"bbox": [179, 97, 62, 40, -56]}
boxes = np.array([annotation["bbox"]], dtype=np.float64) # boxes.shape = (1, 5)
transformed_bbox = transforms.apply_rotated_box(boxes)[0]
expected_bbox = np.array([484, 388, 248, 160, 56], dtype=np.float64)
err_msg = "transformed_bbox = {}, expected {}".format(transformed_bbox, expected_bbox)
assert np.allclose(transformed_bbox, expected_bbox), err_msg
def build_train_dataloader(cfg): # like 'build_detection_train_loader'
if 'coco_2017_train' in cfg.DATASETS.TRAIN:
descs_train: List[Dict] = DatasetCatalog.get("coco_2017_train")
ds_train = DatasetFromList(descs_train, copy=False)
mapper = DatasetMapper(cfg, True)
else: # Open-Image-Dataset
if 'get_detection_dataset_dicts':
all_descs_train: List[Dict] = DatasetCatalog.get("oid_train")
if 'rebalancing':
image_id_vs_idx = {}
for idx, desc in enumerate(all_descs_train):
image_id_vs_idx[desc['image_id']] = idx
descs_train = list(map(lambda img_id: all_descs_train[image_id_vs_idx[img_id]], sample_image_ids()))
print('_' * 50 + f'train dataset len: {len(descs_train)}')
ds_train = DatasetFromList(descs_train, copy=False)
if 'DatasetMapper':
augs = [RandomContrast(0.8, 1.2),
RandomBrightness(0.8, 1.2),
RandomSaturation(0.8, 1.2)]
augs.extend(build_augmentation(cfg, is_train=True))
mapper = make_mapper('oid_train', is_train=True, augmentations=T.AugmentationList(augs))
ds_train = MapDataset(ds_train, mapper)
sampler = TrainingSampler(len(ds_train))
data_loader = build_batch_data_loader(
ds_train,
sampler,
cfg.SOLVER.IMS_PER_BATCH,
aspect_ratio_grouping=cfg.DATALOADER.ASPECT_RATIO_GROUPING,
num_workers=cfg.DATALOADER.NUM_WORKERS,
)
global DATA_LOADER
DATA_LOADER = data_loader
return data_loader
def build_augmentation(cls, cfg: CfgNode, is_train: bool = True):
result = detection_utils.build_augmentation(cfg, is_train=is_train)
return result
