def mapper(dataset_dict):
dataset_dict = copy.deepcopy(dataset_dict)
image = utils.read_image(dataset_dict["file_name"], format="BGR")
image, transforms = T.apply_transform_gens([T.Resize((1152, 1152))], image)
dataset_dict["image"] = torch.as_tensor(
image.transpose(2, 0, 1).astype("float32"))
annos = [
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_rotated(annos, image.shape[:2])
dataset_dict["instances"] = utils.filter_empty_instances(instances)
return dataset_dict
def __call__(self, dataset_dict):
"""
Args:
dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format.
Returns:
dict: a format that builtin models in detectron2 accept
"""
# Implement a mapper, similar to the default DatasetMapper, but with 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")
# Custom augs to be used while training
# Only HFlip and Resize are supported for rotated_boxes
augs = [T.RandomFlip(0.4, horizontal=True,
vertical=False)] #[T.RandomRotation([0,90])]
if self.is_train:
tfm_gens = self.tfm_gens + augs
else:
tfm_gens = self.tfm_gens
logging.getLogger(__name__).info("Original Augmentation: " +
str(self.tfm_gens))
logging.getLogger(__name__).info("Updated Augmentation List: " +
str(tfm_gens))
image, transforms = T.apply_transform_gens(tfm_gens, image)
dataset_dict["image"] = torch.as_tensor(
image.transpose(2, 0, 1).astype("float32"))
for a in dataset_dict['annotations']:
a['bbox'] = transforms.apply_rotated_box(np.asarray(
[a['bbox']]))[0].tolist()
annos = dataset_dict['annotations']
instances = utils.annotations_to_instances_rotated(
annos, image.shape[:2])
dataset_dict["instances"] = utils.filter_empty_instances(instances)
return dataset_dict
def __call__(self, dataset_dict):
dataset_dict = copy.deepcopy(dataset_dict)
image = utils.read_image(dataset_dict["file_name"],
format=self.image_format)
utils.check_image_size(dataset_dict, image)
aug_input = T.AugInput(image, sem_seg=None)
transforms = self.augmentations(aug_input)
image = aug_input.image
image_shape = image.shape[:2]
dataset_dict["image"] = torch.as_tensor(
np.ascontiguousarray(image.transpose(2, 0, 1)))
if not self.is_train:
dataset_dict.pop("annotations", None)
return dataset_dict
if "annotations" in dataset_dict:
annos = [
self.transform_instance_annotations_rotated(
obj, transforms, image_shape)
# obj
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
]
instances = utils.annotations_to_instances_rotated(
annos, image_shape)
if self.recompute_boxes:
instances.gt_boxes = instances.gt_masks.get_bounding_boxes()
dataset_dict["instances"] = utils.filter_empty_instances(instances)
return dataset_dict
def rotated_mapper(original_dataset_dict):
# Implement a mapper, similar to the default DatasetMapper, but with our own customizations
dataset_dict = copy.deepcopy(
original_dataset_dict) # it will be modified by code below
original_gsd = dataset_dict["gsd"]
target_gsd = np.random.uniform(0.09, 0.13) # randomize target gsd
scale = original_gsd / target_gsd
target_size = 400
target_crop = int(target_size / scale)
target_crop = (target_crop, target_crop)
image_np = detection_utils.read_image(dataset_dict["file_name"],
format="BGR")
boxes = np.asarray([anno['bbox'] for anno in dataset_dict['annotations']])
# select anno at random
# draw random center
# h, w = image_np.shape[:2]
# rand_box = boxes[np.random.randint(len(boxes))]
# ch, cw = rand_box[:2]
# xmin = np.min()
# xmax = np.max()
# ymin = 3
# ymax = 4
# h0 = np.random.randint(min(h, ymin), min(h, ymax) + 1)
# w0 = np.random.randint(min(w, xmin), min(w, xmax) + 1)
# assert h >= target_crop[1] and w >= target_crop[0], "Shape computation has bugs."
# crop = T.CropTransform(w0, h0, target_crop)
# make sure random crop contains annotations
i = 0
while True:
random_crop = T.RandomCrop('absolute',
target_crop).get_transform(image_np)
cropped_boxes = RotatedBoxes(
random_crop.apply_coords(copy.deepcopy(boxes)))
inside_ind = cropped_boxes.inside_box(target_crop)
if 1 < sum(inside_ind) <= 100:
break
i += 1
if i > 150:
return None
image, transforms = T.apply_transform_gens([
random_crop,
T.Resize((target_size, target_size)),
], image_np)
dataset_dict["image"] = torch.as_tensor(
image.transpose(2, 0, 1).astype("float32"))
annos = [
rotated_transform_instance_annotations(obj, transforms,
image.shape[:2])
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
]
instances = detection_utils.annotations_to_instances_rotated(
annos, image.shape[:2])
instances = detection_utils.filter_empty_instances(instances)
inside_ind = instances.gt_boxes.inside_box(image.shape[:2])
instances = instances[inside_ind]
assert ((instances.gt_boxes.tensor.numpy()[:, 2] > 0).all().item()
), "width not > 0\n\n" + str(instances.gt_boxes.tensor.numpy())
dataset_dict["instances"] = instances
return dataset_dict