def custom_mapper(dataset_dict, size, flip_prob, min_brightness, max_brightness, \
min_contrast, max_contrast, min_saturation, max_saturation):
# 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")
transform_list = [
T.Resize(size),
T.RandomBrightness(min_brightness, max_brightness),
T.RandomContrast(min_contrast, max_contrast),
T.RandomSaturation(min_saturation, max_saturation),
T.RandomFlip(prob=flip_prob, horizontal=False, vertical=True),
T.RandomFlip(prob=flip_prob, horizontal=True, vertical=False),
]
image, transforms = T.apply_transform_gens(transform_list, image)
dataset_dict["image"] = torch.as_tensor(image.transpose(2, 0, 1).astype("float32"))
annos = [
detection_utils.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(annos, image.shape[:2])
dataset_dict["instances"] = detection_utils.filter_empty_instances(instances)
return dataset_dict
def custom_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")
# transform_list = [T.Resize(800,600),
# T.RandomFlip(prob=0.5, horizontal=True, vertical=True),
# T.RandomContrast(0.8, 3),
# T.RandomBrightness(0.8, 1.6),
# ]
transform_list = [ #T.Resize((800, 800)),
T.RandomContrast(0.8, 3),
T.RandomBrightness(0.8, 1.6),
T.RandomFlip(prob=0.5, horizontal=False, vertical=True),
T.RandomFlip(prob=0.5, horizontal=True, vertical=False)
] ### 数据增强方式
image, transforms = T.apply_transform_gens(transform_list,
image) ## # 数组增强
dataset_dict["image"] = torch.as_tensor(
image.transpose(2, 0, 1).astype("float32")) ##转成Tensor
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]) # 将标注转成Instance（Tensor）
dataset_dict["instances"] = utils.filter_empty_instances(
instances) ## 去除空的
return dataset_dict
def test_print_transform_gen(self):
t = T.RandomCrop("relative", (100, 100))
self.assertTrue(str(t) == "RandomCrop(crop_type='relative', crop_size=(100, 100))")
t = T.RandomFlip(prob=0.5)
self.assertTrue(str(t) == "RandomFlip(prob=0.5)")
t = T.RandomFlip()
self.assertTrue(str(t) == "RandomFlip()")
def test_print_augmentation(self):
t = T.RandomCrop("relative", (100, 100))
self.assertEqual(str(t), "RandomCrop(crop_type='relative', crop_size=(100, 100))")
t0 = T.RandomFlip(prob=0.5)
self.assertEqual(str(t0), "RandomFlip(prob=0.5)")
t1 = T.RandomFlip()
self.assertEqual(str(t1), "RandomFlip()")
t = T.AugmentationList([t0, t1])
self.assertEqual(str(t), f"AugmentationList[{t0}, {t1}]")
def _init_tta_fn(self, cfg):
max_size = cfg.TEST.AUG.MAX_SIZE
size_gens = [T.ResizeShortestEdge(sz, max_size, 'choice') for sz in cfg.TEST.AUG.MIN_SIZES]
flip = T.RandomFlip(1.0)
def tta_fn(image, rois):
image = image.permute(1, 2, 0).to('cpu').numpy()
dtype = image.dtype
image = image.astype(np.uint8)
out_images, out_rois = [], []
for tfm_gen in size_gens:
resized_image, tfm = T.apply_transform_gens([tfm_gen], image)
resized_rois = tfm.transforms[0].apply_box(rois.to('cpu').numpy())
if cfg.TEST.AUG.FLIP:
flipped_image, tfm = T.apply_transform_gens([flip], resized_image)
flipped_rois = tfm.transforms[0].apply_box(resized_rois)
img_batch = torch.stack([
torch.from_numpy(resized_image.astype(dtype)).permute(2,0,1),
torch.from_numpy(flipped_image.astype(dtype)).permute(2,0,1)
])
roi_batch = [
torch.from_numpy(resized_rois),
torch.from_numpy(flipped_rois)
]
else:
img_batch = torch.from_numpy(resized_image.astype(dtype)).permute(2,0,1).unsqueeze(0)
roi_batch = [torch.from_numpy(resized_rois),]
out_images.append(img_batch)
out_rois.append(roi_batch)
return out_images, out_rois
return tta_fn
def build_transform_gen(cfg, is_train):
"""
Create a list of :class:`TransformGen` from config.
Now it includes resizing and flipping.
Returns:
list[TransformGen]
"""
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("detectron2.data.detection_utils")
tfm_gens = []
tfm_gens.append(T.ResizeShortestEdge(min_size, max_size, sample_style))
if is_train:
tfm_gens.append(T.RandomContrast(0.5, 1.5))
tfm_gens.append(T.RandomBrightness(0.5, 1.5))
tfm_gens.append(T.RandomSaturation(0.5, 1.5))
tfm_gens.append(T.RandomFlip())
logger.info("TransformGens used in training[Updated]: " + str(tfm_gens))
return tfm_gens
def build_augmentation(cfg, is_train):
"""
With option to don't use hflip
Returns:
list[Augmentation]
"""
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))
augmentation = []
augmentation.append(T.ResizeShortestEdge(min_size, max_size, sample_style))
if is_train:
if cfg.INPUT.HFLIP_TRAIN:
augmentation.append(T.RandomFlip())
logger.info("Augmentations used in training: " + str(augmentation))
return augmentation
def build_normal_augmentation(cfg, is_train):
"""
Train Augmentations:
- ResizeShortestEdge
- RandomFlip (not for test)
Test:
- ResizeShortestEdge
"""
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"
augmentation = [T.ResizeShortestEdge(min_size, max_size, sample_style)]
if is_train and cfg.INPUT.RANDOM_FLIP != "none":
augmentation.append(
T.RandomFlip(
horizontal=cfg.INPUT.RANDOM_FLIP == "horizontal",
vertical=cfg.INPUT.RANDOM_FLIP == "vertical",
)
)
return augmentation
def custom_mapper(dataset_dict):
# it will be modified by code below
dataset_dict = copy.deepcopy(dataset_dict)
image = utils.read_image(dataset_dict["file_name"], format="BGR")
transform_list = [
T.Resize((512, 512)),
T.RandomBrightness(0.8, 1.8),
T.RandomContrast(0.6, 1.3),
T.RandomSaturation(0.8, 1.4),
T.RandomRotation(angle=[30, 30]),
T.RandomLighting(0.7),
T.RandomFlip(prob=0.4, horizontal=False, vertical=True),
]
image, transforms = T.apply_transform_gens(transform_list, 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 build_augmentation(cfg, is_train):
"""
Create a list of default :class:`Augmentation` from config.
Now it includes resizing and flipping.
Returns:
list[Augmentation]
"""
augmentation = []
if is_train:
if cfg.INPUT.COLOR_AUG:
augmentation.append(ColorAugTransform(img_format=cfg.INPUT.FORMAT))
if cfg.INPUT.SWAP_CHANNELS:
augmentation.append(RandomSwapChannelsTransform())
if cfg.INPUT.EXPAND:
augmentation.append(Expand(img_value=cfg.MODEL.PIXEL_MEAN))
if cfg.INPUT.MIN_IOU_CROP:
augmentation.append(MinIoURandomCrop())
if cfg.INPUT.RESIZE.ENABLED:
shape = cfg.INPUT.RESIZE.SIZE
augmentation.append(T.Resize(shape))
if is_train:
augmentation.append(T.RandomFlip())
return augmentation
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 build_transform_gen(cfg, is_train):
"""
Create a list of :class:`TransformGen` from config.
Returns:
list[TransformGen]
"""
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__)
tfm_gens = []
if is_train:
tfm_gens.append(T.RandomFlip())
tfm_gens.append(T.ResizeShortestEdge(min_size, max_size, sample_style))
if is_train:
logger.info("TransformGens used in training: " + str(tfm_gens))
return tfm_gens
def build_transform_gen(cls, cfg, is_train):
tfm_gens = []
min_size, max_size, sample_style = get_size(cfg, is_train)
tfm_gens.append(T.ResizeShortestEdge(min_size, max_size, sample_style))
if is_train:
tfm_gens.append(T.RandomFlip())
return tfm_gens
def from_config(cls, cfg):
augs = [
T.ResizeShortestEdge(
cfg.INPUT.MIN_SIZE_TRAIN,
cfg.INPUT.MAX_SIZE_TRAIN,
cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING,
)
]
if cfg.INPUT.CROP.ENABLED:
augs.append(T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
augs.append(T.RandomFlip())
# Assume always applies to the training set.
dataset_names = cfg.DATASETS.TRAIN
meta = MetadataCatalog.get(dataset_names[0])
panoptic_target_generator = PanopticDeepLabTargetGenerator(
ignore_label=meta.ignore_label,
thing_ids=list(meta.thing_dataset_id_to_contiguous_id.values()),
sigma=cfg.INPUT.GAUSSIAN_SIGMA,
ignore_stuff_in_offset=cfg.INPUT.IGNORE_STUFF_IN_OFFSET,
small_instance_area=cfg.INPUT.SMALL_INSTANCE_AREA,
small_instance_weight=cfg.INPUT.SMALL_INSTANCE_WEIGHT,
ignore_crowd_in_semantic=cfg.INPUT.IGNORE_CROWD_IN_SEMANTIC,
)
ret = {
"augmentations": augs,
"image_format": cfg.INPUT.FORMAT,
"panoptic_target_generator": panoptic_target_generator,
}
return ret
def build_augmentation(cfg, is_train):
"""
Create a list of default :class:`Augmentation` from config.
Now it includes resizing and flipping.
Returns:
list[Augmentation]
"""
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:
augmentation.append(T.RandomFlip())
logger.info("Augmentations used in training: " + str(augmentation))
return augmentation
def mapper(dataset_dict):
# 自定义mapper
dataset_dict = copy.deepcopy(dataset_dict) # 后面要改变这个dict，所以先复制
image = utils.read_image(dataset_dict["file_name"], format="BGR") # 读取图片，numpy array
# image, transforms = T.apply_transform_gens(
# [T.Resize((800, 800)), T.RandomContrast(0.1, 3), T.RandomSaturation(0.1, 2), T.RandomRotation(angle=[0, 180]),
# T.RandomFlip(prob=0.4, horizontal=False, vertical=True), T.RandomCrop('relative_range', (0.4, 0.6))], image) # 数组增强
# image, transforms = T.apply_transform_gens(
# [T.Resize((800, 800)), T.RandomContrast(0.1, 3), T.RandomSaturation(0.1, 2),
# T.RandomFlip(prob=0.4, horizontal=True, vertical=False), T.RandomCrop('relative_range', (0.4, 0.6))], image)
image, transforms = T.apply_transform_gens(
[T.Resize((800, 800)), T.RandomContrast(0.1, 3), T.RandomSaturation(0.1, 2),
T.RandomFlip(prob=0.4, horizontal=True, vertical=False)], image)
# 数组增强
dataset_dict["image"] = torch.as_tensor(image.transpose(2, 0, 1).astype("float32")) # 转成Tensor
annos = [
utils.transform_instance_annotations(obj, transforms, image.shape[:2])
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
] # 数据增强要同步标注
instances = utils.annotations_to_instances(annos, image.shape[:2]) # 将标注转成Instance（Tensor）
dataset_dict["instances"] = utils.filter_empty_instances(instances) # 去除空的
return dataset_dict
def __call__(self, dataset_dict):
self.tfm_gens = []
dataset_dict = deepcopy(dataset_dict)
image = utils.read_image(dataset_dict["file_name"],
format=self.img_format)
utils.check_image_size(dataset_dict, image)
if self.is_train:
# Crop
if 'crop' in self.da.keys():
crop_gen = T.RandomCrop(self.da['crop']['type'],
self.da['crop']['size'])
self.tfm_gens.append(crop_gen)
# Horizontal flip
if 'flip' in self.da.keys():
flip_gen = T.RandomFlip(
prob=self.da['flip']['prob'],
horizontal=self.da['flip']['horizontal'],
vertical=self.da['flip']['vertical'])
self.tfm_gens.append(flip_gen)
image, transforms = T.apply_transform_gens(self.tfm_gens, image)
image_shape = image.shape[:2] # h, w
dataset_dict["image"] = torch.as_tensor(
np.ascontiguousarray(image.transpose(2, 0, 1)))
if not self.is_train:
dataset_dict.pop("annotations", None)
dataset_dict.pop("sem_seg_file_name", None)
return dataset_dict
if "annotations" in dataset_dict:
for anno in dataset_dict["annotations"]:
if not self.mask_on:
anno.pop("segmentation", None)
if not self.keypoint_on:
anno.pop("keypoints", None)
annos = [
utils.transform_instance_annotations(
obj,
transforms,
image_shape,
keypoint_hflip_indices=self.keypoint_hflip_indices)
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
]
instances = utils.annotations_to_instances(
annos, image_shape, mask_format=self.mask_format)
if self.crop_gen and instances.has("gt_masks"):
instances.gt_boxes = instances.gt_masks.get_bounding_boxes()
dataset_dict["instances"] = utils.filter_empty_instances(instances)
return dataset_dict
def test_augmentation_list(self):
input_shape = (100, 100)
image = np.random.rand(*input_shape).astype("float32")
sem_seg = (np.random.rand(*input_shape) < 0.5).astype("uint8")
inputs = T.StandardAugInput(image, sem_seg=sem_seg) # provide two args
augs = T.AugmentationList([T.RandomFlip(), T.Resize(20)])
_ = T.AugmentationList([augs, T.Resize(30)])(inputs)
def build_train_loader(cls, cfg):
print(cfg.INPUT.MIN_SIZE_TRAIN)
mapper = DatasetMapper(cfg,
is_train=True,
augmentations=[
transforms.Resize(cfg.INPUT.MIN_SIZE_TEST),
transforms.RandomFlip()
])
return build_detection_train_loader(cfg, mapper)
def build_sem_seg_train_aug(cfg):
augs = [
T.ResizeShortestEdge(cfg.INPUT.MIN_SIZE_TRAIN,
cfg.INPUT.MAX_SIZE_TRAIN,
cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING)
]
if cfg.INPUT.CROP.ENABLED:
augs.append(T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
augs.append(T.RandomFlip())
return augs
def customMapper(dataset_dict):
dataset_dict = copy.deepcopy(dataset_dict)
image = utils.read_image(dataset_dict["file_name"], format="BGR")
transform_list = [
T.Resize((600, 800)),
T.RandomFlip(prob=0.6, horizontal=True, vertical=False),
T.RandomFlip(prob=0.6, horizontal=False, vertical=True),
]
image, transforms = T.apply_transform_gens(transform_list, 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 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(),
]
if cfg.INPUT.CROP.ENABLED:
augs.insert(0, T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
return augs
def build_train_loader(cls, cfg):
return build_detection_train_loader(
cfg,
mapper=DatasetMapper(
cfg,
is_train=True,
augmentations=[
# T.RandomBrightness(0.9, 1.1),
T.RandomFlip(prob=0.5, horizontal=True, vertical=False),
# T.RandomCrop("absolute", (640, 640))
]))
def __call__(self, dataset_dict):
self.tfm_gens = []
dataset_dict = deepcopy(dataset_dict)
image = utils.read_image(dataset_dict["file_name"],
format=self.img_format)
utils.check_image_size(dataset_dict, image)
if self.is_train:
# Crop
'''print("Augmentation: ", "T.RandomCrop('relative', [0.8, 0.4])")
crop_gen = T.RandomCrop('relative', [0.8, 0.4])
self.tfm_gens.append(crop_gen)'''
# Horizontal flip
print("Augmentation: ",
"T.RandomFlip(prob=0.5, horizontal=True, vertical=False)")
flip_gen = T.RandomFlip(prob=0.5, horizontal=True, vertical=False)
self.tfm_gens.append(flip_gen)
image, transforms = T.apply_transform_gens(self.tfm_gens, image)
image_shape = image.shape[:2] # h, w
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:
for anno in dataset_dict["annotations"]:
if not self.mask_on:
anno.pop("segmentation", None)
annos = [
utils.transform_instance_annotations(
obj,
transforms,
image_shape,
keypoint_hflip_indices=self.keypoint_hflip_indices)
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
]
instances = utils.annotations_to_instances(
annos, image_shape, mask_format=self.mask_format)
if self.crop_gen and instances.has("gt_masks"):
instances.gt_boxes = instances.gt_masks.get_bounding_boxes()
dataset_dict["instances"] = utils.filter_empty_instances(instances)
return dataset_dict
def build_transform_gen(cfg, is_train):
"""
Create a list of :class:`TransformGen` from config.
Now it includes resizing and flipping.
Returns:
list[TransformGen]
"""
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__)
tfm_gens = []
tfm_gens.append(T.ResizeShortestEdge(min_size, max_size, sample_style))
if is_train:
if cfg.INPUT.VFLIP:
tfm_gens.append(T.RandomFlip(vertical=True, horizontal=False))
if cfg.INPUT.HFLIP:
tfm_gens.append(T.RandomFlip(vertical=False, horizontal=True))
if cfg.INPUT.RANDOM_CONTRAST.ENABLED:
tfm_gens.append(
T.RandomContrast(cfg.INPUT.RANDOM_CONTRAST.MIN,
cfg.INPUT.RANDOM_CONTRAST.MAX))
if cfg.INPUT.RANDOM_BRIGHTNESS.ENABLED:
tfm_gens.append(
T.RandomBrightness(cfg.INPUT.RANDOM_BRIGHTNESS.MIN,
cfg.INPUT.RANDOM_BRIGHTNESS.MAX))
logger.info("TransformGens used in training: " + str(tfm_gens))
return tfm_gens
def build_Pt_collect_train_aug(cfg):
augs = [
T.ResizeShortestEdge(cfg.INPUT.MIN_SIZE_TRAIN,
cfg.INPUT.MAX_SIZE_TRAIN,
cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING)
]
if cfg.INPUT.CROP.ENABLED:
augs.append(T.RandomCrop(
cfg.INPUT.CROP.TYPE,
cfg.INPUT.CROP.SIZE,
))
augs.append(T.RandomRotation(angle=[-10, 10], ))
augs.append(T.RandomFlip())
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_train_loader1(cls, cfg: CfgNode, mapper=None):
if mapper is None:
mapper = DatasetMapper(
cfg=cfg,
is_train=True,
augmentations=[
T.ResizeShortestEdge(
cfg.INPUT.MIN_SIZE_TRAIN,
cfg.INPUT.MAX_SIZE_TRAIN,
cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING,
),
T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE),
T.RandomFlip(),
],
)
return build_detection_train_loader(cfg, mapper=mapper)
def build_sem_seg_train_aug(cfg):
augs = [
T.ResizeShortestEdge(cfg.INPUT.MIN_SIZE_TRAIN,
cfg.INPUT.MAX_SIZE_TRAIN,
cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING)
]
if cfg.INPUT.CROP.ENABLED:
augs.append(
T.RandomCrop_CategoryAreaConstraint(
cfg.INPUT.CROP.TYPE,
cfg.INPUT.CROP.SIZE,
cfg.INPUT.CROP.SINGLE_CATEGORY_MAX_AREA,
cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE,
))
augs.append(T.RandomFlip())
return augs
def build_augmentation(cfg):
"""
Create a list of default :class:`Augmentation` from config.
Now it includes resizing and flipping.
Returns:
list[Augmentation]
"""
min_size = cfg.INPUT.MIN_SIZE_TRAIN
max_size = cfg.INPUT.MAX_SIZE_TRAIN
sample_style = cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING
augmentation = [
T.ResizeShortestEdge(min_size, max_size, sample_style),
T.RandomFlip(prob=0.5, horizontal=True, vertical=False)
]
return augmentation
