def load_image_gt(image,
mask,
boxes,
class_ids,
image_id,
config,
use_mini_mask=False):
#------------------------------#
# 原始shape
#------------------------------#
original_shape = image.shape
#------------------------------#
# 对图片和mask进行填充
#------------------------------#
image, window, scale, padding, crop = letterbox_image(
image, max_dim=config.IMAGE_MAX_DIM)
mask = letterbox_mask(mask, scale, padding, crop)
#------------------------------#
# 检漏，防止resize后目标消失
#------------------------------#
_idx = np.sum(mask, axis=(0, 1)) * (boxes[:, 3] - boxes[:, 1]) * (
boxes[:, 2] - boxes[:, 0]) > 0
mask = mask[:, :, _idx]
boxes = boxes[_idx]
class_ids = class_ids[_idx]
#------------------------------#
# 对mask再次进行缩小
#------------------------------#
if use_mini_mask:
mask = minimize_mask(boxes, mask, config.MINI_MASK_SHAPE)
#------------------------------#
# 生成Image_meta
#------------------------------#
active_class_ids = np.zeros(config.NUM_CLASSES)
active_class_ids[0] = 1
for id in class_ids:
active_class_ids[id] = 1
image_meta = compose_image_meta(image_id, original_shape, image.shape,
window, scale, active_class_ids)
return image, image_meta, class_ids, boxes, mask
def load_image_gt(dataset,
config,
image_id,
augment=False,
augmentation=None,
use_mini_mask=False):
# 载入图片和语义分割效果
image = dataset.load_image(image_id)
mask, class_ids = dataset.load_mask(image_id)
# print("\nbefore:",image_id,np.shape(mask),np.shape(class_ids))
# 原始shape
original_shape = image.shape
# 获得新图片，原图片在新图片中的位置，变化的尺度，填充的情况等
image, window, scale, padding, crop = utils.resize_image(
image,
min_dim=config.IMAGE_MIN_DIM,
min_scale=config.IMAGE_MIN_SCALE,
max_dim=config.IMAGE_MAX_DIM,
mode=config.IMAGE_RESIZE_MODE)
mask = utils.resize_mask(mask, scale, padding, crop)
# print("\nafter:",np.shape(mask),np.shape(class_ids))
# print(np.shape(image),np.shape(mask))
# 可以把图片进行翻转
if augment:
logging.warning("'augment' is deprecated. Use 'augmentation' instead.")
if random.randint(0, 1):
image = np.fliplr(image)
mask = np.fliplr(mask)
if augmentation:
import imgaug
# 可用于图像增强
MASK_AUGMENTERS = [
"Sequential", "SomeOf", "OneOf", "Sometimes", "Fliplr", "Flipud",
"CropAndPad", "Affine", "PiecewiseAffine"
]
def hook(images, augmenter, parents, default):
"""Determines which augmenters to apply to masks."""
return augmenter.__class__.__name__ in MASK_AUGMENTERS
image_shape = image.shape
mask_shape = mask.shape
det = augmentation.to_deterministic()
image = det.augment_image(image)
mask = det.augment_image(mask.astype(np.uint8),
hooks=imgaug.HooksImages(activator=hook))
assert image.shape == image_shape, "Augmentation shouldn't change image size"
assert mask.shape == mask_shape, "Augmentation shouldn't change mask size"
mask = mask.astype(np.bool)
# 检漏，防止某些层内部实际上不存在语义分割情况
_idx = np.sum(mask, axis=(0, 1)) > 0
# print("\nafterer:",np.shape(mask),np.shape(_idx))
mask = mask[:, :, _idx]
class_ids = class_ids[_idx]
# 找到mask对应的box
bbox = utils.extract_bboxes(mask)
active_class_ids = np.zeros([dataset.num_classes], dtype=np.int32)
source_class_ids = dataset.source_class_ids[dataset.image_info[image_id]
["source"]]
active_class_ids[source_class_ids] = 1
if use_mini_mask:
mask = utils.minimize_mask(bbox, mask, config.MINI_MASK_SHAPE)
# 生成Image_meta
image_meta = utils.compose_image_meta(image_id, original_shape,
image.shape, window, scale,
active_class_ids)
return image, image_meta, class_ids, bbox, mask