def load_mask(self, image_id):
""" Generate instance masks for an image.
Returns:
masks: A bool array of shape [height, width, instance count] with one mask per instance.
class_ids: a 1D array of class IDs of the instance masks.
"""
# If not a sidelobe dataset image, delegate to parent class.
image_info = self.image_info[image_id]
if image_info["source"] != "sidelobe":
return super(self.__class__, self).load_mask(image_id)
# Set bitmap mask of shape [height, width, instance_count]
info = self.image_info[image_id]
filename = info["path_mask"]
class_id = info["class_id"]
# Read mask
data, header = utils.read_fits(filename,
stretch=False,
normalize=False,
convertToRGB=False)
height = data.shape[0]
width = data.shape[1]
data = data.astype(np.bool)
mask = np.zeros([height, width, 1], dtype=np.bool)
mask[:, :, 0] = data
instance_counts = np.full([mask.shape[-1]], class_id, dtype=np.int32)
# Return mask, and array of class IDs of each instance
return mask, instance_counts
def load_image(self, image_id): """Load the specified image and return a [H, W, 1] Numpy array.""" # Load image filename = self.image_info[image_id]['path'] convertToRGB: bool = False image, header = utils.read_fits(filename, stretch=True, normalize=True, convertToRGB=convertToRGB) if not convertToRGB: image = np.expand_dims(image, axis=2) return image
def load_image(self, image_id):
"""Load the specified image and return a [H,W,3] Numpy array."""
# Load image
filename = self.image_info[image_id]['path']
image, header = utils.read_fits(filename,
stretch=True,
normalize=True,
convertToRGB=True)
return image
def load_gt_mask(self, image_id): """ Load gt mask """ # Read filename info = self.image_info[image_id] filename = info["path_mask"] class_id = info["class_id"] # Read mask data, header = utils.read_fits(filename, stretch=False, normalize=False, convertToRGB=False) height = data.shape[0] width = data.shape[1] data = data.astype(np.bool) mask = np.zeros([height, width, 1], dtype=np.bool) mask[:, :, 0] = data return mask
def load_image(self, image_id):
"""Load the specified image and return a [H,W,3] Numpy array."""
# Load image
filename = self.image_info[image_id]['path']
image, header = utils.read_fits(filename,
stretch=True,
normalize=True,
convertToRGB=True)
#image = skimage.io.imread(filename)
# If grayscale. Convert to RGB for consistency.
#if image.ndim != 3:
# image = skimage.color.gray2rgb(image)
# If has an alpha channel, remove it for consistency
#if image.shape[-1] == 4:
# image = image[..., :3]
return image
def detect_and_color_splash(model, image_path):
# Run model detection and generate the color splash effect
print("Running on {}".format(args.image))
# Read image
#image = skimage.io.imread(args.image)
image, header = utils.read_fits(filename=image_path,
stretch=True,
normalize=True,
convertToRGB=True)
# Detect objects
r = model.detect([image], verbose=1)[0]
# Color splash
splash = color_splash(image, r['masks'])
# Save output
file_name = "splash_{:%Y%m%dT%H%M%S}.png".format(datetime.datetime.now())
skimage.io.imsave(file_name, splash)
def read_img(self):
""" Read input FITS image """
res= utils.read_fits(
self.image_path,
stretch=False,
normalize=False,
convertToRGB=False
)
if not res:
logger.error("Failed to read image %s!" % self.image_path)
return -1
self.img_data= res[0]
self.img_header= res[1]
self.nx= self.img_data.shape[1]
self.ny= self.img_data.shape[0]
logger.info("Input image %s has size %d x %d..." % (self.image_path,self.nx,self.ny))
return 0