def cluster(self, sem_seg_prediction, ins_seg_prediction,
n_objects_prediction):
seg_height, seg_width = ins_seg_prediction.shape[1:]
sem_seg_prediction = sem_seg_prediction.cpu().numpy()
sem_seg_prediction = sem_seg_prediction.argmax(0).astype(np.uint8)
embeddings = ImageUtilities.coordinate_adder(
seg_height, seg_width)(ins_seg_prediction)
embeddings = embeddings.cpu().numpy()
embeddings = embeddings.transpose(1, 2, 0) # h, w, c
n_objects_prediction = n_objects_prediction.cpu().numpy()[0]
embeddings = np.stack([
embeddings[:, :, i][sem_seg_prediction != 0]
for i in range(embeddings.shape[2])
],
axis=1)
clustering = SpectralClustering(n_clusters=n_objects_prediction,
eigen_solver=None,
random_state=None,
n_init=10,
gamma=1.0,
affinity='rbf',
n_neighbors=10,
eigen_tol=0.0,
assign_labels='discretize',
degree=3,
coef0=1,
kernel_params=None,
n_jobs=self.n_workers).fit(embeddings)
labels = clustering.labels_
instance_mask = np.zeros((seg_height, seg_width), dtype=np.uint8)
fg_coords = np.where(sem_seg_prediction != 0)
for si in range(len(fg_coords[0])):
y_coord = fg_coords[0][si]
x_coord = fg_coords[1][si]
_label = labels[si] + 1
instance_mask[y_coord, x_coord] = _label
return sem_seg_prediction, instance_mask, n_objects_prediction
def __init__(self, resize_height, resize_width, mean, std, use_coordinates,
model, n_workers):
self.normalizer = ImageUtilities.image_normalizer(mean, std)
self.use_coordinates = use_coordinates
self.resize_height = resize_height
self.resize_width = resize_width
self.model = model
self.n_workers = n_workers
self.img_resizer = ImageUtilities.image_resizer(
self.resize_height, self.resize_width)
if self.use_coordinates:
self.coordinate_adder = ImageUtilities.coordinate_adder(
self.resize_height, self.resize_width)
def __init__(self, resize_height, resize_width, mean,
std, use_coordinates, model, n_workers):
self.normalizer = ImageUtilities.image_normalizer(mean, std)
self.use_coordinates = use_coordinates
self.resize_height = resize_height
self.resize_width = resize_width
self.model = model
self.n_workers = n_workers
self.img_resizer = ImageUtilities.image_resizer(
self.resize_height, self.resize_width)
if self.use_coordinates:
self.coordinate_adder = ImageUtilities.coordinate_adder(
self.resize_height, self.resize_width)
def cluster(self, sem_seg_prediction, ins_seg_prediction,
n_objects_prediction):
seg_height, seg_width = ins_seg_prediction.shape[1:]
sem_seg_prediction = sem_seg_prediction.cpu().numpy()
sem_seg_prediction = sem_seg_prediction.argmax(0).astype(np.uint8)
embeddings = ImageUtilities.coordinate_adder(
seg_height, seg_width)(ins_seg_prediction)
embeddings = embeddings.cpu().numpy()
embeddings = embeddings.transpose(1, 2, 0) # h, w, c
n_objects_prediction = n_objects_prediction.cpu().numpy()[0]
embeddings = np.stack([embeddings[:, :, i][sem_seg_prediction != 0]
for i in range(embeddings.shape[2])], axis=1)
clustering = SpectralClustering(n_clusters=n_objects_prediction,
eigen_solver=None, random_state=None,
n_init=10, gamma=1.0, affinity='rbf',
n_neighbors=10, eigen_tol=0.0,
assign_labels='discretize', degree=3,
coef0=1,
kernel_params=None,
n_jobs=self.n_workers).fit(embeddings)
labels = clustering.labels_
instance_mask = np.zeros((seg_height, seg_width), dtype=np.uint8)
fg_coords = np.where(sem_seg_prediction != 0)
for si in range(len(fg_coords[0])):
y_coord = fg_coords[0][si]
x_coord = fg_coords[1][si]
_label = labels[si] + 1
instance_mask[y_coord, x_coord] = _label
return sem_seg_prediction, instance_mask, n_objects_prediction
def __init__(self,
mode,
n_classes,
max_n_objects,
mean,
std,
image_height,
image_width,
random_hor_flipping=True,
random_ver_flipping=True,
random_90x_rotation=True,
random_rotation=True,
random_color_jittering=True,
use_coordinates=False):
self._mode = mode
self.n_classes = n_classes
self.max_n_objects = max_n_objects
assert self._mode in ['training', 'test']
self.mean = mean
self.std = std
self.image_height = image_height
self.image_width = image_width
self.random_horizontal_flipping = random_hor_flipping
self.random_vertical_flipping = random_ver_flipping
self.random_90x_rotation = random_90x_rotation
self.random_rotation = random_rotation
self.random_color_jittering = random_color_jittering
self.use_coordinates = use_coordinates
if self._mode == 'training':
if self.random_horizontal_flipping:
self.horizontal_flipper = IU.image_random_horizontal_flipper()
if self.random_vertical_flipping:
self.vertical_flipper = IU.image_random_vertical_flipper()
if self.random_90x_rotation:
self.rotator_90x = IU.image_random_90x_rotator()
if self.random_rotation:
self.rotator = IU.image_random_rotator(expand=True)
if self.random_color_jittering:
self.color_jitter = IU.image_random_color_jitter(
brightness=0.1, contrast=0.1, saturation=0.1, hue=0.1)
self.img_resizer = IU.image_resizer(self.image_height,
self.image_width)
self.ann_resizer = IU.image_resizer(self.image_height,
self.image_width,
interpolation=Image.NEAREST)
else:
self.img_resizer = IU.image_resizer(self.image_height,
self.image_width)
self.ann_resizer = IU.image_resizer(self.image_height,
self.image_width,
interpolation=Image.NEAREST)
self.image_normalizer = IU.image_normalizer(self.mean, self.std)
if self.use_coordinates:
self.coordinate_adder = IU.coordinate_adder(
self.image_height, self.image_width)
