def make_ground_truth(self, labels: List[Label3D]):
"""
return shape: 252*252*4, 252*252*4*3, 252*252*4*3, 252*252*4, 252*252*4, 252*252*4*4
"""
# filter labels by classes (cars, pedestrians and Trams)
# Label has 4 properties (Classification (0th index of labels file),
# centroid coordinates, dimensions, yaw)
labels = list(
filter(lambda x: x.classification in self.classes, labels))
if len(labels) == 0:
pX, pY = int(self.Xn / self.downscaling_factor), int(
self.Yn / self.downscaling_factor)
a = int(self.anchor_dims.shape[0])
return np.zeros((pX, pY, a), dtype='float32'), np.zeros((pX, pY, a, self.nb_dims), dtype='float32'), \
np.zeros((pX, pY, a, self.nb_dims), dtype='float32'), np.zeros((pX, pY, a), dtype='float32'), \
np.zeros((pX, pY, a, self.nb_classes), dtype='float64')
# For each label file, generate these properties except for the Don't care class
target_positions = np.array([label.centroid for label in labels],
dtype=np.float32)
target_dimension = np.array([label.dimension for label in labels],
dtype=np.float32)
target_yaw = np.array([label.yaw for label in labels],
dtype=np.float32)
target_class = np.array(
[self.classes[label.classification] for label in labels],
dtype=np.int32)
assert np.all(target_yaw >= -np.pi) & np.all(target_yaw <= np.pi)
assert len(target_positions) == len(target_dimension) == len(
target_yaw) == len(target_class)
target, pos, neg = createPillarsTarget(
target_positions, target_dimension, target_yaw, target_class,
self.anchor_dims, self.anchor_z, self.anchor_yaw,
self.positive_iou_threshold, self.negative_iou_threshold,
self.nb_classes, self.downscaling_factor, self.x_step, self.y_step,
self.x_min, self.x_max, self.y_min, self.y_max, self.z_min,
self.z_max, False)
self.pos_cnt += pos
self.neg_cnt += neg
# return a merged target view for all objects in the ground truth and get categorical labels
sel = select_best_anchors(target)
# class_label = np.array(sel[...,9],dtype='uint8').tolist()
# print(class_label)
# one_hot_encode = to_categorical(sel[..., 9], num_classes=self.nb_classes)
one_hot_encode = tf.keras.utils.to_categorical(
sel[..., 9], num_classes=self.nb_classes, dtype='float64')
# 252*252*4, 252*252*4*3, 252*252*4*3 252*252*4 252*252*4, 252*252*4*4
return sel[..., 0], sel[...,
1:4], sel[...,
4:7], sel[...,
7], sel[...,
8], one_hot_encode
def make_ground_truth(self, labels: List[Label3D]):
# filter by class
labels = list(filter(lambda x: x.classification in self.classes, labels))
if len(labels) == 0:
return
target_positions = np.array([label.centroid for label in labels], dtype=np.float32)
target_dimension = np.array([label.dimension for label in labels], dtype=np.float32)
target_yaw = np.array([label.yaw for label in labels], dtype=np.float32)
target_class = np.array([self.classes[label.classification] for label in labels], dtype=np.int32)
assert np.all(target_yaw >= -np.pi) & np.all(target_yaw <= np.pi)
assert len(target_positions) == len(target_dimension) == len(target_yaw) == len(target_class)
target = createPillarsTarget(target_positions,
target_dimension,
target_yaw,
target_class,
self.anchor_dims,
self.anchor_z,
self.anchor_yaw,
self.positive_iou_threshold,
self.negative_iou_threshold,
self.nb_classes,
self.downscaling_factor,
self.x_step,
self.y_step,
self.x_min,
self.x_max,
self.y_min,
self.y_max,
self.z_min,
self.z_max,
False)
best_anchors = target[..., 0:1].argmax(0)
selection = select(target, best_anchors)
# one hot encoding of class
clf = selection[..., 9]
clf[clf == -1] = 0
ohe = np.eye(self.nb_classes)[np.array(clf, dtype=np.int32).reshape(-1)]
ohe = ohe.reshape(list(clf.shape) + [self.nb_classes])
return selection[..., 0], selection[..., 1:4], selection[..., 4:7], selection[..., 7], selection[..., 8], ohe
def test_pillar_target_creation():
dims = np.array([[3.7, 1.6, 1.4], [3.7, 1.6, 1.4], [0.8, 0.6, 1.7]],
dtype=np.float32)
posn = np.array([[50, 10, 0], [20, 0, 0], [30, 5, 0]],
dtype=np.float32)
yaws = np.array([0, 0, 90], dtype=np.float32)
target = createPillarsTarget(posn, dims, yaws,
np.array([1, 1, 2],
dtype=np.int32), dims[[0, 2]],
np.array([0, 0], dtype=np.float32),
np.array([0, 90],
dtype=np.float32), 0.5, 0.4, 10,
2, 0.1, 0.1, 0, 80, -40, 40, -3, 1, True)
assert target.shape == (3, 400, 400, 2, 10)
assert (target[..., 0] == 1).sum() == 83
selected = target[..., 0:1].argmax(axis=0)
target = select(target, selected)
assert (target.shape == (400, 400, 2, 10))