def __init__(self, lr=0.01, epsilon=1e-8, decay=0., **kwargs): super(Adagrad, self).__init__(**kwargs) self.lr = K.variable(lr, name='lr') self.epsilon = epsilon self.decay = K.variable(decay, name='decay') self.initial_decay = decay self.iterations = K.variable(0., name='iterations')
def __init__(self, lr=0.01, epsilon=1e-8, decay=0., **kwargs):
super(Adagrad, self).__init__(**kwargs)
self.lr = K.variable(lr, name='lr')
self.epsilon = epsilon
self.decay = K.variable(decay, name='decay')
self.initial_decay = decay
self.iterations = K.variable(0., name='iterations')
def __init__(self, lr=1.0, rho=0.95, epsilon=1e-8, decay=0., **kwargs): super(Adadelta, self).__init__(**kwargs) self.lr = K.variable(lr, name='lr') self.rho = rho self.epsilon = epsilon self.decay = K.variable(decay, name='decay') self.initial_decay = decay self.iterations = K.variable(0., name='iterations')
def __init__(self, lr=0.001, rho=0.9, epsilon=1e-8, decay=0., **kwargs): super(RMSprop, self).__init__(**kwargs) self.lr = K.variable(lr, name='lr') self.rho = K.variable(rho, name='rho') self.epsilon = epsilon self.decay = K.variable(decay, name='decay') self.initial_decay = decay self.iterations = K.variable(0., name='iterations')
def __init__(self, lr=0.01, momentum=0., decay=0., nesterov=False, **kwargs): super(SGD, self).__init__(**kwargs) self.iterations = K.variable(0., name='iterations') self.lr = K.variable(lr, name='lr') self.momentum = K.variable(momentum, name='momentum') self.decay = K.variable(decay, name='decay') self.initial_decay = decay self.nesterov = nesterov
def __init__(self, lr=0.01, momentum=0., decay=0., nesterov=False, **kwargs): super(SGD, self).__init__(**kwargs) self.iterations = K.variable(0., name='iterations') self.lr = K.variable(lr, name='lr') self.momentum = K.variable(momentum, name='momentum') self.decay = K.variable(decay, name='decay') self.initial_decay = decay self.nesterov = nesterov
def __init__(self, lr=1.0, rho=0.95, epsilon=1e-8, decay=0., **kwargs):
super(Adadelta, self).__init__(**kwargs)
self.lr = K.variable(lr, name='lr')
self.rho = rho
self.epsilon = epsilon
self.decay = K.variable(decay, name='decay')
self.initial_decay = decay
self.iterations = K.variable(0., name='iterations')
def __init__(self, lr=0.01, epsilon=1e-8, decay=0., **kwargs):
super(Adagrad, self).__init__(**kwargs)
with K.name_scope(self.__class__.__name__):
self.lr = K.variable(lr, name='lr')
self.decay = K.variable(decay, name='decay')
self.iterations = K.variable(0, dtype='int64', name='iterations')
self.epsilon = epsilon
self.initial_decay = decay
def __init__(self, lr=0.001, rho=0.9, epsilon=1e-8, decay=0., **kwargs):
super(RMSprop, self).__init__(**kwargs)
self.lr = K.variable(lr, name='lr')
self.rho = K.variable(rho, name='rho')
self.epsilon = epsilon
self.decay = K.variable(decay, name='decay')
self.initial_decay = decay
self.iterations = K.variable(0., name='iterations')
def __init__(self, lr=0.01, momentum=0., decay=0., nesterov=False, **kwargs):
super(SGD, self).__init__(**kwargs)
with K.name_scope(self.__class__.__name__):
self.iterations = K.variable(0, dtype='int64', name='iterations')
self.lr = K.variable(lr, name='lr')
self.momentum = K.variable(momentum, name='momentum')
self.decay = K.variable(decay, name='decay')
self.initial_decay = decay
self.nesterov = nesterov
def __init__(self,
lr=0.002,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-8,
schedule_decay=0.004,
**kwargs):
super(Nadam, self).__init__(**kwargs)
self.iterations = K.variable(0., name='iterations')
self.m_schedule = K.variable(1., name='m_schedule')
self.lr = K.variable(lr, name='lr')
self.beta_1 = K.variable(beta_1, name='beta_1')
self.beta_2 = K.variable(beta_2, name='beta_2')
self.epsilon = epsilon
self.schedule_decay = schedule_decay
def __init__(self,
lr=0.002,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-8,
decay=0.,
**kwargs):
super(Adamax, self).__init__(**kwargs)
self.iterations = K.variable(0., name='iterations')
self.lr = K.variable(lr, name='lr')
self.beta_1 = K.variable(beta_1, name='beta_1')
self.beta_2 = K.variable(beta_2, name='beta_2')
self.epsilon = epsilon
self.decay = K.variable(decay, name='decay')
self.initial_decay = decay
def __init__(self,
lr=0.002,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-8,
decay=0.,
**kwargs):
super(Adamax, self).__init__(**kwargs)
self.iterations = K.variable(0., name='iterations')
self.lr = K.variable(lr, name='lr')
self.beta_1 = K.variable(beta_1, name='beta_1')
self.beta_2 = K.variable(beta_2, name='beta_2')
self.epsilon = epsilon
self.decay = K.variable(decay, name='decay')
self.initial_decay = decay
def __init__(self,
lr=0.002,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-8,
schedule_decay=0.004,
**kwargs):
super(Nadam, self).__init__(**kwargs)
self.iterations = K.variable(0., name='iterations')
self.m_schedule = K.variable(1., name='m_schedule')
self.lr = K.variable(lr, name='lr')
self.beta_1 = K.variable(beta_1, name='beta_1')
self.beta_2 = K.variable(beta_2, name='beta_2')
self.epsilon = epsilon
self.schedule_decay = schedule_decay
def yolo_eval(yolo_outputs,
image_shape,
max_boxes=10,
score_threshold=.6,
iou_threshold=.5):
"""Evaluate YOLO model on given input batch and return filtered boxes."""
box_xy, box_wh, box_confidence, box_class_probs = yolo_outputs
boxes = yolo_boxes_to_corners(box_xy, box_wh)
boxes, scores, classes = yolo_filter_boxes(boxes,
box_confidence,
box_class_probs,
threshold=score_threshold)
# Scale boxes back to original image shape.
height = image_shape[0]
width = image_shape[1]
image_dims = K.stack([height, width, height, width])
image_dims = K.reshape(image_dims, [1, 4])
boxes = boxes * image_dims
# TODO: Something must be done about this ugly hack!
max_boxes_tensor = K.variable(max_boxes, dtype='int32')
K.get_session().run(tf.variables_initializer([max_boxes_tensor]))
nms_index = tf.image.non_max_suppression(boxes,
scores,
max_boxes_tensor,
iou_threshold=iou_threshold)
boxes = K.gather(boxes, nms_index)
scores = K.gather(scores, nms_index)
classes = K.gather(classes, nms_index)
return boxes, scores, classes
def __init__(self,
lr=0.002,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-8,
schedule_decay=0.004,
**kwargs):
super(Nadam, self).__init__(**kwargs)
with K.name_scope(self.__class__.__name__):
self.iterations = K.variable(0, dtype='int64', name='iterations')
self.m_schedule = K.variable(1., name='m_schedule')
self.lr = K.variable(lr, name='lr')
self.beta_1 = K.variable(beta_1, name='beta_1')
self.beta_2 = K.variable(beta_2, name='beta_2')
self.epsilon = epsilon
self.schedule_decay = schedule_decay
def __init__(self,
lr=0.002,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-8,
decay=0.,
**kwargs):
super(Adamax, self).__init__(**kwargs)
with K.name_scope(self.__class__.__name__):
self.iterations = K.variable(0, dtype='int64', name='iterations')
self.lr = K.variable(lr, name='lr')
self.beta_1 = K.variable(beta_1, name='beta_1')
self.beta_2 = K.variable(beta_2, name='beta_2')
self.decay = K.variable(decay, name='decay')
self.epsilon = epsilon
self.initial_decay = decay
def call(self, x, mask=None):
input_shape = K.int_shape(x)
layer_width = input_shape[self.waxis]
layer_height = input_shape[self.haxis]
img_width = self.img_size[0]
img_height = self.img_size[1]
# define prior boxes shapes
box_widths = []
box_heights = []
for ar in self.aspect_ratios:
if ar == 1 and len(box_widths) == 0:
box_widths.append(self.min_size)
box_heights.append(self.min_size)
elif ar == 1 and len(box_widths) > 0:
box_widths.append(np.sqrt(self.min_size * self.max_size))
box_heights.append(np.sqrt(self.min_size * self.max_size))
elif ar != 1:
box_widths.append(self.min_size * np.sqrt(ar))
box_heights.append(self.min_size / np.sqrt(ar))
box_widths = 0.5 * np.array(box_widths)
box_heights = 0.5 * np.array(box_heights)
# define centers of prior boxes
step_x = img_width / layer_width
step_y = img_height / layer_height
linx = np.linspace(0.5 * step_x, img_width - 0.5 * step_x, layer_width)
liny = np.linspace(0.5 * step_y, img_height - 0.5 * step_y,
layer_height)
centers_x, centers_y = np.meshgrid(linx, liny)
centers_x = centers_x.reshape(-1, 1)
centers_y = centers_y.reshape(-1, 1)
# define xmin, ymin, xmax, ymax of prior boxes
num_priors_ = len(self.aspect_ratios)
prior_boxes = np.concatenate((centers_x, centers_y), axis=1)
prior_boxes = np.tile(prior_boxes, (1, 2 * num_priors_))
prior_boxes[:, ::4] -= box_widths
prior_boxes[:, 1::4] -= box_heights
prior_boxes[:, 2::4] += box_widths
prior_boxes[:, 3::4] += box_heights
prior_boxes[:, ::2] /= img_width
prior_boxes[:, 1::2] /= img_height
prior_boxes = prior_boxes.reshape(-1, 4)
if self.clip:
prior_boxes = np.minimum(np.maximum(prior_boxes, 0.0), 1.0)
# define variances
num_boxes = len(prior_boxes)
if len(self.variances) == 1:
variances = np.ones((num_boxes, 4)) * self.variances[0]
elif len(self.variances) == 4:
variances = np.tile(self.variances, (num_boxes, 1))
else:
raise Exception('Must provide one or four variances.')
prior_boxes = np.concatenate((prior_boxes, variances), axis=1)
prior_boxes_tensor = K.expand_dims(K.variable(prior_boxes), 0)
pattern = [tf.shape(x)[0], 1, 1]
prior_boxes_tensor = tf.tile(prior_boxes_tensor, pattern)
return prior_boxes_tensor
def __init__(self, optimizer): # pylint: disable=super-init-not-called
self.optimizer = optimizer
self.iterations = K.variable(0., name='iterations')
self.updates = []
def build(self, input_shape):
self.input_spec = [InputSpec(shape=input_shape)]
shape = (input_shape[self.axis], )
init_gamma = self.scale * np.ones(shape)
self.gamma = K.variable(init_gamma, name='{}_gamma'.format(self.name))
self.trainable_weights = [self.gamma]
def __init__(self, optimizer): # pylint: disable=super-init-not-called self.optimizer = optimizer self.iterations = K.variable(0., name='iterations') self.updates = []
def __init__(self, optimizer): # pylint: disable=super-init-not-called
self.optimizer = optimizer
with K.name_scope(self.__class__.__name__):
self.iterations = K.variable(0, dtype='int64', name='iterations')
