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=0.01, 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=0.01, 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=0.01, epsilon=None, 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') if epsilon is None: epsilon = K.epsilon() self.epsilon = epsilon self.initial_decay = decay
def __init__(self, lr=1.0, rho=0.95, epsilon=None, decay=0., **kwargs): super(Adadelta, 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') if epsilon is None: epsilon = K.epsilon() self.rho = rho self.epsilon = epsilon 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) 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 __init__(self, optimizer): # pylint: disable=super-init-not-called self.optimizer = optimizer with K.name_scope(self.__class__.__name__): if context.in_graph_mode(): self.iterations = K.variable(0, dtype='int64', name='iterations')
def __init__(self, lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=None, 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') if epsilon is None: epsilon = K.epsilon() self.epsilon = epsilon self.schedule_decay = schedule_decay
def __init__(self, lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=None, 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') if epsilon is None: epsilon = K.epsilon() self.epsilon = epsilon self.initial_decay = decay
def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0., amsgrad=False, **kwargs): super(Adam, 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') if epsilon is None: epsilon = K.epsilon() self.epsilon = epsilon self.initial_decay = decay self.amsgrad = amsgrad
if mask[i, j] == 0.: for k in range(3): generated[i,j][k] = bg_color[k] return generated def pooling_func(x): if pooltype == 1: return AveragePooling2D((2, 2), strides=(2, 2))(x) else: return MaxPooling2D((2, 2), strides = (2,2))(x) # get tensor representations of our images base_image = K.variable(preprocess_image(base_image_path, True, read_mode=read_mode)) style_reference_images = [] for style_path in style_image_paths: style_reference_images.append(K.variable(preprocess_image(style_path))) # this will contain our generated image combination_image = K.placeholder((1, img_width, img_height, 3)) image_tensors = [base_image] for style_image_tensor in style_reference_images: image_tensors.append(style_image_tensor) image_tensors.append(combination_image) nb_tensors = len(image_tensors) print("nb_tensors", nb_tensors)
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')