def __init__(self, config):
ModelBase.__init__(self, config)
# tree meta hyper parameters
self.max_layers = envs.get_global_env("tree_parameters.max_layers", 4,
self._namespace)
self.node_nums = envs.get_global_env("tree_parameters.node_nums", 26,
self._namespace)
self.leaf_node_nums = envs.get_global_env(
"tree_parameters.leaf_node_nums", 13, self._namespace)
self.output_positive = envs.get_global_env(
"tree_parameters.output_positive", True, self._namespace)
self.layer_node_num_list = envs.get_global_env(
"tree_parameters.layer_node_num_list", [2, 4, 7, 12],
self._namespace)
self.child_nums = envs.get_global_env("tree_parameters.child_nums", 2,
self._namespace)
self.tree_layer_path = envs.get_global_env("tree.tree_layer_path",
None, "train.startup")
# model training hyper parameter
self.node_emb_size = envs.get_global_env(
"hyper_parameters.node_emb_size", 64, self._namespace)
self.input_emb_size = envs.get_global_env(
"hyper_parameters.input_emb_size", 768, self._namespace)
self.act = envs.get_global_env("hyper_parameters.act", "tanh",
self._namespace)
self.neg_sampling_list = envs.get_global_env(
"hyper_parameters.neg_sampling_list", [1, 2, 3, 4],
self._namespace)
# model infer hyper parameter
self.topK = envs.get_global_env("hyper_parameters.node_nums", 1,
self._namespace)
self.batch_size = envs.get_global_env("batch_size", 1,
"evaluate.reader")
def __init__(self, config):
ModelBase.__init__(self, config)
self.dict_dim = 100
self.max_len = 10
self.cnn_dim = 32
self.cnn_filter_size = 128
self.emb_dim = 8
self.hid_dim = 128
self.class_dim = 2
def __init__(self, config):
ModelBase.__init__(self, config)
self.dict_dim = 100
self.max_len = 10
self.cnn_dim = 32
self.cnn_filter_size = 128
self.emb_dim = 8
self.hid_dim = 128
self.class_dim = 2
self.is_sparse = envs.get_global_env("hyper_parameters.is_sparse",
False)
def __init__(self, config):
ModelBase.__init__(self, config)
self.cost = None
self.metrics = {}
self.vocab_text_size = envs.get_global_env("vocab_text_size", None,
self._namespace)
self.vocab_tag_size = envs.get_global_env("vocab_tag_size", None,
self._namespace)
self.emb_dim = envs.get_global_env("emb_dim", None, self._namespace)
self.hid_dim = envs.get_global_env("hid_dim", None, self._namespace)
self.win_size = envs.get_global_env("win_size", None, self._namespace)
self.margin = envs.get_global_env("margin", None, self._namespace)
self.neg_size = envs.get_global_env("neg_size", None, self._namespace)
def __init__(self, config):
ModelBase.__init__(self, config)
self.cost = None
self.metrics = {}
self.vocab_text_size = envs.get_global_env(
"hyper_parameters.vocab_text_size")
self.vocab_tag_size = envs.get_global_env(
"hyper_parameters.vocab_tag_size")
self.emb_dim = envs.get_global_env("hyper_parameters.emb_dim")
self.hid_dim = envs.get_global_env("hyper_parameters.hid_dim")
self.win_size = envs.get_global_env("hyper_parameters.win_size")
self.margin = envs.get_global_env("hyper_parameters.margin")
self.neg_size = envs.get_global_env("hyper_parameters.neg_size")
def __init__(self, config):
"""R
"""
Model.__init__(self, config)
self._config = config
self._name = config['name']
f = open(config['layer_file'], 'r')
self._build_nodes = yaml.safe_load(f.read())
self._build_phase = ['input', 'param', 'summary', 'layer']
self._build_param = {
'layer': {},
'inner_layer': {},
'layer_extend': {},
'model': {}
}
self._inference_meta = {'dependency': {}, 'params': {}}
def __init__(self, config):
ModelBase.__init__(self, config)
def __init__(self, config):
ModelBase.__init__(self, config)
self.init_config()