def __init__(self):
self.feature_encoder = load_obj(model_path, "feature_encoder")
self.trained_model = load_obj(model_path, "rf_recommender")
self.user_data = self.load_user_data()
self.movie_lookup = self.load_movie_names()
self.movie_ids = list(self.movie_lookup.keys())
self.c = metric.MetricClient()
def __init__(self):
model_parameters = load_obj(model_path, "model_parameters")
self.trained_model = CFModel(model_parameters["max_userid"],
model_parameters["max_movieid"],
model_parameters["k_factors"])
self.trained_model.load_weights(os.path.join(model_path, 'weights.h5'))
self.trained_model._make_predict_function()
self.class_names = ["class:rating"]
self.movie_lookup = self.load_movie_names()
self.movie_ids = list(self.movie_lookup.keys())
self.c = metric.MetricClient()
def __init__(self):
self.sess = tf.Session()
saver = tf.train.import_meta_graph(
os.path.join(model_path, "model.ckpt.meta"))
saver.restore(self.sess, os.path.join(model_path, "model.ckpt"))
self.c = metric.MetricClient()
def __init__(self):
self.model = pickle.load(open(model_path + "lr.pkl", 'rb'))
self.c = metric.MetricClient()
def __init__(self):
self.model = load(os.path.join(model_path, 'sk.pkl'))
self.c = metric.MetricClient()
def __init__(self):
self.sess = GPT2Generator.start_tf_sess()
self.load_gpt2(self.sess)
self.c = metric.MetricClient()
def __init__(self): self.model = keras.models.load_model(os.path.join(model_path, "saved_models/keras_cifar10_trained_model.h5")) self.c = metric.MetricClient()