def __init__(self, config):
"""Initialize NGCF_train Class.
Args:
config (dict): All the parameters for the model.
"""
self.config = config
super(NGCF_train, self).__init__(self.config)
self.load_dataset()
self.build_data_loader()
self.engine = NGCFEngine(self.config["model"])
def __init__(self, config):
"""Constructor
Args:
config (dict): All the parameters for the model
"""
self.config = config
super(NGCF_train, self).__init__(self.config)
self.load_dataset()
self.build_data_loader()
self.engine = NGCFEngine(self.config)
def train(self):
"""Train the model."""
self.monitor = Monitor(log_dir=self.config["system"]["run_dir"],
delay=1,
gpu_id=self.gpu_id)
self.model_save_dir = os.path.join(
self.config["system"]["model_save_dir"],
self.config["model"]["save_name"])
if self.config["model"]["loss"] == "bpr":
train_loader = self.data.instance_bpr_loader(
batch_size=self.config["model"]["batch_size"],
device=self.config["model"]["device_str"],
)
elif self.config["model"]["loss"] == "bce":
train_loader = self.data.instance_bce_loader(
num_negative=self.config["model"]["num_negative"],
batch_size=self.config["model"]["batch_size"],
device=self.config["model"]["device_str"],
)
else:
raise ValueError(
f"Unsupported loss type {self.config['loss']}, try other options: 'bpr' or 'bce'"
)
self.engine = NGCFEngine(self.config)
self._train(self.engine, train_loader, self.model_save_dir)
self.config["run_time"] = self.monitor.stop()
return self.eval_engine.best_valid_performance
class NGCF_train(TrainEngine):
""" An instance class from the TrainEngine base class
"""
def __init__(self, config):
"""Constructor
Args:
config (dict): All the parameters for the model
"""
self.config = config
super(NGCF_train, self).__init__(self.config)
self.load_dataset()
self.build_data_loader()
self.engine = NGCFEngine(self.config)
def build_data_loader(self):
# ToDo: Please define the directory to store the adjacent matrix
plain_adj, norm_adj, mean_adj = self.dataset.get_adj_mat()
norm_adj = sparse_mx_to_torch_sparse_tensor(norm_adj)
self.config["norm_adj"] = norm_adj
self.config["num_batch"] = self.dataset.n_train // config["batch_size"] + 1
self.config["n_users"] = self.dataset.n_users
self.config["n_items"] = self.dataset.n_items
def train(self):
self.monitor = Monitor(
log_dir=self.config["run_dir"], delay=1, gpu_id=self.gpu_id
)
self.model_dir = os.path.join(
self.config["model_save_dir"], self.config["save_name"]
)
for epoch in range(config["max_epoch"]):
print(f"Epoch {epoch} starts !")
print("-" * 80)
if epoch > 0 and self.eval_engine.n_no_update == 0:
# previous epoch have already obtained better result
self.engine.save_checkpoint(model_dir=self.model_dir)
if self.eval_engine.n_no_update >= MAX_N_UPDATE:
print(
"Early stop criterion triggered, no performance update for {:} times".format(
MAX_N_UPDATE
)
)
break
train_loader = self.dataset
self.engine.train_an_epoch(
epoch_id=epoch, train_loader=train_loader
)
self.eval_engine.train_eval(
self.dataset.valid[0], self.dataset.test[0], self.engine.model, epoch
)
self.config["run_time"] = self.monitor.stop()
def test(self):
self.engine.resume_checkpoint(model_dir=self.model_dir)
super(NGCF_train, self).test()