def main(args):
ts = time.strftime('%Y-%b-%d-%H:%M:%S', time.gmtime())
seed = 1111
set_seed(seed)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print('device', device, torch.cuda.current_device())
# exit()
data_obj = _DATA()
if "yelp" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_yelp_restaurant(
args)
if "movie" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_movie(args)
if "beer" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_beer(args)
if "wine" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_wine(args)
if "lthing" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_movie(args)
if args.train:
now_time = datetime.now()
time_name = str(now_time.month) + "_" + str(now_time.day) + "_" + str(
now_time.hour) + "_" + str(now_time.minute)
model_file = os.path.join(args.model_path,
args.data_name + "_" + args.model_name)
if not os.path.isdir(model_file):
print("create a directory", model_file)
os.mkdir(model_file)
args.model_file = model_file + "/model_best_" + time_name + ".pt"
print("model_file", model_file)
print("vocab_size", vocab_obj.vocab_size)
print("user num", vocab_obj.user_num)
print("item num", vocab_obj.item_num)
pretrain_model_file = args.pretrain_model_file
pretrain_network = None
if pretrain_model_file != "":
pretrain_network = BPR(vocab_obj, args, device)
pretrain_model_abs_file = os.path.join(args.model_path,
pretrain_model_file)
print("pretrain_model_abs_file", pretrain_model_abs_file)
checkpoint = torch.load(pretrain_model_abs_file)
pretrain_network.load_state_dict(checkpoint['model'])
network = _ATTR_NETWORK(vocab_obj, args, device)
total_param_num = 0
for name, param in network.named_parameters():
if param.requires_grad:
param_num = param.numel()
total_param_num += param_num
print(name, "\t", param_num)
print("total parameters num", total_param_num)
if args.train:
logger_obj = _LOGGER()
logger_obj.f_add_writer(args)
optimizer = _OPTIM(network.parameters(), args)
trainer = _TRAINER(vocab_obj, args, device)
trainer.f_train(pretrain_network, train_data, valid_data, network,
optimizer, logger_obj)
logger_obj.f_close_writer()
if args.eval:
print("=" * 10, "eval", "=" * 10)
eval_obj = _EVAL(vocab_obj, args, device)
network = network.to(device)
eval_obj.f_init_eval(network, args.model_file, reload_model=True)
# eval_obj.f_eval_new_user(train_data, valid_data)
eval_obj.f_eval(train_data, valid_data)
if args.test:
print("=" * 10, "eval", "=" * 10)
infer_obj = _INFER(vocab_obj, args, device)
network = network.to(device)
infer_obj.f_init_infer(network, args.model_file, reload_model=True)
infer_obj.f_infer(train_data, valid_data)
def main(args):
ts = time.strftime('%Y-%b-%d-%H:%M:%S', time.gmtime())
seed = 1111
set_seed(seed)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print('device', device)
local_rank = None
if args.parallel:
local_rank = args.local_rank
torch.distributed.init_process_group(backend="nccl")
device = torch.device('cuda:{}'.format(local_rank))
data_obj = _DATA()
if "beer" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_movie(args)
if "wine" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_movie(args)
if "yelp" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_yelp(args)
if "movie" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_movie(args)
if "lthing" in args.data_name:
train_data, valid_data, vocab_obj = data_obj.f_load_data_movie(args)
if args.train:
now_time = datetime.now()
time_name = str(now_time.month)+"_"+str(now_time.day)+"_"+str(now_time.hour)+"_"+str(now_time.minute)
model_file = os.path.join(args.model_path, args.data_name+"_"+args.model_name)
if not os.path.isdir(model_file):
print("create a directory", model_file)
os.mkdir(model_file)
args.model_file = model_file+"/model_best_"+time_name+".pt"
print("model_file", model_file)
print("vocab_size", vocab_obj.vocab_size)
print("user num", vocab_obj.user_num)
print("item num", vocab_obj.item_num)
network = _ATTR_NETWORK(vocab_obj, args, device)
total_param_num = 0
for name, param in network.named_parameters():
if param.requires_grad:
param_num = param.numel()
total_param_num += param_num
print(name, "\t", param_num)
print("total parameters num", total_param_num)
if args.train:
logger_obj = _LOGGER()
logger_obj.f_add_writer(args)
if args.parallel:
network = torch.nn.parallel.DistributedDataParallel(network, device_ids=[local_rank], output_device=local_rank, find_unused_parameters=True)
optimizer = _OPTIM(network.parameters(), args)
trainer = _TRAINER(args, device)
trainer.f_train(train_data, valid_data, network, optimizer, logger_obj, local_rank)
logger_obj.f_close_writer()
if args.eval:
print("="*10, "eval", "="*10)
eval_obj = _EVAL(vocab_obj, args, device)
network = network.to(device)
eval_obj.f_init_eval(network, args.model_file, reload_model=True)
# eval_obj.f_eval_new_user(train_data, valid_data)
eval_obj.f_eval(train_data, valid_data)
