def main(args):
ts = time.strftime('%Y-%b-%d-%H:%M:%S', time.gmtime())
#### get data
# with open(os.path.join(args.data_dir, args.data_file), 'rb') as file:
# data = pickle.load(file)
data_obj = _Data()
train_data, valid_data, vocab_obj = data_obj.f_load_data_amazon(args)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
logger_obj = Logger()
logger_obj.f_add_writer(args)
### add count parameters
if not args.test:
now_time = datetime.datetime.now()
time_name = str(now_time.day)+"_"+str(now_time.month)+"_"+str(now_time.hour)+"_"+str(now_time.minute)
model_file = os.path.join(args.model_path, args.model_name+"/model_best_"+time_name+".pt")
args.model_file = model_file
print("vocab_size", len(vocab_obj.m_w2i))
### get model
# user_num = 10
network = REVIEWDI(vocab_obj, args, device=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 not args.test:
optimizer = Optimizer(network.parameters(), args)
trainer = TRAINER(vocab_obj, args, device)
trainer.f_train(train_data, valid_data, network, optimizer, logger_obj)
if args.test:
print("="*10, "eval", "="*10)
# eval_obj = EVAL(vocab_obj, args, device)
# eval_obj.f_init_eval(network, args.model_file, reload_model=True)
# eval_obj.f_eval(valid_data)
print("="*10, "inference", "="*10)
infer = INFER(vocab_obj, args, device)
infer.f_init_infer(network, args.model_file, reload_model=True)
infer.f_inference(valid_data)
logger_obj.f_close_writer()
def main(args):
ts = time.strftime('%Y-%b-%d-%H:%M:%S', time.gmtime())
#### get data
data_obj = _Data()
train_data, valid_data, vocab_obj = data_obj.f_load_data_google(args)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
logger_obj = Logger()
logger_obj.f_add_writer(args)
# print(vocab_obj.m_w2i['the'])
# exit()
if not args.test:
now_time = datetime.datetime.now()
time_name = str(now_time.day) + "_" + str(now_time.month) + "_" + str(
now_time.hour) + "_" + str(now_time.minute)
model_file = os.path.join(
args.model_path,
args.model_name + "/model_best_" + time_name + ".pt")
args.model_file = model_file
### add count parameters
### get model
vocab_size = len(vocab_obj.m_w2i)
print("vocab_size", vocab_size)
network = REVIEWDI(vocab_obj, args, device=device)
if not args.test:
optimizer = Optimizer(network.parameters(), args)
trainer = TRAINER(vocab_obj, args, device)
trainer.f_train(train_data, valid_data, network, optimizer, logger_obj)
if args.test:
print("=" * 10, "eval")
# eval_obj = EVAL(vocab_obj, args, device)
# eval_obj.f_init_eval(network, args.model_file, reload_model=True)
# eval_obj.f_eval(valid_data)
print("=" * 10, "inference")
infer = INFER(vocab_obj, args, device)
infer.f_init_infer(network, args.model_file, reload_model=True)
infer.f_inference(valid_data)
logger_obj.f_close_writer()
def main(args):
ts = time.strftime('%Y-%b-%d-%H:%M:%S', time.gmtime())
#### get data
# with open(os.path.join(args.data_dir, args.data_file), 'rb') as file:
# data = pickle.load(file)
# data_obj = _Data()
# data_obj.f_create_data(args)
int_to_vocab, vocab_to_int, n_vocab, in_text, out_text = get_data_from_file(
flags.train_file, flags.batch_size, flags.seq_size)
# exit()
# train_data, valid_data, vocab_obj, user_num= data_obj._load_data_amazon(args)
# train_data, valid_data, vocab_obj, user_num = data_obj._load_data_amazon(args)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
logger_obj = Logger()
logger_obj.f_add_writer(args)
### add count parameters
print("vocab_size", len(int_to_vocab))
### get model
user_num = 10
network = REVIEWDI(n_vocab,
flags.seq_size,
flags.embedding_size,
flags.lstm_size,
device=device)
optimizer = Optimizer(network.parameters(), args)
trainer = TRAINER(args, flags.seq_size, device)
trainer.f_train(in_text, out_text, network, optimizer, logger_obj)
# print("*"*10, "inference")
# infer = INFER(vocab_obj, args, device)
# infer.f_init_infer(network, args.model_file, reload_model=True)
# infer.f_inference(valid_data)
logger_obj.f_close_writer()
def main(args):
ts = time.strftime('%Y-%b-%d-%H:%M:%S', time.gmtime())
seed = 1111
set_seed(seed)
#### get data
data_obj = _Data()
train_data, valid_data, vocab_obj = data_obj.f_load_data(args)
# train_data, valid_data = data()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("device", device)
if args.train:
now_time = datetime.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.model_name+"/model_best_"+time_name+"_"+args.data_name+".pt")
args.model_file = model_file
print("vocab_size", vocab_obj.vocab_size)
print("user num", vocab_obj.user_size)
### get model
network = REVIEWDI(vocab_obj, args, device=device)
### add count parameters
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 = Optimizer(network.parameters(), args)
trainer = TRAINER(vocab_obj, args, device)
trainer.f_train(train_data, valid_data, network, optimizer, logger_obj)
logger_obj.f_close_writer()
if args.test or args.eval:
print("="*10, "test", "="*10)
infer_obj = INFER(vocab_obj, args, device)
infer_obj.f_init_infer(network, args.model_file, reload_model=True)
infer_obj.f_inference(valid_data)
if args.eval:
print("="*10, "eval", "="*10)
eval_obj = _EVAL(vocab_obj, args, device)
eval_obj.f_init_eval(network, args.model_file, reload_model=True)
eval_obj.f_eval(valid_data)
def main(args):
ts = time.strftime('%Y-%b-%d-%H:%M:%S', time.gmtime())
#### get data
set_seed(1111)
data_obj = _Data()
train_data, valid_data, vocab_obj = data_obj.f_load_data_amazon(args)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
logger_obj = Logger()
logger_obj.f_add_writer(args)
### add count parameters
if args.train:
now_time = datetime.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.model_name+"/model_best_"+time_name+"_"+args.data_name+".pt")
args.model_file = model_file
print("vocab_size", len(vocab_obj.m_w2i))
### get model
# user_num = 10
network = REVIEWDI(vocab_obj, args, device=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:
optimizer = Optimizer(network.parameters(), args)
trainer = TRAINER(vocab_obj, args, device)
trainer.f_train(train_data, valid_data, network, optimizer, logger_obj)
if args.test or args.eval:
print("="*10, "test", "="*10)
infer = INFER(vocab_obj, args, device)
infer.f_init_infer(network, args.model_file, reload_model=True)
infer.f_inference(valid_data)
if args.eval:
print("="*10, "eval", "="*10)
eval_obj = EVAL(vocab_obj, args, device)
eval_obj.f_init_eval(network, args.model_file, reload_model=True)
eval_obj.f_eval(valid_data)
# infer = INFER(vocab_obj, args, device)
# infer.f_init_infer(network, args.model_file, reload_model=True)
# input_text = "verrry cheaply constructed , not as comfortable as i expected . i have been wearing this brand , but the first time i wore it , it was a little more than a few days ago . i have been wearing this brand before , so far , no complaints . i will be ordering more in different colors . update : after washing & drying , i will update after washing . after washing , this is a great buy . the fabric is not as soft as it appears to be made of cotton material . <eos>"
# infer.f_search_text(input_text, train_data)
logger_obj.f_close_writer()