def main():
# parse args first
parser = argparse.ArgumentParser()
parser.add_argument('-m')
parser.add_argument('-cfg', nargs='*')
args = parser.parse_args()
if args.m:
cfg.mode = args.m
parse_arg_cfg(args)
if cfg.mode == 'validate' or cfg.mode == 'adjust':
assert (cfg.eval_load_path != 'to be input')
cfg.gpt_path = cfg.eval_load_path
if cfg.mode == 'adjust':
cfg.mode = 'train'
else: # train
if cfg.exp_path in ['', 'to be generated']:
experiments_path = './experiments'
cfg.exp_path = os.path.join(
experiments_path, '{}_sd{}_lr{}_bs{}_ga{}_ctx{}'.format(
cfg.exp_no, cfg.seed, cfg.lr, cfg.batch_size,
cfg.gradient_accumulation_steps, cfg.context_scheme))
if cfg.save_log:
if not os.path.exists(cfg.exp_path):
os.mkdir(cfg.exp_path)
# to gpt later
cfg.model_path = os.path.join(cfg.exp_path, 'model.pkl')
cfg.result_path = os.path.join(cfg.exp_path, 'result.csv')
cfg.vocab_path_eval = os.path.join(cfg.exp_path, 'vocab')
cfg.eval_load_path = cfg.exp_path
cfg._init_logging_handler(args.m)
#fix random seed
torch.manual_seed(cfg.seed)
torch.cuda.manual_seed(cfg.seed)
random.seed(cfg.seed)
np.random.seed(cfg.seed)
#initialize model
m = UBARdoc(cfg.device)
if cfg.mode == 'train':
m.train()
elif cfg.mode == 'validate':
m.validate()
print('done')
return 0
def main():
if not os.path.exists('./experiments'):
os.mkdir('./experiments')
if not os.path.exists('./experiments_21'):
os.mkdir('./experiments_21')
parser = argparse.ArgumentParser()
parser.add_argument('-mode')
parser.add_argument('-cfg', nargs='*')
args = parser.parse_args()
cfg.mode = args.mode
if args.mode == 'test' or args.mode == 'adjust':
parse_arg_cfg(args)
# cfg.model_path = cfg.eval_load_path
cfg.gpt_path = cfg.eval_load_path
else: # train
parse_arg_cfg(args)
if cfg.exp_path in ['', 'to be generated']:
# log file path, control the factors: seed, learning_rate, batch_size, early_stop_count, weight decay...
# cfg.exp_path = 'experiments/{}_{}_sd{}_lr{}_bs{}_sp{}_dc{}/'.format('-'.join(cfg.exp_domains),
# cfg.exp_no, cfg.seed, cfg.lr, cfg.batch_size,
# cfg.early_stop_count, cfg.weight_decay_count)
experiments_path = './experiments' if 'all' in cfg.exp_domains else './experiments_Xdomain'
cfg.exp_path = os.path.join(
experiments_path, '{}_{}_sd{}_lr{}_bs{}_ga{}'.format(
'-'.join(cfg.exp_domains), cfg.exp_no, cfg.seed, cfg.lr,
cfg.batch_size, cfg.gradient_accumulation_steps))
logging.info('save path:', cfg.exp_path)
if cfg.save_log:
if not os.path.exists(cfg.exp_path):
os.mkdir(cfg.exp_path)
# to gpt later
cfg.model_path = os.path.join(cfg.exp_path, 'model.pkl')
cfg.result_path = os.path.join(cfg.exp_path, 'result.csv')
cfg.vocab_path_eval = os.path.join(cfg.exp_path, 'vocab')
cfg.eval_load_path = cfg.exp_path
cfg._init_logging_handler(args.mode)
if cfg.cuda:
if len(cfg.cuda_device) == 1:
cfg.multi_gpu = False
# torch.cuda.set_device(cfg.cuda_device[0])
device = torch.device("cuda:{}".format(cfg.cuda_device[0]))
else:
pass # multi-gpu
else:
device = torch.device('cpu')
logging.info('Device: {}'.format(torch.cuda.current_device()))
# fix random seed
torch.manual_seed(cfg.seed)
torch.cuda.manual_seed(cfg.seed)
random.seed(cfg.seed)
np.random.seed(cfg.seed)
# initialize model
m = Modal(device)
if args.mode == 'train': # train
if cfg.save_log: # save cfg details.
pass
if cfg.context_scheme == 'UBARU':
m.train()
elif cfg.context_scheme == 'URURU':
m.train_URURU()
else:
logging.info('Invalid context Scheme. must be UBARU or URURU')
exit()
elif args.mode == 'adjuest':
pass
else: # test
logging.info(
"Generate setting: \n\t use true_prev_bspn={} \n\t use true_prev_aspn={} \n\t use true_db_pointer={} \n\t use true_prev_resp={} \n\t use true_curr_bspn={} \n\t use true_curr_aspn={} \n\t use_all_previous_context={}"
.format(cfg.use_true_prev_bspn, cfg.use_true_prev_aspn,
cfg.use_true_db_pointer, cfg.use_true_prev_resp,
cfg.use_true_curr_bspn, cfg.use_true_curr_aspn,
cfg.use_all_previous_context))
if cfg.context_scheme == 'UBARU':
m.validate()
m.validate('test')
elif cfg.context_scheme == 'URURU':
m.validate_URURU()
m.validate_URURU('test')
def main():
if not os.path.exists('./experiments'):
os.mkdir('./experiments')
parser = argparse.ArgumentParser()
parser.add_argument('-mode')
parser.add_argument('-cfg', nargs='*')
args = parser.parse_args()
cfg.mode = args.mode
if args.mode == 'test' or args.mode == 'adjust':
parse_arg_cfg(args)
cfg_load = json.loads(
open(os.path.join(cfg.eval_load_path, 'config.json'), 'r').read())
for k, v in cfg_load.items():
if k in [
'mode', 'cuda', 'cuda_device', 'eval_load_path',
'eval_per_domain', 'use_true_pv_resp',
'use_true_prev_bspn', 'use_true_prev_aspn',
'use_true_curr_bspn', 'use_true_curr_aspn',
'name_slot_unable', 'book_slot_unable',
'count_req_dials_only', 'log_time', 'model_path',
'result_path', 'model_parameters', 'multi_gpu',
'use_true_bspn_for_ctr_eval', 'nbest', 'limit_bspn_vocab',
'limit_aspn_vocab', 'same_eval_as_cambridge', 'beam_width',
'use_true_domain_for_ctr_eval', 'use_true_prev_dspn',
'aspn_decode_mode', 'beam_diverse_param',
'same_eval_act_f1_as_hdsa', 'topk_num', 'nucleur_p',
'act_selection_scheme', 'beam_penalty_type', 'record_mode'
]:
continue
setattr(cfg, k, v)
cfg.model_path = os.path.join(cfg.eval_load_path, 'model.pkl')
cfg.result_path = os.path.join(cfg.eval_load_path, 'result.csv')
else:
parse_arg_cfg(args)
if cfg.exp_path in ['', 'to be generated']:
cfg.exp_path = 'experiments/{}_{}_sd{}_lr{}_bs{}_sp{}_dc{}/'.format(
'-'.join(cfg.exp_domains), cfg.exp_no, cfg.seed, cfg.lr,
cfg.batch_size, cfg.early_stop_count, cfg.weight_decay_count)
if cfg.save_log:
os.mkdir(cfg.exp_path)
cfg.model_path = os.path.join(cfg.exp_path, 'model.pkl')
cfg.result_path = os.path.join(cfg.exp_path, 'result.csv')
cfg.vocab_path_eval = os.path.join(cfg.exp_path, 'vocab')
cfg.eval_load_path = cfg.exp_path
cfg._init_logging_handler(args.mode)
if cfg.cuda:
if len(cfg.cuda_device) == 1:
cfg.multi_gpu = False
torch.cuda.set_device(cfg.cuda_device[0])
else:
# cfg.batch_size *= len(cfg.cuda_device)
cfg.multi_gpu = True
torch.cuda.set_device(cfg.cuda_device[0])
logging.info('Device: {}'.format(torch.cuda.current_device()))
torch.manual_seed(cfg.seed)
torch.cuda.manual_seed(cfg.seed)
random.seed(cfg.seed)
np.random.seed(cfg.seed)
m = Model()
cfg.model_parameters = m.count_params()
logging.info(str(cfg))
if args.mode == 'train':
if cfg.save_log:
# open(cfg.exp_path + 'config.json', 'w').write(str(cfg))
m.reader.vocab.save_vocab(cfg.vocab_path_eval)
with open(os.path.join(cfg.exp_path, 'config.json'), 'w') as f:
json.dump(cfg.__dict__, f, indent=2)
# m.load_glove_embedding()
m.train()
elif args.mode == 'adjust':
m.load_model(cfg.model_path)
m.train()
elif args.mode == 'test':
m.load_model(cfg.model_path)
# m.train()
m.eval(data='test')