def predict(path):
np.random.seed(42)
tf.set_random_seed(42)
config = Config.get_default_config(args)
model = Model(config)
predictor = InteractivePredictor(config, model, path)
predictor.predict()
model.close_session()
args = parser.parse_args()
replace_tokens = ["@R_%d@"%i for i in range(1, args.num_replace_tokens+1)]
if args.debug:
config = Config.get_debug_config(args)
else:
config = Config.get_default_config(args)
# Composite training loss
lamb = args.lamb
print('Lamb :=' + str(lamb))
model = Model(config, replace_tokens)
print('Created model')
if config.TRAIN_PATH:
model.train(lamb=lamb)
if config.TEST_PATH and not args.data_path:
results, precision, recall, f1 = model.evaluate()
print('Accuracy: ' + str(results))
print('Precision: ' + str(precision) + ', recall: ' + str(recall) + ', F1: ' + str(f1))
if args.predict:
predictor = InteractivePredictor(config, model)
predictor.predict()
if args.adv_eval:
model.adv_eval_batched()
if args.release and args.load_path:
model.evaluate(release=True)
model.close_session()
tf.random.set_seed(args.seed)
if args.debug:
config = Config.get_debug_config(args)
tf.config.experimental_run_functions_eagerly(True)
else:
config = Config.get_default_config(args)
print('Created model')
if config.TRAIN_PATH:
model = ModelRunner(config)
model.train()
#if config.TEST_PATH and not args.data_path:
#model = ModelRunner(config)
#results, precision, recall, f1, rouge, bleu = model.evaluate('test')
#print('Accuracy: ' + str(results))
#print('Precision: ' + str(precision) + ', recall: ' + str(recall) + ', F1: ' + str(f1))
#print('Rouge: ', rouge)
#print('Bleu: ', bleu)
if args.predict:
model = ModelRunner(config)
predictor = InteractivePredictor(config, model)
paths = glob(args.predict)
if args.shard:
paths = [
path for path in paths if path[args.predict.find('*') +
1:].startswith(str(args.shard))
]
predictor.predict(paths)
