log_to_file(log_file_name, epoch, avg_train_loss, train_accuracy, dev_accuracy)
if patience == train_hyperparams['PATIENCE']:
print 'out of patience after {} epochs'.format(epoch)
train_progress_bar.finish()
break
# finished epoch
train_progress_bar.update(epoch)
print 'finished training.'
ti = SoftAttention(pc, model_hyperparams, best_model_path)
dev_accuracy, dev_results = ti.evaluate(dev_data.iter(), int(arguments['--beam']))
print 'Best dev accuracy: {}'.format(dev_accuracy)
write_param_file(output_file_path, dict(model_hyperparams.items()+train_hyperparams.items()))
write_pred_file(output_file_path, dev_results)
write_eval_file(output_file_path, best_dev_accuracy, dev_path)
elif arguments['test']:
print '=========EVALUATION ONLY:========='
# requires test path, model path of pretrained path and results path where to write the results to
assert arguments['--test_path']!=None
print 'Loading data...'
test_path = check_path(arguments['--test_path'], '--test_path')
data_set = SoftDataSet
input_format = [int(col) for col in arguments['--input_format'].split(',')]
test_data = data_set.from_file(test_path,input_format, arguments['--lowercase'])
print 'Test data has {} examples'.format(test_data.length)
print 'Checking if any special symbols in data...'
arguments["--lm_paths"].split(','),\
[int(o) for o in arguments["--lm_orders"].split(',')]\
)):
lm_model_folder = check_path(path, 'LM_MODEL_FOLDER_{}'.format(i), is_data_path=False)
if lm_type=="srilm_char":
print '...Loading lm model {} from path {}'.format(i,lm_model_folder)
lm_model = SRILM_char_lm_loader(lm_model_folder, order)
elif lm_type=="srilm_morph":
lm_model = SRILM_morpheme_lm_loader(lm_model_folder,order)
assert arguments['--morph_vocab'] != None
lm_model.vocab = Vocab.from_file(check_path(arguments['--morph_vocab'], 'morph_vocab', is_data_path=False))
else:
print "WARNING -- Could not load language model. Unknown type",lm_type,". Use 'srilm_char' or 'srilm_morph'"
lm_models.append(lm_model)
lm_number = len(lm_models)
output_file_path = os.path.join(model_folder,arguments['--pred_path'])
# save best dev model parameters and predictions
print 'Evaluating on test..'
t = time.clock()
if arguments['--indices']:
indices = [int(ind) for ind in arguments['--indices'].split(',')]
accuracy, test_results = evaluate_syncbeam(test_data.iter(indices), nmt_models, lm_models, weights, int(arguments['--beam']), int(arguments['--output_format']), verbose=arguments['--verbose'], exclude_eow=arguments['--exclude_eow'])
else:
accuracy, test_results = evaluate_syncbeam(test_data.iter(), nmt_models, lm_models, weights, int(arguments['--beam']), int(arguments['--output_format']), verbose=arguments['--verbose'], exclude_eow=arguments['--exclude_eow'])
print 'Time: {}'.format(time.clock()-t)
print 'accuracy: {}'.format(accuracy)
write_pred_file(output_file_path, test_results, int(arguments['--output_format']))
write_eval_file(output_file_path, accuracy, test_path)
