ga.train(train, dev, gtrain, dir_name, batch_size, glove, beam_size,
epoch_size, dev_sample_size, cmodel, gen_epochs)
if method == 'augment':
gtrain = gm.gen_train(len(train[0]), g_hidden_size, latent_size, glove, hypo_len, version)
gtrain.load_weights(dir_name + '/weights.hdf5')
gtest = gm.gen_test(gtrain, glove, batch_size)
augment.new_generate_save(dev, dir_name, augment_file_size, gtest, beam_size, hypo_len,
latent_size, cmodel, wi, 'dev', len(dev[0]), aug_threshold)
augment.new_generate_save(train, dir_name, augment_file_size, gtest, beam_size, hypo_len,
latent_size, cmodel, wi, 'train', len(train[0]), aug_threshold)
if method == 'train_class':
for t in thresholds:
if type(t) == str and t[0] == 'a':
aug_train, aug_dev = augment.load_dataset(dir_name, True, 2**30, 2**30, wi, prem_len, hypo_len)
aug_dev = aa.filter_adverserial(aug_dev, t, len(dev[0]), dir_name, glove, a_hidden_size)
aug_train = aa.filter_adverserial(aug_train, t, len(train[0]), dir_name, glove, a_hidden_size)
else:
aug_train, aug_dev = augment.load_dataset(dir_name, t, len(train[0]), len(dev[0]), wi, prem_len, hypo_len)
aug_cmodel = cm.attention_model(c_hidden_size, glove)
ca.train(aug_train, aug_dev, aug_cmodel, dir_name + '/threshold' + str(t), batch_size)
if method == 'train_discriminator':
aug_train, aug_dev = augment.load_dataset(dir_name, 0.0, len(train[0]), len(dev[0]), wi, prem_len, hypo_len)
aa.adverse_model_train(dir_name, train, aug_train, dev, aug_dev, a_hidden_size, glove)
if method == 'evaluate':
csvf = open(dir_name + '/total_eval.csv', 'wb')
writer = csv.writer(csvf)
def evaluate_model(dir_name, dev, wi, metrics):
aug_train, aug_dev = augment.load_dataset(dir_name, 0.0, len(dev[0]),
len(dev[0]), wi, 25, 15)
gts, res = process_input(dev[1], aug_dev[1], wi)
return evaluate(gts, res, metrics)
if method == 'augment':
gtrain = gm.gen_train(len(train[0]), g_hidden_size, latent_size, glove,
hypo_len, version)
gtrain.load_weights(dir_name + '/weights.hdf5')
gtest = gm.gen_test(gtrain, glove, batch_size)
augment.new_generate_save(dev, dir_name, augment_file_size, gtest,
beam_size, hypo_len, latent_size, cmodel, wi,
'dev', len(dev[0]), aug_threshold)
augment.new_generate_save(train, dir_name, augment_file_size, gtest,
beam_size, hypo_len, latent_size, cmodel, wi,
'train', len(train[0]), aug_threshold)
if method == 'train_class':
for t in thresholds:
if type(t) == str and t[0] == 'a':
aug_train, aug_dev = augment.load_dataset(
dir_name, True, 2**30, 2**30, wi, prem_len, hypo_len)
aug_dev = aa.filter_adverserial(aug_dev, t, len(dev[0]),
dir_name, glove, a_hidden_size)
aug_train = aa.filter_adverserial(aug_train, t, len(train[0]),
dir_name, glove,
a_hidden_size)
else:
aug_train, aug_dev = augment.load_dataset(
dir_name, t, len(train[0]), len(dev[0]), wi, prem_len,
hypo_len)
aug_cmodel = cm.attention_model(c_hidden_size, glove)
ca.train(aug_train, aug_dev, aug_cmodel,
dir_name + '/threshold' + str(t), batch_size)
if method == 'train_adverse':
def evaluate_model(dir_name, dev, wi, metrics):
aug_train, aug_dev = augment.load_dataset(dir_name, 0.0, len(dev[0]), len(dev[0]), wi, 25, 15)
gts, res = process_input(dev[1], aug_dev[1], wi)
return evaluate(gts, res, metrics)