def test_transformer():
params = load_tests_params()
# Current test params: Transformer
params['MODEL_TYPE'] = 'Transformer'
params['TIED_EMBEDDINGS'] = True
params['N_LAYERS_ENCODER'] = 2
params['N_LAYERS_DECODER'] = 2
params['MULTIHEAD_ATTENTION_ACTIVATION'] = 'relu'
params['MODEL_SIZE'] = 8
params['FF_SIZE'] = params['MODEL_SIZE'] * 4
params['N_HEADS'] = 2
params['REBUILD_DATASET'] = True
params['OPTIMIZED_SEARCH'] = False
params['POS_UNK'] = False
dataset = build_dataset(params)
params['INPUT_VOCABULARY_SIZE'] = dataset.vocabulary_len[params['INPUTS_IDS_DATASET'][0]]
params['OUTPUT_VOCABULARY_SIZE'] = dataset.vocabulary_len[params['OUTPUTS_IDS_DATASET'][0]]
params['MODEL_NAME'] = \
params['TASK_NAME'] + '_' + params['SRC_LAN'] + params['TRG_LAN'] + '_' + params['MODEL_TYPE'] + \
'_model_size_' + str(params['MODEL_SIZE']) + \
'_ff_size_' + str(params['FF_SIZE']) + \
'_num_heads_' + str(params['N_HEADS']) + \
'_encoder_blocks_' + str(params['N_LAYERS_ENCODER']) + \
'_decoder_blocks_' + str(params['N_LAYERS_DECODER']) + \
'_deepout_' + '_'.join([layer[0] for layer in params['DEEP_OUTPUT_LAYERS']]) + \
'_' + params['OPTIMIZER'] + '_' + str(params['LR'])
params['STORE_PATH'] = K.backend() + '_test_train_models/' + params['MODEL_NAME'] + '/'
# Test several NMT-Keras utilities: train, sample, sample_ensemble, score_corpus...
print ("Training model")
train_model(params)
params['RELOAD'] = 1
print ("Done")
parser = argparse.ArgumentParser('Parser for unit testing')
parser.dataset = params['DATASET_STORE_PATH'] + '/Dataset_' + params['DATASET_NAME'] + '_' + params['SRC_LAN'] + params['TRG_LAN'] + '.pkl'
parser.text = params['DATA_ROOT_PATH'] + '/' + params['TEXT_FILES']['val'] + params['SRC_LAN']
parser.splits = ['val']
parser.config = params['STORE_PATH'] + '/config.pkl'
parser.models = [params['STORE_PATH'] + '/epoch_' + str(1)]
parser.verbose = 0
parser.dest = None
parser.source = params['DATA_ROOT_PATH'] + '/' + params['TEXT_FILES']['val'] + params['SRC_LAN']
parser.target = params['DATA_ROOT_PATH'] + '/' + params['TEXT_FILES']['val'] + params['TRG_LAN']
parser.weights = []
parser.glossary = None
for n_best in [True, False]:
parser.n_best = n_best
print ("Sampling with n_best = %s " % str(n_best))
sample_ensemble(parser, params)
print ("Done")
print ("Scoring corpus")
score_corpus(parser, params)
print ("Done")
def test_ConditionalLSTM_dot():
params = load_tests_params()
# Current test params: Single layered LSTM - ConditionalGRU
params['BIDIRECTIONAL_ENCODER'] = True
params['N_LAYERS_ENCODER'] = 1
params['BIDIRECTIONAL_DEEP_ENCODER'] = True
params['ENCODER_RNN_TYPE'] = 'LSTM'
params['DECODER_RNN_TYPE'] = 'ConditionalLSTM'
params['N_LAYERS_DECODER'] = 1
params['ATTENTION_MODE'] = 'dot'
params['REBUILD_DATASET'] = True
dataset = build_dataset(params)
params['INPUT_VOCABULARY_SIZE'] = dataset.vocabulary_len[params['INPUTS_IDS_DATASET'][0]]
params['OUTPUT_VOCABULARY_SIZE'] = dataset.vocabulary_len[params['OUTPUTS_IDS_DATASET'][0]]
params['MODEL_NAME'] = \
params['TASK_NAME'] + '_' + params['SRC_LAN'] + params['TRG_LAN'] + '_' + params['MODEL_TYPE'] + \
'_src_emb_' + str(params['SOURCE_TEXT_EMBEDDING_SIZE']) + \
'_bidir_' + str(params['BIDIRECTIONAL_ENCODER']) + \
'_enc_' + params['ENCODER_RNN_TYPE'] + '_*' + str(params['N_LAYERS_ENCODER']) + '_' + str(
params['ENCODER_HIDDEN_SIZE']) + \
'_dec_' + params['DECODER_RNN_TYPE'] + '_*' + str(params['N_LAYERS_DECODER']) + '_' + str(
params['DECODER_HIDDEN_SIZE']) + params['ATTENTION_MODE'] + \
'_deepout_' + '_'.join([layer[0] for layer in params['DEEP_OUTPUT_LAYERS']]) + \
'_trg_emb_' + str(params['TARGET_TEXT_EMBEDDING_SIZE']) + \
'_' + params['OPTIMIZER'] + '_' + str(params['LR'])
params['STORE_PATH'] = os.path.join(K.backend() + '_test_train_models', params['MODEL_NAME'])
# Test several NMT-Keras utilities: train, sample, sample_ensemble, score_corpus...
print("Training model")
train_model(params)
params['RELOAD'] = 1
print("Done")
parser = argparse.ArgumentParser('Parser for unit testing')
parser.dataset = os.path.join(
params['DATASET_STORE_PATH'],
'Dataset_' + params['DATASET_NAME'] + '_' + params['SRC_LAN'] + params['TRG_LAN'] + '.pkl')
parser.text = os.path.join(params['DATA_ROOT_PATH'], params['TEXT_FILES']['val'] + params['SRC_LAN'])
parser.splits = ['val']
parser.config = params['STORE_PATH'] + '/config.pkl'
parser.models = [params['STORE_PATH'] + '/epoch_' + str(1)]
parser.verbose = 0
parser.dest = None
parser.source = os.path.join(params['DATA_ROOT_PATH'], params['TEXT_FILES']['val'] + params['SRC_LAN'])
parser.target = os.path.join(params['DATA_ROOT_PATH'], params['TEXT_FILES']['val'] + params['TRG_LAN'])
parser.weights = []
parser.glossary = None
for n_best in [True, False]:
parser.n_best = n_best
print("Sampling with n_best = %s " % str(n_best))
sample_ensemble(parser, params)
print("Done")
print("Scoring corpus")
score_corpus(parser, params)
print("Done")
def test_unk_replace_1():
params = load_tests_params()
params['REBUILD_DATASET'] = True
params['INPUT_VOCABULARY_SIZE'] = 0
params['OUTPUT_VOCABULARY_SIZE'] = 50
params['POS_UNK'] = True
params['HEURISTIC'] = 1
params['ALIGN_FROM_RAW'] = True
dataset = build_dataset(params)
# params['MAPPING'] = DATA_ROOT_PATH + '/mapping.%s_%s.pkl' % (SRC_LAN, TRG_LAN)
params['INPUT_VOCABULARY_SIZE'] = dataset.vocabulary_len[params['INPUTS_IDS_DATASET'][0]]
params['OUTPUT_VOCABULARY_SIZE'] = dataset.vocabulary_len[params['OUTPUTS_IDS_DATASET'][0]]
params['MODEL_NAME'] = \
params['TASK_NAME'] + '_' + params['SRC_LAN'] + params['TRG_LAN'] + '_' + params['MODEL_TYPE'] + \
'_src_emb_' + str(params['SOURCE_TEXT_EMBEDDING_SIZE']) + \
'_bidir_' + str(params['BIDIRECTIONAL_ENCODER']) + \
'_enc_' + params['ENCODER_RNN_TYPE'] + '_*' + str(params['N_LAYERS_ENCODER']) + '_' + str(
params['ENCODER_HIDDEN_SIZE']) + \
'_dec_' + params['DECODER_RNN_TYPE'] + '_*' + str(params['N_LAYERS_DECODER']) + '_' + str(
params['DECODER_HIDDEN_SIZE']) + \
'_deepout_' + '_'.join([layer[0] for layer in params['DEEP_OUTPUT_LAYERS']]) + \
'_trg_emb_' + str(params['TARGET_TEXT_EMBEDDING_SIZE']) + \
'_' + params['OPTIMIZER'] + '_' + str(params['LR'])
params['STORE_PATH'] = os.path.join(K.backend() + '_test_train_models', params['MODEL_NAME'])
# Test several NMT-Keras utilities: train, sample, sample_ensemble, score_corpus...
print("Training model")
train_model(params)
params['RELOAD'] = 1
print("Done")
parser = argparse.ArgumentParser('Parser for unit testing')
parser.dataset = os.path.join(
params['DATASET_STORE_PATH'],
'Dataset_' + params['DATASET_NAME'] + '_' + params['SRC_LAN'] + params['TRG_LAN'] + '.pkl')
parser.text = os.path.join(params['DATA_ROOT_PATH'], params['TEXT_FILES']['val'] + params['SRC_LAN'])
parser.splits = ['val']
parser.config = os.path.join(params['STORE_PATH'], 'config.pkl')
parser.models = [os.path.join(params['STORE_PATH'], 'epoch_' + str(1))]
parser.verbose = 0
parser.dest = None
parser.source = os.path.join(params['DATA_ROOT_PATH'], params['TEXT_FILES']['val'] + params['SRC_LAN'])
parser.target = os.path.join(params['DATA_ROOT_PATH'], params['TEXT_FILES']['val'] + params['TRG_LAN'])
parser.weights = []
parser.glossary = None
for n_best in [True, False]:
parser.n_best = n_best
print("Sampling with n_best = %s " % str(n_best))
sample_ensemble(parser, params)
print("Done")
print("Scoring corpus")
score_corpus(parser, params)
print("Done")
if __name__ == "__main__":
args = parse_args()
if args.config is None:
logger.info("Reading parameters from config.py")
from config import load_parameters
params = load_parameters()
else:
logger.info("Loading parameters from %s" % str(args.config))
params = pkl2dict(args.config)
try:
for arg in args.changes:
try:
k, v = arg.split('=')
except ValueError:
print(
'Overwritten arguments must have the form key=Value. \n Currently are: %s'
% str(args.changes))
exit(1)
try:
params[k] = ast.literal_eval(v)
except ValueError:
params[k] = v
except ValueError:
print('Error processing arguments: (', k, ",", v, ")")
exit(2)
params = check_params(params)
sample_ensemble(args, params)