def test_train_dev_loss_equal(self):
layer_dim = 512
batcher = SrcBatcher(batch_size=5, break_ties_randomly=False)
train_args = {}
train_args['src_file'] = "examples/data/head.ja"
train_args['trg_file'] = "examples/data/head.en"
train_args['loss_calculator'] = AutoRegressiveMLELoss()
train_args['model'] = DefaultTranslator(src_reader=PlainTextReader(),
trg_reader=PlainTextReader(),
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=BiLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim),
attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim,
hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(input_dim=layer_dim,
trg_embed_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="model.decoder.rnn"),
transform=NonLinear(input_dim=layer_dim*2, output_dim=layer_dim),
scorer=Softmax(input_dim=layer_dim, vocab_size=100),
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
train_args['dev_tasks'] = [LossEvalTask(model=train_args['model'],
src_file="examples/data/head.ja",
ref_file="examples/data/head.en",
batcher=batcher)]
train_args['trainer'] = DummyTrainer()
train_args['batcher'] = batcher
train_args['run_for_epochs'] = 1
training_regimen = xnmt.training_regimen.SimpleTrainingRegimen(**train_args)
training_regimen.run_training(save_fct = lambda: None)
self.assertAlmostEqual(training_regimen.train_loss_tracker.epoch_loss.sum_factors() / training_regimen.train_loss_tracker.epoch_words,
training_regimen.dev_loss_tracker.dev_score.loss, places=5)
def setUp(self):
layer_dim = 512
xnmt.events.clear()
ParamManager.init_param_col()
self.model = DefaultTranslator(
src_reader=PlainTextReader(),
trg_reader=PlainTextReader(),
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
attender=MlpAttender(input_dim=layer_dim,
state_dim=layer_dim,
hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(
input_dim=layer_dim,
trg_embed_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="model.decoder.rnn"),
transform=NonLinear(input_dim=layer_dim * 2,
output_dim=layer_dim),
scorer=Softmax(input_dim=layer_dim, vocab_size=100),
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.model.set_train(False)
self.src_data = list(
self.model.src_reader.read_sents("examples/data/head.ja"))
self.trg_data = list(
self.model.trg_reader.read_sents("examples/data/head.en"))
def test_py_lstm_mask(self):
layer_dim = 512
model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=PyramidalLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, layers=1),
attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(input_dim=layer_dim,
trg_embed_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"),
transform=NonLinear(input_dim=layer_dim*2, output_dim=layer_dim),
scorer=Softmax(input_dim=layer_dim, vocab_size=100),
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
batcher = xnmt.batcher.TrgBatcher(batch_size=3)
train_src, _ = \
batcher.pack(self.src_data, self.trg_data)
self.set_train(True)
for sent_i in range(3):
dy.renew_cg()
src = train_src[sent_i]
self.start_sent(src)
embeddings = model.src_embedder.embed_sent(src)
encodings = model.encoder.transduce(embeddings)
if train_src[sent_i].mask is None:
assert encodings.mask is None
else:
np.testing.assert_array_almost_equal(train_src[sent_i].mask.np_arr, encodings.mask.np_arr)
def setUp(self):
# Seeding
numpy.random.seed(2)
random.seed(2)
layer_dim = 64
xnmt.events.clear()
ParamManager.init_param_col()
self.segment_composer = SumComposer()
self.src_reader = CharFromWordTextReader()
self.trg_reader = PlainTextReader()
self.loss_calculator = AutoRegressiveMLELoss()
self.segmenting_encoder = SegmentingSeqTransducer(
segment_composer=self.segment_composer,
final_transducer=BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
)
self.model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=self.segmenting_encoder,
attender=MlpAttender(input_dim=layer_dim,
state_dim=layer_dim,
hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(
input_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="decoder"),
transform=AuxNonLinear(input_dim=layer_dim,
output_dim=layer_dim,
aux_input_dim=layer_dim),
scorer=Softmax(vocab_size=100, input_dim=layer_dim),
trg_embed_dim=layer_dim,
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.model.set_train(True)
self.layer_dim = layer_dim
self.src_data = list(
self.model.src_reader.read_sents("examples/data/head.ja"))
self.trg_data = list(
self.model.trg_reader.read_sents("examples/data/head.en"))
my_batcher = xnmt.batcher.TrgBatcher(batch_size=3,
src_pad_token=1,
trg_pad_token=2)
self.src, self.trg = my_batcher.pack(self.src_data, self.trg_data)
dy.renew_cg(immediate_compute=True, check_validity=True)
def test_uni_lstm_encoder_len(self):
layer_dim = 512
model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim),
attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(input_dim=layer_dim,
trg_embed_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"),
transform=NonLinear(input_dim=layer_dim*2, output_dim=layer_dim),
scorer=Softmax(input_dim=layer_dim, vocab_size=100),
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.assert_in_out_len_equal(model)
def test_loss_model2(self):
layer_dim = 512
model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=PyramidalLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, layers=3),
attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(input_dim=layer_dim,
trg_embed_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="model.decoder.rnn"),
transform=NonLinear(input_dim=layer_dim*2, output_dim=layer_dim),
scorer=Softmax(input_dim=layer_dim, vocab_size=100),
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
model.set_train(False)
self.assert_single_loss_equals_batch_loss(model, pad_src_to_multiple=4)
def test_py_lstm_encoder_len(self):
layer_dim = 512
model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=PyramidalLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, layers=3),
attender=MlpAttender(input_dim=layer_dim, state_dim=layer_dim, hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(input_dim=layer_dim,
trg_embed_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, decoder_input_dim=layer_dim, yaml_path="model.decoder.rnn"),
transform=NonLinear(input_dim=layer_dim*2, output_dim=layer_dim),
scorer=Softmax(input_dim=layer_dim, vocab_size=100),
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.set_train(True)
for sent_i in range(10):
dy.renew_cg()
src = self.src_data[sent_i].get_padded_sent(Vocab.ES, 4 - (self.src_data[sent_i].sent_len() % 4))
self.start_sent(src)
embeddings = model.src_embedder.embed_sent(src)
encodings = model.encoder.transduce(embeddings)
self.assertEqual(int(math.ceil(len(embeddings) / float(4))), len(encodings))
layer_dim = 512
model = DefaultTranslator(
src_reader=PlainTextReader(vocab=src_vocab),
trg_reader=PlainTextReader(vocab=trg_vocab),
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=len(src_vocab)),
encoder=BiLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim, layers=1),
attender=MlpAttender(hidden_dim=layer_dim, state_dim=layer_dim, input_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=len(trg_vocab)),
decoder=AutoRegressiveDecoder(input_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim, hidden_dim=layer_dim,
decoder_input_dim=layer_dim, yaml_path="decoder"),
transform=AuxNonLinear(input_dim=layer_dim, output_dim=layer_dim,
aux_input_dim=layer_dim),
scorer=Softmax(vocab_size=len(trg_vocab), input_dim=layer_dim),
trg_embed_dim=layer_dim,
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
inference=inference
)
train = SimpleTrainingRegimen(
name=f"{EXP}",
model=model,
batcher=batcher,
trainer=AdamTrainer(alpha=0.001),
run_for_epochs=2,
src_file="examples/data/head.ja",
trg_file="examples/data/head.en",
dev_tasks=[LossEvalTask(src_file="examples/data/head.ja",
ref_file="examples/data/head.en",
def setUp(self):
# Seeding
numpy.random.seed(2)
random.seed(2)
layer_dim = 64
xnmt.events.clear()
ParamManager.init_param_col()
self.segment_encoder_bilstm = BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim)
self.segment_composer = SumComposer()
self.src_reader = CharFromWordTextReader()
self.trg_reader = PlainTextReader()
self.loss_calculator = AutoRegressiveMLELoss()
baseline = Linear(input_dim=layer_dim, output_dim=1)
policy_network = Linear(input_dim=layer_dim, output_dim=2)
self.poisson_prior = PoissonPrior(mu=3.3)
self.eps_greedy = EpsilonGreedy(eps_prob=0.0, prior=self.poisson_prior)
self.conf_penalty = ConfidencePenalty()
self.policy_gradient = PolicyGradient(input_dim=layer_dim,
output_dim=2,
baseline=baseline,
policy_network=policy_network,
z_normalization=True,
conf_penalty=self.conf_penalty,
sample=5)
self.length_prior = PoissonLengthPrior(lmbd=3.3, weight=1)
self.segmenting_encoder = SegmentingSeqTransducer(
embed_encoder=self.segment_encoder_bilstm,
segment_composer=self.segment_composer,
final_transducer=BiLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim),
policy_learning=self.policy_gradient,
eps_greedy=self.eps_greedy,
length_prior=self.length_prior,
)
self.model = DefaultTranslator(
src_reader=self.src_reader,
trg_reader=self.trg_reader,
src_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
encoder=self.segmenting_encoder,
attender=MlpAttender(input_dim=layer_dim,
state_dim=layer_dim,
hidden_dim=layer_dim),
trg_embedder=SimpleWordEmbedder(emb_dim=layer_dim, vocab_size=100),
decoder=AutoRegressiveDecoder(
input_dim=layer_dim,
rnn=UniLSTMSeqTransducer(input_dim=layer_dim,
hidden_dim=layer_dim,
decoder_input_dim=layer_dim,
yaml_path="decoder"),
transform=AuxNonLinear(input_dim=layer_dim,
output_dim=layer_dim,
aux_input_dim=layer_dim),
scorer=Softmax(vocab_size=100, input_dim=layer_dim),
trg_embed_dim=layer_dim,
bridge=CopyBridge(dec_dim=layer_dim, dec_layers=1)),
)
self.model.set_train(True)
self.layer_dim = layer_dim
self.src_data = list(
self.model.src_reader.read_sents("examples/data/head.ja"))
self.trg_data = list(
self.model.trg_reader.read_sents("examples/data/head.en"))
my_batcher = xnmt.batcher.TrgBatcher(batch_size=3,
src_pad_token=1,
trg_pad_token=2)
self.src, self.trg = my_batcher.pack(self.src_data, self.trg_data)
dy.renew_cg(immediate_compute=True, check_validity=True)