def main():
config = setup_config()
vocab_src, vocab_tgt = load_dataset_joey(config)
src_file = "{}/vocab.{}".format(config["data_dir"], config["src"])
tgt_file = "{}/vocab.{}".format(config["data_dir"], config["tgt"])
vocab_src.to_file(src_file)
vocab_tgt.to_file(tgt_file)
def main():
config = setup_config()
vocab_src, vocab_tgt = load_vocabularies(config)
train_data, dev_data, opt_data = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
dl = DataLoader(train_data,
batch_size=config["batch_size_train"],
shuffle=True,
num_workers=4)
bucketing_dl = BucketingParallelDataLoader(dl)
cycle_iterate_dl_back = None
if config["back_prefix"] != None:
dl_back = DataLoader(dataset=opt_data['back'],
batch_size=config["batch_size_train"],
shuffle=True,
num_workers=2)
bucketing_dl_back = BucketingParallelDataLoader(dl_back)
cycle_iterate_dl_back = cycle(bucketing_dl_back)
model, train_fn, validate_fn = create_model(vocab_src, vocab_tgt, config)
model.to(torch.device(config["device"]))
train(model,
train_fn,
validate_fn,
bucketing_dl,
dev_data,
vocab_src,
vocab_tgt,
config,
cycle_iterate_dl_back=cycle_iterate_dl_back)
def main():
config = setup_config()
config["train_prefix"] = 'sample'
vocab_src, vocab_tgt = load_vocabularies(config)
train_data, _, _ = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
val_dl = DataLoader(train_data,
batch_size=config["batch_size_eval"],
shuffle=False,
num_workers=4)
val_dl = BucketingParallelDataLoader(val_dl)
sentences_x, sentences_y = next(val_dl)
model, _, validate_fn = create_model(vocab_src, vocab_tgt, config)
model.to(torch.device(config["device"]))
# checkpoint_path = "output/aevnmt_z_loss_en-de_run_0/checkpoints/aevnmt_z_loss_en-de_run_0"
checkpoint_path = "output/aevnmt_z_loss_de-en_run_0/checkpoints/aevnmt_z_loss_de-en_run_0"
state = torch.load(checkpoint_path)
model.load_state_dict(state['state_dict'])
sample_from_latent(model, vocab_src, vocab_tgt, config)
sample_from_posterior(model, sentences_x, vocab_src, vocab_tgt, config)
def main():
# config = setup_config()
# config["train_prefix"] = 'sample'
# train_data, dev_data, vocab_src, vocab_tgt = load_dataset_joey(config)
# dataloader = data.make_data_iter(train_data, 1, train=True)
# sample = next(iter(dataloader))
# batch = Batch(sample, vocab_src.stoi[config["pad"]], use_cuda=False if config["device"] == "cpu" else True)
#
# model_xy, model_yx, _, _, validate_fn = create_models(vocab_src, vocab_tgt, config)
# model_xy.to(torch.device(config["device"]))
# model_yx.to(torch.device(config["device"]))
#
# checkpoint_path = "output/coaevnmt_greedy_lm_off_run_5/checkpoints/coaevnmt_greedy_lm_off_run_5"
# state = torch.load(checkpoint_path)
# model_xy.load_state_dict(state['state_dict_xy'])
# model_yx.load_state_dict(state['state_dict_yx'])
config = setup_config()
config["train_prefix"] = 'sample'
vocab_src, vocab_tgt = load_vocabularies(config)
train_data, _, _ = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
val_dl = DataLoader(train_data,
batch_size=config["batch_size_eval"],
shuffle=False,
num_workers=4)
val_dl = BucketingParallelDataLoader(val_dl)
sentences_x, sentences_y = next(val_dl)
# model, _, validate_fn = create_model(vocab_src, vocab_tgt, config)
# model.to(torch.device(config["device"]))
# model_xy, model_yx, _, _, validate_fn = create_models(vocab_src, vocab_tgt, config)
# model_xy.to(torch.device(config["device"]))
# model_yx.to(torch.device(config["device"]))
model_xy, model_yx, bi_train_fn, mono_train_fn, validate_fn = create_models(
vocab_src, vocab_tgt, config)
model_xy.to(torch.device(config["device"]))
model_yx.to(torch.device(config["device"]))
checkpoint_path = "output/coaevnmt_curc_diff_greedy_lr2_en-de_run_1/checkpoints/coaevnmt_curc_diff_greedy_lr2_en-de_run_1"
state = torch.load(checkpoint_path)
model_xy.load_state_dict(state['state_dict_xy'])
model_yx.load_state_dict(state['state_dict_yx'])
print("validation: {}-{}".format(config["src"], config["tgt"]))
sample_from_latent(model_xy, vocab_src, vocab_tgt, config)
sample_from_posterior(model_xy, sentences_x, vocab_src, vocab_tgt, config)
print("")
print("validation: {}-{}".format(config["tgt"], config["src"]))
sample_from_latent(model_yx, vocab_tgt, vocab_src, config)
sample_from_posterior(model_yx, sentences_y, vocab_tgt, vocab_src, config)
def main():
config = setup_config()
train_data, dev_data, vocab_src, vocab_tgt = load_dataset_joey(config)
model, train_fn, validate_fn = create_model(vocab_src, vocab_tgt, config)
model.to(torch.device(config["device"]))
init_model(model, vocab_src.stoi[config["pad"]],
vocab_tgt.stoi[config["pad"]], config)
trainer = Trainer(model, train_fn, validate_fn, vocab_src, vocab_tgt,
train_data, dev_data, config)
trainer.train_model()
def main():
# config = setup_config()
config = setup_config()
config["dev_prefix"] = "dev"
# config["dev_prefix"] = "test_2016_flickr.lc.norm.tok"
# config["dev_prefix"] = "test_2017_flickr.lc.norm.tok"
vocab_src, vocab_tgt = load_vocabularies(config)
_, dev_data, _ = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
checkpoint_path = "output/aevnmt_z_loss_en-de_run_1/checkpoints/aevnmt_z_loss_en-de_run_1"
if config["model_type"] == "coaevnmt":
model_xy, model_yx, _, _, validate_fn = create_models(
vocab_src, vocab_tgt, config)
model_xy.to(torch.device(config["device"]))
model_yx.to(torch.device(config["device"]))
state = torch.load(checkpoint_path)
model_xy.load_state_dict(state['state_dict_xy'])
model_yx.load_state_dict(state['state_dict_yx'])
printKL(model_xy,
dev_data,
vocab_src,
vocab_tgt,
config,
direction="xy")
printKL(model_yx,
dev_data,
vocab_tgt,
vocab_src,
config,
direction="yx")
elif config["model_type"] == "aevnmt":
model, _, _ = create_model(vocab_src, vocab_tgt, config)
model.to(torch.device(config["device"]))
state = torch.load(checkpoint_path)
model.load_state_dict(state['state_dict'])
printKL(model,
dev_data,
vocab_src,
vocab_tgt,
config,
direction="None")
def main():
# config = setup_config()
config = setup_config()
# config["dev_prefix"] = "dev"
# config["dev_prefix"] = "test_2016_flickr.lc.norm.tok"
config["dev_prefix"] = "test_2017_flickr.lc.norm.tok"
vocab_src, vocab_tgt = load_vocabularies(config)
_, dev_data, _ = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
model_xy, model_yx, _, _, validate_fn = create_models(
vocab_src, vocab_tgt, config)
model_xy.to(torch.device(config["device"]))
model_yx.to(torch.device(config["device"]))
# checkpoint_path = "output/coaevnmt_greedy_lm_off_run_5/checkpoints/coaevnmt_greedy_lm_off_run_5"
# checkpoint_path = "output/coaevnmt_lr3_curriculum_en-de_run_4/checkpoints/coaevnmt_lr3_curriculum_en-de_run_4"
# checkpoint_path = "output/coaevnmt_lr3_no_curriculum_no_warmup_en-de_run_4/checkpoints/coaevnmt_lr3_no_curriculum_no_warmup_en-de_run_4"
# checkpoint_path = "output/coaevnmt_lr3_beam_dec_3_en-de_run_3/checkpoints/coaevnmt_lr3_beam_dec_3_en-de_run_3"
# checkpoint_path = "output/conmt_anc_en-de_run_3/checkpoints/conmt_anc_en-de_run_3"
# checkpoint_path = "output/conmt_greedy_2en-de_run_3/checkpoints/conmt_greedy_2en-de_run_3"
# checkpoint_path = "output/conmt_greedy_no_warmup_en-de_run_3/checkpoints/conmt_greedy_no_warmup_en-de_run_3"
# checkpoint_path = "output/conmt_beam_dec_3_2en-de_run_1/checkpoints/conmt_beam_dec_3_2en-de_run_1"
# checkpoint_path = "output/conmt_beam_dec_5_2en-de_run_3/checkpoints/conmt_beam_dec_5_2en-de_run_3"
# checkpoint_path = "output/conmt_beam_dec_10_2en-de_run_3/checkpoints/conmt_beam_dec_10_2en-de_run_3"
# checkpoint_path = "output/conmt_beam_dec_10_en-de_run_3/checkpoints/conmt_beam_dec_10_en-de_run_3"
# checkpoint_path = "output/conmt_curc_diff_greedy_conv_yx_en-de_run_7/checkpoints/conmt_curc_diff_greedy_conv_yx_en-de_run_7"
# checkpoint_path = "output/conmt_final_full_en-de_run_3/checkpoints/conmt_final_full_en-de_run_3"
# checkpoint_path = "output/conmt_final_half_en-de_run_3/checkpoints/conmt_final_half_en-de_run_3"
# checkpoint_path = "output/conmt_final_fourth_en-de_run_3/checkpoints/conmt_final_fourth_en-de_run_3"
# checkpoint_path = "output/coaevnmt_final_full_en-de_run_3/checkpoints/coaevnmt_final_full_en-de_run_3"
# checkpoint_path = "output/coaevnmt_final_half_en-de_run_3/checkpoints/coaevnmt_final_half_en-de_run_3"
checkpoint_path = "output/coaevnmt_final_fourth_en-de_run_3/checkpoints/coaevnmt_final_fourth_en-de_run_3"
state = torch.load(checkpoint_path)
model_xy.load_state_dict(state['state_dict_xy'])
model_yx.load_state_dict(state['state_dict_yx'])
print("validation: {}-{}".format(config["src"], config["tgt"]))
evaluate(model_xy, dev_data, vocab_src, vocab_tgt, config, direction="xy")
print("validation: {}-{}".format(config["tgt"], config["src"]))
evaluate(model_yx, dev_data, vocab_tgt, vocab_src, config, direction="yx")
def main():
config = setup_config()
en_files = [config["data_dir"] + "/" + "all_data." + config["src"]]
de_files = [config["data_dir"] + "/" + "all_data." + config["tgt"]]
vocab_src = Vocabulary().from_data(en_files,
min_freq=0,
max_size=sys.maxsize)
vocab_tgt = Vocabulary().from_data(de_files,
min_freq=0,
max_size=sys.maxsize)
# print(vocab_src)
vocab_src.print_statistics()
vocab_tgt.print_statistics()
vocab_src.save(config["data_dir"] + "/" + "vocab_new." + config["src"])
vocab_tgt.save(config["data_dir"] + "/" + "vocab_new." + config["tgt"])
def main():
config = setup_config()
vocab_src, vocab_tgt = load_vocabularies(config)
train_data, dev_data, opt_data = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
dl_xy = DataLoader(train_data,
batch_size=config["batch_size_train"],
shuffle=True,
num_workers=2)
bucketing_dl_xy = BucketingParallelDataLoader(dl_xy)
dl_x = DataLoader(dataset=opt_data['mono_src'],
batch_size=config["batch_size_train"],
shuffle=True,
num_workers=2)
bucketing_dl_x = BucketingTextDataLoader(dl_x)
cycle_iterate_dl_x = cycle(bucketing_dl_x)
dl_y = DataLoader(dataset=opt_data['mono_tgt'],
batch_size=config["batch_size_train"],
shuffle=True,
num_workers=2)
bucketing_dl_y = BucketingTextDataLoader(dl_y)
cycle_iterate_dl_y = cycle(bucketing_dl_y)
model, bi_train_fn, mono_train_fn, validate_fn = create_model(
vocab_src, vocab_tgt, config)
print(model.emb_src is model.model_xy.emb_src)
print(model.emb_tgt is model.model_xy.emb_tgt)
asf
model.to(torch.device(config["device"]))
# model_yx.to(torch.device(config["device"]))
train(model, bi_train_fn, mono_train_fn, validate_fn, bucketing_dl_xy,
dev_data, cycle_iterate_dl_x, cycle_iterate_dl_y, vocab_src,
vocab_tgt, config)
def main():
config = setup_config()
config["dev_prefix"] = "comparable"
vocab_src, vocab_tgt = load_vocabularies(config)
_, dev_data, _ = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
model, _, validate_fn = create_model(vocab_src, vocab_tgt, config)
model.to(torch.device(config["device"]))
checkpoint_path = "{}/cond_nmt_de-en_run_7/checkpoints/cond_nmt_de-en_run_7".format(
config["out_dir"])
state = torch.load(checkpoint_path)
model.load_state_dict(state['state_dict'])
model.eval()
device = torch.device(
"cpu") if config["device"] == "cpu" else torch.device("cuda:0")
with torch.no_grad():
model_hypotheses = []
references = []
val_dl = DataLoader(dev_data,
batch_size=config["batch_size_eval"],
shuffle=False,
num_workers=4)
# val_dl = BucketingParallelDataLoader(val_dl)
for sentences_x, sentences_y in tqdm(val_dl):
sentences_x = np.array(sentences_x)
seq_len = np.array([len(s.split()) for s in sentences_x])
sort_keys = np.argsort(-seq_len)
sentences_x = sentences_x[sort_keys]
# #
sentences_y = np.array(sentences_y)
x_in, _, x_mask, x_len = create_batch(sentences_x, vocab_src,
device)
x_mask = x_mask.unsqueeze(1)
if config["model_type"] == "aevnmt":
qz = model.inference(x_in, x_mask, x_len)
z = qz.mean
enc_output, enc_hidden = model.encode(x_in, x_len, z)
dec_hidden = model.init_decoder(enc_output, enc_hidden, z)
raw_hypothesis = beam_search(model.decoder, model.emb_tgt,
model.generate_tm, enc_output,
dec_hidden, x_mask,
vocab_tgt.size(),
vocab_tgt[SOS_TOKEN],
vocab_tgt[EOS_TOKEN],
vocab_tgt[PAD_TOKEN], config)
else:
enc_output, enc_hidden = model.encode(x_in, x_len)
dec_hidden = model.decoder.initialize(enc_output, enc_hidden)
raw_hypothesis = beam_search(model.decoder, model.emb_tgt,
model.generate_tm, enc_output,
dec_hidden, x_mask,
vocab_tgt.size(),
vocab_tgt[SOS_TOKEN],
vocab_tgt[EOS_TOKEN],
vocab_tgt[PAD_TOKEN], config)
hypothesis = batch_to_sentences(raw_hypothesis, vocab_tgt)
inverse_sort_keys = np.argsort(sort_keys)
model_hypotheses += hypothesis[inverse_sort_keys].tolist()
references += sentences_y.tolist()
save_hypotheses(model_hypotheses, 0, config, None)
model_hypotheses, references = clean_sentences(model_hypotheses,
references, config)
bleu = sacrebleu.raw_corpus_bleu(model_hypotheses, [references]).score
print(bleu)
def main():
config = setup_config()
config["dev_prefix"] = "comparable"
vocab_src, vocab_tgt = load_vocabularies(config)
_, dev_data, _ = load_data(config,
vocab_src=vocab_src,
vocab_tgt=vocab_tgt)
# _, dev_data, vocab_src, vocab_tgt = load_dataset_joey(config)
model, _, validate_fn = create_model(vocab_src, vocab_tgt, config)
model.to(torch.device(config["device"]))
checkpoint_path = "{}/cond_nmt_new_de-en_run_2/checkpoints/cond_nmt_new_de-en_run_2".format(
config["out_dir"])
state = torch.load(checkpoint_path)
model.load_state_dict(state['state_dict'])
model.eval()
device = torch.device(
"cpu") if config["device"] == "cpu" else torch.device("cuda:0")
with torch.no_grad():
model_hypotheses = []
references = []
val_dl = DataLoader(dev_data,
batch_size=config["batch_size_eval"],
shuffle=False,
num_workers=4)
val_dl = BucketingParallelDataLoader(val_dl)
for sentences_x, sentences_y in tqdm(val_dl):
x_in, _, x_mask, x_len = create_batch(sentences_x, vocab_src,
device)
x_mask = x_mask.unsqueeze(1)
if config["model_type"] == "aevnmt":
qz = model.inference(x_in, x_mask)
z = qz.mean
enc_output, enc_hidden = model.encode(x_in, z)
dec_hidden = model.init_decoder(enc_output, enc_hidden, z)
raw_hypothesis = beam_search(model.decoder, model.emb_tgt,
model.generate_tm, enc_output,
dec_hidden, x_mask,
vocab_tgt.size(),
vocab_tgt[SOS_TOKEN],
vocab_tgt[EOS_TOKEN],
vocab_tgt[PAD_TOKEN], config)
else:
enc_output, enc_hidden = model.encode(x_in)
dec_hidden = model.decoder.initialize(enc_output, enc_hidden)
raw_hypothesis = beam_search(model.decoder, model.emb_tgt,
model.generate, enc_output,
dec_hidden, x_mask,
vocab_tgt.size(),
vocab_tgt[SOS_TOKEN],
vocab_tgt[EOS_TOKEN],
vocab_tgt[PAD_TOKEN], config)
hypothesis = batch_to_sentences(raw_hypothesis, vocab_tgt)
model_hypotheses += hypothesis.tolist()
references += sentences_y.tolist()
save_hypotheses(model_hypotheses, 0, config, None)
