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()
_, dev_data, vocab_src, vocab_tgt = load_dataset_joey(config)
model, _, validate_fn = create_model(vocab_src, vocab_tgt, config)
checkpoint_path = "output/aevnmt_word_dropout_0.1/checkpoints/aevnmt_word_dropout_0.1"
state = torch.load(checkpoint_path)
model.load_state_dict(state['state_dict'])
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["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)