train_data_944K = data.encode_phrase_pairs_RLTR(phrase_pairs_944K,
emb_dict)
train_data_944K = data.group_train_data_RLTR_for_support(train_data_944K)
dict944k = data.get944k(DICT_944K)
log.info("Reading dict944k from %s is done. %d pairs in dict944k.",
DICT_944K, len(dict944k))
dict944k_weak = data.get944k(DICT_944K_WEAK)
log.info(
"Reading dict944k_weak from %s is done. %d pairs in dict944k_weak",
DICT_944K_WEAK, len(dict944k_weak))
rand = np.random.RandomState(data.SHUFFLE_SEED)
rand.shuffle(train_data)
train_data, test_data = data.split_train_test(train_data, TRAIN_RATIO)
log.info("Training data converted, got %d samples", len(train_data))
log.info("Train set has %d phrases, test %d", len(train_data),
len(test_data))
log.info("Batch size is %d", args.batches)
log.info("Number of the support sets %d", args.supportsets)
if (args.att):
log.info("Using attention mechanism to train the SEQ2SEQ model...")
else:
log.info("Train the SEQ2SEQ model without attention mechanism...")
if (args.lstm):
log.info("Using LSTM mechanism to train the SEQ2SEQ model...")
else:
log.info("Using RNN mechanism to train the SEQ2SEQ model...")
if (args.embed_grad):
log.info(
args = parser.parse_args()
device = torch.device("cuda" if args.cuda else "cpu")
saves_path = os.path.join(SAVES_DIR, args.name)
os.makedirs(saves_path, exist_ok=True)
phrase_pairs, emb_dict = \
data.load_data(genre_filter=args.data)
log.info("Obtained %d phrase pairs with %d uniq words", len(phrase_pairs),
len(emb_dict))
data.save_emb_dict(saves_path, emb_dict)
end_token = emb_dict[data.END_TOKEN]
train_data = data.encode_phrase_pairs(phrase_pairs, emb_dict)
rand = np.random.RandomState(data.SHUFFLE_SEED)
rand.shuffle(train_data)
train_data, test_data = data.split_train_test(train_data)
log.info("Training data converted, got %d samples", len(train_data))
train_data = data.group_train_data(train_data)
test_data = data.group_train_data(test_data)
log.info("Train set has %d phrases, test %d", len(train_data),
len(test_data))
rev_emb_dict = {idx: word for word, idx in emb_dict.items()}
net = model.PhraseModel(emb_size=model.EMBEDDING_DIM,
dict_size=len(emb_dict),
hid_size=model.HIDDEN_STATE_SIZE).to(device)
log.info("Model: %s", net)
writer = SummaryWriter(comment="-" + args.name)
net.load_state_dict(torch.load(args.load))
args = parser.parse_args()
device = torch.device("cuda" if args.cuda else "cpu")
saves_path = os.path.join(SAVES_DIR, args.name)
os.makedirs(saves_path, exist_ok=True)
phrase_pairs, emb_dict = data.load_data(genre_filter=args.data)
log.info("Obtained %d phrase pairs with %d uniq words",
len(phrase_pairs), len(emb_dict))
data.save_emb_dict(saves_path, emb_dict)
end_token = emb_dict[data.END_TOKEN]
train_data = data.encode_phrase_pairs(phrase_pairs, emb_dict)
rand = np.random.RandomState(data.SHUFFLE_SEED)
rand.shuffle(train_data)
log.info("Training data converted, got %d samples", len(train_data))
train_data, test_data = data.split_train_test(train_data)
log.info("Train set has %d phrases, test %d", len(train_data), len(test_data))
net = model.PhraseModel(emb_size=model.EMBEDDING_DIM, dict_size=len(emb_dict),
hid_size=model.HIDDEN_STATE_SIZE).to(device)
log.info("Model: %s", net)
writer = SummaryWriter(comment="-" + args.name)
optimiser = optim.Adam(net.parameters(), lr=LEARNING_RATE)
best_bleu = None
for epoch in range(MAX_EPOCHES):
losses = []
bleu_sum = 0.0
bleu_count = 0
for batch in data.iterate_batches(train_data, BATCH_SIZE):
