config.d_out = len(answers.vocab)
config.n_cells = config.n_layers
# double the number of cells for bidirectional networks
if config.birnn:
config.n_cells *= 2
if args.resume_snapshot:
model = torch.load(
args.resume_snapshot,
map_location=lambda storage, location: storage.cuda(args.gpu))
else:
model = LSTMSentiment(config)
if args.word_vectors:
model.embed.weight.data = inputs.vocab.vectors
model.cuda()
criterion = nn.CrossEntropyLoss()
opt = O.Adam(model.parameters())
# model.embed.requires_grad = False
iterations = 0
start_time = time.time()
best_dev_acc = -1
train_iter.repeat = False
header = ' Time Epoch Loss Dev/Loss CD Loss Accuracy Dev/Accuracy'
dev_log_template = ' '.join(
'{:6.0f},{:5.0f},{:9.4f},{:8.6f},{:8.6f},{:12.4f},{:12.4f}'.split(','))
print(len(train))
inputs.build_vocab(train, dev, test)
inputs.vocab.load_vectors('glove.6B.300d')
answers.build_vocab(train)
train_iter, dev_iter, test_iter = data.BucketIterator.splits(
(train, dev, test), batch_size=50, repeat=False, device=DEVICE)
############################################
# CREATING MODEL
print("Creating model")
model = LSTMSentiment(embedding_dim=300,
hidden_dim=168,
vocab_size=300,
label_size=2,
gpu_device=DEVICE)
model.word_embeddings.weight.data = inputs.vocab.vectors
model.cuda(device=DEVICE)
# Load previously checkpointed model if it exists
model_path = "model.pt"
if os.path.exists(model_path) and RESUME_CKPT:
print("Loading previously stored model")
model = torch.load(model_path)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
#############################################
# TRAINING
print("Beginning training")
early_stop_test = 0
tqdm_epoch = tqdm(range(5), desc="Epoch")