ntokens = len(word2idx)
train_path = os.path.join(args.data_path, 'fisher_' + args.dtype, \
'train.pickle')
valid_path = os.path.join(args.data_path, 'fisher_' + args.dtype, \
'valid.pickle')
train_data = pickle.load(open(train_path))
valid_data = pickle.load(open(valid_path))
train_batches = batchify(train_data, args.batch_size)
valid_batches = batchify(valid_data, args.batch_size)
###############################################################################
# Build the model
###############################################################################
model = lm_model.RNNModel(args.model_type, ntokens, args.emsize, \
args.nhid, args.nlayers, args.dropout, args.tied).to(device)
pad_idx = word2idx['<pad>']
criterion = nn.CrossEntropyLoss(ignore_index=pad_idx)
params = filter(lambda p: p.requires_grad, model.parameters())
optimizer = optim.Adam(params, lr=args.lr)
cuda = torch.cuda.is_available()
###############################################################################
# Training code
###############################################################################
def get_batch(batch):
current_batch_size = len(batch)
# pad sequence, ensure correct dimensions
bitch_size = args.batch_size
train_loader = torch.utils.data.DataLoader(dataset=train_data,
batch_size=bitch_size,
shuffle=True,
collate_fn=data.collate_fn)
print('The size of the dictionary is', len(Corpus_Dic))
###############################################################################
# Build the model
###############################################################################
learning_rate = args.lr
ntokens = len(Corpus_Dic)
model = model.RNNModel(args.model, ntokens, args.emsize, args.nhid,
args.nlayers, args.dropout_em, args.dropout_rnn,
args.dropout_cl, args.tied).to(device)
criterion = nn.CrossEntropyLoss(reduction='none')
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=5,
gamma=args.reduce_rate)
###############################################################################
# Training code
###############################################################################
def train():
# Turn on training mode which enables dropout.