def model_fn(model_dir):
logger.info('Loading the model.')
model_info = {}
with open(os.path.join(model_dir, 'model_info.pth'), 'rb') as f:
model_info = torch.load(f)
print('model_info: {}'.format(model_info))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
logger.info('Current device: {}'.format(device))
model = RNNModel(rnn_type=model_info['rnn_type'], ntoken=model_info['ntoken'],
ninp=model_info['ninp'], nhid=model_info['nhid'], nlayers=model_info['nlayers'],
dropout=model_info['dropout'], tie_weights=model_info['tie_weights'])
with open(os.path.join(model_dir, 'model.pth'), 'rb') as f:
model.load_state_dict(torch.load(f))
# after load the rnn params are not a continuous chunk of memory
# this makes them a continuous chunk, and will speed up forward pass
model.rnn.flatten_parameters()
model.to(device).eval()
logger.info('Loading the data.')
corpus = data.Corpus(model_dir)
logger.info('Done loading model and corpus. Corpus dictionary size: {}'.format(len(corpus.dictionary)))
return {'model': model, 'corpus': corpus}
def model_fn(model_dir):
logger.info('Loading the model.')
model_info = {}
with open(os.path.join(model_dir, 'model_info.pth'), 'rb') as f:
model_info = torch.load(f)
print('model_info: {}'.format(model_info))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
logger.info('Current device: {}'.format(device))
model = RNNModel(rnn_type=model_info['rnn_type'], ntoken=model_info['ntoken'],
ninp=model_info['ninp'], nhid=model_info['nhid'], nlayers=model_info['nlayers'],
dropout=model_info['dropout'], tie_weights=model_info['tie_weights'])
with open(os.path.join(model_dir, 'model.pth'), 'rb') as f:
model.load_state_dict(torch.load(f))
# after load the rnn params are not a continuous chunk of memory
# this makes them a continuous chunk, and will speed up forward pass
model.rnn.flatten_parameters()
model.to(device).eval()
logger.info('Loading the data.')
corpus = data.Corpus(model_dir)
logger.info('Done loading model and corpus. Corpus dictionary size: {}'.format(len(corpus.dictionary)))
return {'model': model, 'corpus': corpus}
#0.25, 0.1, 0.2, 0.02, 0.15
# net = CharLSTM(sequence_len=sequence_len, vocab_size=vocab_size, hidden_dim=hs, batch_size=batch_size, n_fac=n_fac, device="cuda:0")
net = RNNModel(rnn_type="LSTM",
ntoken=vocab_size,
ninp=hs,
nhid=hs,
nlayers=3,
dropout=0.25,
dropouth=0.1,
dropouti=0.2,
dropoute=0.02,
wdrop=0,
tie_weights=False,
device="cuda:0")
try:
net.to(net.device)
except:
net.to(net.device)
# optimizer = optim.Adam(net.parameters(), lr=30, weight_decay=0.0001 )
optimizer = torch.optim.SGD(net.parameters(),
lr=1e3,
momentum=0.90,
weight_decay=1.2e-6,
nesterov=False)
# get the validation and the training data
val_idx = int(len(encoded) * (1 - 0.1))
data, val_data = encoded[:val_idx], encoded[val_idx:]
# empty list for the validation losses
val_losses = list()