def __init__(self, mode, config_file, model_file):
"""
BERT NLU initialization.
Args:
mode (str):
can be either `'usr'`, `'sys'` or `'all'`, representing which side of data the model was trained on.
model_file (str):
model path or url
Example:
nlu = BERTNLU(mode='all', model_file='https://convlab.blob.core.windows.net/models/bert_multiwoz_all_context.zip')
"""
assert mode == 'usr' or mode == 'sys' or mode == 'all'
config_file = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'configs/{}'.format(config_file))
config = json.load(open(config_file))
DEVICE = config['DEVICE']
root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
data_dir = os.path.join(root_dir, config['data_dir'])
output_dir = os.path.join(root_dir, config['output_dir'])
if not os.path.exists(os.path.join(data_dir, 'intent_vocab.json')):
preprocess(mode)
intent_vocab = json.load(
open(os.path.join(data_dir, 'intent_vocab.json')))
tag_vocab = json.load(open(os.path.join(data_dir, 'tag_vocab.json')))
dataloader = Dataloader(
intent_vocab=intent_vocab,
tag_vocab=tag_vocab,
pretrained_weights=config['model']['pretrained_weights'])
print('intent num:', len(intent_vocab))
print('tag num:', len(tag_vocab))
bert_config = BertConfig.from_pretrained(
config['model']['pretrained_weights'])
best_model_path = os.path.join(output_dir, 'pytorch_model.bin')
if not os.path.exists(best_model_path):
if not os.path.exists(output_dir):
os.makedirs(output_dir)
print('Load from model_file param')
archive_file = cached_path(model_file)
archive = zipfile.ZipFile(archive_file, 'r')
archive.extractall(root_dir)
archive.close()
print('Load from', best_model_path)
model = JointBERT(bert_config, config['model'], DEVICE,
dataloader.tag_dim, dataloader.intent_dim)
model.load_state_dict(
torch.load(os.path.join(output_dir, 'pytorch_model.bin'), DEVICE))
model.to(DEVICE)
model.eval()
self.model = model
self.dataloader = dataloader
print("BERTNLU loaded")
torch.manual_seed(9102)
random.seed(9102)
np.random.seed(9102)
if __name__ == '__main__':
mode = sys.argv[1]
config_path = 'configs/multiwoz_{}.json'.format(mode)
config = json.load(open(config_path))
DEVICE = config['DEVICE']
root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
data_dir = os.path.join(root_dir, config['data_dir'])
output_dir = os.path.join(root_dir, config['output_dir'])
log_dir = os.path.join(root_dir, config['log_dir'])
if not os.path.exists(os.path.join(data_dir, 'data.pkl')):
preprocess(mode)
data = pickle.load(open(os.path.join(data_dir, 'data.pkl'), 'rb'))
intent_vocab = pickle.load(
open(os.path.join(data_dir, 'intent_vocab.pkl'), 'rb'))
tag_vocab = pickle.load(open(os.path.join(data_dir, 'tag_vocab.pkl'),
'rb'))
for key in data:
print('{} set size: {}'.format(key, len(data[key])))
print('intent num:', len(intent_vocab))
print('tag num:', len(tag_vocab))
dataloader = Dataloader(data, intent_vocab, tag_vocab,
config['model']["pre-trained"])
best_model_path = os.path.join(output_dir, 'bestcheckpoint.tar')
def __init__(self, mode, model_file):
"""
BERT NLU initialization.
Args:
mode (str):
can be either `'usr'`, `'sys'` or `'all'`, representing which side of data the model was trained on.
model_file (str):
model path or url
Example:
nlu = BERTNLU(mode='usr', model_file='https://convlab.blob.core.windows.net/models/bert_multiwoz_usr.zip')
"""
assert mode == 'usr' or mode == 'sys' or mode == 'all'
config_file = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'configs/multiwoz_{}.json'.format(mode))
config = json.load(open(config_file))
DEVICE = config['DEVICE']
root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
data_dir = os.path.join(root_dir, config['data_dir'])
output_dir = os.path.join(root_dir, config['output_dir'])
if not os.path.exists(os.path.join(data_dir, 'data.pkl')):
preprocess(mode)
data = pickle.load(open(os.path.join(data_dir, 'data.pkl'), 'rb'))
intent_vocab = pickle.load(
open(os.path.join(data_dir, 'intent_vocab.pkl'), 'rb'))
tag_vocab = pickle.load(
open(os.path.join(data_dir, 'tag_vocab.pkl'), 'rb'))
dataloader = Dataloader(data, intent_vocab, tag_vocab,
config['model']["pre-trained"])
best_model_path = os.path.join(output_dir, 'bestcheckpoint.tar')
if not os.path.exists(best_model_path):
if not os.path.exists(output_dir):
os.makedirs(output_dir)
print('Load from model_file param')
archive_file = cached_path(model_file)
archive = zipfile.ZipFile(archive_file, 'r')
archive.extractall(root_dir)
archive.close()
print('Load from', best_model_path)
checkpoint = torch.load(best_model_path, map_location=DEVICE)
print('train step', checkpoint['step'])
model = BertNLU(config['model'],
dataloader.intent_dim,
dataloader.tag_dim,
DEVICE=DEVICE,
intent_weight=dataloader.intent_weight)
model_dict = model.state_dict()
state_dict = {
k: v
for k, v in checkpoint['model_state_dict'].items()
if k in model_dict.keys()
}
model_dict.update(state_dict)
model.load_state_dict(model_dict)
model.to(DEVICE)
model.eval()
self.model = model
self.dataloader = dataloader
print("BERTNLU loaded")