def __init__(self, args, schema, price_tracker, model_path, timed):
super(PytorchNeuralSystem, self).__init__()
self.schema = schema
self.price_tracker = price_tracker
self.timed_session = timed
# TODO: do we need the dummy parser?
dummy_parser = argparse.ArgumentParser(description='duh')
options.add_model_arguments(dummy_parser)
options.add_data_generator_arguments(dummy_parser)
dummy_args = dummy_parser.parse_known_args([])[0]
# Load the model.
mappings, model, model_args = model_builder.load_test_model(
model_path, args, dummy_args.__dict__)
self.model_name = model_args.model
vocab = mappings['utterance_vocab']
self.mappings = mappings
generator = get_generator(model, vocab, Scorer(args.alpha), args, model_args)
builder = UtteranceBuilder(vocab, args.n_best, has_tgt=True)
preprocessor = Preprocessor(schema, price_tracker, model_args.entity_encoding_form,
model_args.entity_decoding_form, model_args.entity_target_form)
textint_map = TextIntMap(vocab, preprocessor)
remove_symbols = map(vocab.to_ind, (markers.EOS, markers.PAD))
use_cuda = use_gpu(args)
kb_padding = mappings['kb_vocab'].to_ind(markers.PAD)
dialogue_batcher = DialogueBatcherFactory.get_dialogue_batcher(model=self.model_name,
kb_pad=kb_padding,
mappings=mappings, num_context=model_args.num_context)
# TODO: class variable is not a good way to do this
Dialogue.preprocessor = preprocessor
Dialogue.textint_map = textint_map
Dialogue.mappings = mappings
Dialogue.num_context = model_args.num_context
Env = namedtuple('Env', ['model', 'vocab', 'preprocessor', 'textint_map',
'stop_symbol', 'remove_symbols', 'gt_prefix',
'max_len', 'dialogue_batcher', 'cuda',
'dialogue_generator', 'utterance_builder', 'model_args'])
self.env = Env(model, vocab, preprocessor, textint_map,
stop_symbol=vocab.to_ind(markers.EOS), remove_symbols=remove_symbols,
gt_prefix=1,
max_len=20, dialogue_batcher=dialogue_batcher, cuda=use_cuda,
dialogue_generator=generator, utterance_builder=builder, model_args=model_args)
def __init__(self, args, schema, price_tracker, model_path, timed, name=None):
super(PytorchNeuralSystem, self).__init__()
self.schema = schema
self.price_tracker = price_tracker
self.timed_session = timed
# TODO: do we need the dummy parser?
dummy_parser = argparse.ArgumentParser(description='duh')
options.add_model_arguments(dummy_parser)
options.add_data_generator_arguments(dummy_parser)
dummy_args = dummy_parser.parse_known_args([])[0]
# Load the model.
mappings, model, model_args, critic = rl_model_builder.load_test_model(
model_path, args, dummy_args.__dict__)
# Load critic from other model.
# if name == 'tom':
if hasattr(args, 'load_critic_from') and args.load_critic_from is not None:
critic_path = args.load_critic_from
_, _, _, critic = rl_model_builder.load_test_model(
critic_path, args, dummy_args.__dict__)
self.model_name = model_args.model
vocab = mappings['utterance_vocab']
# print(vocab.word_to_ind)
self.mappings = mappings
generator = get_generator(model, vocab, Scorer(args.alpha), args, model_args)
builder = UtteranceBuilder(vocab, args.n_best, has_tgt=True)
nlg_module = IRNLG(args)
preprocessor = Preprocessor(schema, price_tracker, model_args.entity_encoding_form,
model_args.entity_decoding_form, model_args.entity_target_form)
textint_map = TextIntMap(vocab, preprocessor)
remove_symbols = map(vocab.to_ind, (markers.EOS, markers.PAD))
use_cuda = use_gpu(args)
kb_padding = mappings['kb_vocab'].to_ind(markers.PAD)
# print('args: ', model_args.dia_num, model_args.state_length)
dialogue_batcher = DialogueBatcherFactory.get_dialogue_batcher(model=self.model_name,
kb_pad=kb_padding,
mappings=mappings, num_context=model_args.num_context,
dia_num=model_args.dia_num, state_length=model_args.state_length)
# TODO: class variable is not a good way to do this
Dialogue.preprocessor = preprocessor
Dialogue.textint_map = textint_map
Dialogue.mappings = mappings
Dialogue.num_context = model_args.num_context
Env = namedtuple('Env', ['model', 'vocab', 'preprocessor', 'textint_map',
'stop_symbol', 'remove_symbols', 'gt_prefix',
'max_len', 'dialogue_batcher', 'cuda',
'dialogue_generator', 'utterance_builder', 'model_args', 'critic', 'usetom',
'name', 'price_strategy', 'tom_type', 'nlg_module'])
self.env = Env(model, vocab, preprocessor, textint_map,
stop_symbol=vocab.to_ind(markers.EOS), remove_symbols=remove_symbols,
gt_prefix=1,
max_len=20, dialogue_batcher=dialogue_batcher, cuda=use_cuda,
dialogue_generator=generator, utterance_builder=builder, model_args=model_args,
critic=critic, usetom=(name == 'tom'), name=name,
price_strategy=args.price_strategy, tom_type=args.tom_type, nlg_module=nlg_module)
options.add_model_arguments(dummy_parser)
options.add_data_generator_arguments(dummy_parser)
dummy_args = dummy_parser.parse_known_args([])[0]
if cuda.is_available() and not args.gpuid:
print("WARNING: You have a CUDA device, should run with --gpuid 0")
if args.gpuid:
cuda.set_device(args.gpuid[0])
# Load the model.
mappings, model, model_args = \
model_builder.load_test_model(args.checkpoint, args, dummy_args.__dict__)
# Figure out src and tgt vocab
make_model_mappings(model_args.model, mappings)
schema = Schema(model_args.schema_path, None)
data_generator = get_data_generator(args, model_args, schema, test=True)
# Prefix: [GO, CATEGORY]
# Just giving it GO seems okay as it can learn to copy the CATEGORY from the input
scorer = Scorer(args.alpha)
generator = get_generator(model, mappings['tgt_vocab'], scorer, args,
model_args)
builder = UtteranceBuilder(mappings['tgt_vocab'],
args.n_best,
has_tgt=True)
evaluator = Evaluator(model, mappings, generator, builder, gt_prefix=1)
evaluator.evaluate(args, model_args, data_generator)