def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batch-size', default=32, type=int)
parser.add_argument('--data-type', default='SNLI')
parser.add_argument('--dropout', default=0.25, type=float)
parser.add_argument('--epoch', default=40, type=int)
parser.add_argument('--gpu', default=0, type=int)
parser.add_argument('--learning-rate', default=0.5, type=float)
parser.add_argument('--print-freq', default=3000, type=int)
parser.add_argument('--weight-decay', default=5e-5, type=float)
parser.add_argument('--word-dim', default=300, type=int)
parser.add_argument('--d-e', default=300, type=int)
parser.add_argument('--d-h', default=300, type=int)
args = parser.parse_args()
print('loading SNLI data...')
data = SNLI(args)
setattr(args, 'word_vocab_size', len(data.TEXT.vocab))
setattr(args, 'class_size', len(data.LABEL.vocab))
setattr(args, 'model_time', strftime('%H:%M:%S', gmtime()))
if args.gpu > -1:
setattr(args, 'device', "cuda:0")
else:
setattr(args, 'device', "cpu")
print('training start!')
best_model = train(args, data)
if not os.path.exists('saved_models'):
os.makedirs('saved_models')
torch.save(best_model.state_dict(), f'saved_models/DiSAN_{args.data_type}_{args.model_time}.pt')
print('training finished!')
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batch-size', default=16, type=int)
parser.add_argument('--data-type', default='SNLI')
parser.add_argument('--dropout', default=0.3, type=float)
parser.add_argument('--epoch', default=20, type=int)
parser.add_argument('--gpu', default=0, type=int)
parser.add_argument('--learning-rate', default=3e-4, type=float)
parser.add_argument('--print-freq', default=3000, type=int)
parser.add_argument('--word-dim', default=300, type=int)
parser.add_argument('--filter-size', default=5, type=int)
parser.add_argument('--stride', default=2, type=int)
parser.add_argument('--latent-size', default=500, type=int)
parser.add_argument('--tau', default=0.01, type=float)
parser.add_argument('--hidden-size', default=500, type=int)
parser.add_argument('--mode', default='VAE', help="available mode: VAE, SNLI")
args = parser.parse_args()
print('loading SNLI data...')
data = SNLI(args)
setattr(args, 'word_vocab_size', len(data.TEXT.vocab))
setattr(args, 'class_size', len(data.LABEL.vocab))
setattr(args, 'model_time', strftime('%H:%M:%S', gmtime()))
setattr(args, 'feature_maps', [300, 600, 500])
if args.gpu > -1:
setattr(args, 'device', "cuda:0")
else:
setattr(args, 'device', "cpu")
print('training start!')
if args.mode == 'VAE':
best_model = train(args, data)
else:
best_model = snli_train(args, data)
if not os.path.exists('saved_models'):
os.makedirs('saved_models')
if args.mode == 'VAE':
torch.save(best_model.state_dict(), f'saved_models/DeConv_VAE_{args.data_type}_{args.model_time}.pt')
else:
torch.save(best_model.state_dict(), f'saved_models/DeConv_VAE_SNLI_{args.data_type}_{args.model_time}.pt')
print('training finished!')
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batch-size', default=128, type=int)
parser.add_argument('--data-type', default='SNLI')
parser.add_argument('--dropout', default=0.1, type=float)
parser.add_argument('--epoch', default=20, type=int)
parser.add_argument('--gpu', default=0, type=int)
parser.add_argument('--hidden-dim', default=600, type=int)
parser.add_argument('--learning-rate', default=4e-4, type=float)
parser.add_argument('--print-freq', default=1000, type=int)
parser.add_argument('--weight-decay', default=5e-5, type=float)
parser.add_argument('--word-dim', default=300, type=int)
parser.add_argument('--char-dim', default=15, type=int)
parser.add_argument('--num-feature-maps', default=100, type=int)
parser.add_argument('--num-layers', default=3, type=int)
parser.add_argument('--num-heads', default=5, type=int)
parser.add_argument('--no-char-emb', default=False, action='store_true')
parser.add_argument('--norm-limit', default=10, type=float)
args = parser.parse_args()
print('loading SNLI data...')
data = SNLI(args)
setattr(args, 'word_vocab_size', len(data.TEXT.vocab))
setattr(args, 'char_vocab_size', len(data.char_vocab))
setattr(args, 'max_word_len', data.max_word_len)
setattr(args, 'class_size', len(data.LABEL.vocab))
setattr(args, 'model_time', strftime('%H:%M:%S', gmtime()))
setattr(args, 'FILTER_SIZES', [1, 3, 5])
print('training start!')
best_model = train(args, data)
if not os.path.exists('saved_models'):
os.makedirs('saved_models')
torch.save(best_model.state_dict(),
f'saved_models/BiLSM_GP_{args.data_type}_{args.model_time}.pt')
print('training finished!')
return model
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--batch-size', default=64, type=int)
parser.add_argument('--data-type', default='SNLI')
parser.add_argument('--dropout', default=0.1, type=float)
parser.add_argument('--gpu', default=0, type=int)
parser.add_argument('--hidden-size', default=300, type=int)
parser.add_argument('--word-dim', default=300, type=int)
parser.add_argument('--model-path', required=True)
args = parser.parse_args()
print('loading SNLI data...')
data = SNLI(args)
setattr(args, 'word_vocab_size', len(data.TEXT.vocab))
setattr(args, 'class_size', len(data.LABEL.vocab))
# if block size is lower than 0, a heuristic for block size is applied.
if args.block_size < 0:
args.block_size = data.block_size
print('loading model...')
model = load_model(args, data)
_, acc = test(model, data)
print(f'test acc: {acc:.3f}')
print("Sentence Length:")
# Long: > 20, Regular: 5-20, Short: < 5
print("Long: %.3f\t\t Regular: %.3f\t\t Short: %.3f" %
(correct_dict[3] / total_dict[3], correct_dict[4] / total_dict[4],
correct_dict[5] / total_dict[5]))
print("Contain Specific Words:")
print("Negation: %.3f\t\t Quantifier: %.3f\t Belief: %.3f" %
(correct_dict[6] / total_dict[6], correct_dict[7] / total_dict[7],
correct_dict[8] / total_dict[8]))
if __name__ == "__main__":
device = torch.device('cuda')
snli = SNLI(batch_size=1, gpu=device)
model = Bowman(snli.TEXT.vocab)
model.load_state_dict(torch.load("./model/bowman_48.pth"))
model.to(device)
criterion = nn.CrossEntropyLoss()
# build list for type of specific words
neg = [
"no", "not", "none", "nobody", "nothing", "neither", "nowhere",
"never", "hardly", "barely", "doesnt", "isnt", "wasnt", "shouldnt",
"wouldnt", "couldnt", "wont", "cant", "dont"
]
qua = [
"much", "enough", "more", "most", "less", "least", "no", "none",
"some", "any", "many", "few", "several", "almost", "nearly"
]
shapes = dict(ids1=[None],
ids2=[None],
mask1=[None],
mask2=[None],
label=[])
return tf.data.Dataset.from_generator(lambda: (ex for ex in data),
types, shapes)
if __name__ == '__main__':
print("TensorFlow version: {}".format(tf.__version__))
print("Eager execution: {}".format(tf.executing_eagerly()))
fdata = os.path.join('data', 'proc.json')
if not os.path.isfile(fdata):
data = SNLI.load()
proc = Model.preprocess_data(data)
with open(fdata, 'wt') as f:
json.dump(proc, f)
else:
with open(fdata) as f:
proc = json.load(f)
for k, v in proc.items():
print(k, len(v))
args = argparse.Namespace(
nwords=len(proc['word2index']),
seed=42,
batch=32,
demb=100,