parser.add_argument('--dropout', type=float, default=0.5)
parser.add_argument('--emb_dim', type=int, default=64)
parser.add_argument('--hidden_sizes', type=str, default='64,128,128')
parser.add_argument('--l_2', type=float, default=.0)
parser.add_argument('--filter_sizes', type=str, default='2,3,4')
parser.add_argument('--num_filters', type=int, default=128)
args = parser.parse_args()
# ##############################################################################
# Load data
################################################################################
from corpus import middle_load
from data_loader import DataLoader
data = middle_load(args.data)
args.max_len = data["max_len"]
args.vocab_size = data['dict']['vocab_size']
args.label_size = data['dict']['label_size']
args.hidden_sizes = list(map(int, args.hidden_sizes.split(",")))
args.filter_sizes = list(map(int, args.filter_sizes.split(",")))
training_data = DataLoader(data['train']['src'],
data['train']['label'],
args.max_len,
args.label_size,
batch_size=args.batch_size)
validation_data = DataLoader(data['valid']['src'],
data['valid']['label'],
args.max_len,
def __next__(self):
if self._step == self.stop_step:
self._step = 0
raise StopIteration()
_start = self._step * self._batch_size
_bsz = min(self._batch_size, self.sents_size - _start)
self._step += 1
data = data_pad(self._src_sents[_start:_start + _bsz], self._max_len)
label = label_pad(self._label[_start:_start + _bsz], self.label_size)
return data, label
if __name__ == '__main__':
from corpus import middle_load
data = middle_load('./data/corpus')
print(data['dict']['label'])
i2w = {v: k for k, v in data['dict']['train'].items()}
training_data = DataLoader(data['train']['src'], data['train']['label'],
16, 6, 8)
data, label = next(training_data)
for d, l in zip(data, label):
print([i2w[i] for i in d])
print(l)
