代码拉取完成,页面将自动刷新
同步操作将从 大漠/LaTeX_OCR_PRO 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
import click
from model.utils.data_generator import DataGenerator
from model.utils.text import build_vocab, write_vocab
from model.utils.image import build_images
from model.utils.general import Config
@click.command()
@click.option('--data', default="configs/data_small.json",
help='Path to data json config')
@click.option('--vocab', default="configs/vocab_small.json",
help='Path to vocab json config')
def main(data, vocab):
data_config = Config(data)
# datasets
train_set = DataGenerator(
path_formulas=data_config.path_formulas_train,
dir_images=data_config.dir_images_train,
path_matching=data_config.path_matching_train)
test_set = DataGenerator(
path_formulas=data_config.path_formulas_test,
dir_images=data_config.dir_images_test,
path_matching=data_config.path_matching_test)
val_set = DataGenerator(
path_formulas=data_config.path_formulas_val,
dir_images=data_config.dir_images_val,
path_matching=data_config.path_matching_val)
# produce images and matching files
train_set.build(buckets=data_config.buckets)
test_set.build(buckets=data_config.buckets)
val_set.build(buckets=data_config.buckets)
# vocab
vocab_config = Config(vocab)
vocab = build_vocab([train_set], min_count=vocab_config.min_count_tok)
write_vocab(vocab, vocab_config.path_vocab)
if __name__ == "__main__":
main()
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。