search

opconty / Transformer_STR

PyTorch implementation of my new method for Scene Text Recognition (STR) based on Transformer,Equipped with Transformer, this method outperforms the best model of the aforementioned deep-text-recognition-benchmark by 7.6% on CUTE80.
https://mp.weixin.qq.com/s/a_ahIwxiCaO7Bxmj81HUTw
224 stars 53 forks source link

assert len(datasets) > 0, 'datasets should not be an empty iterable' # type: ignore #19

Open xianyu-123 opened 3 years ago

xianyu-123 commented 3 years ago

assert len(datasets) > 0, 'datasets should not be an empty iterable' # type: ignore AssertionError: datasets should not be an empty iterable

运行evaluation或者train，使用绝对路径会提示路径不存在，使用相对路径提示数据集不能为空，这种情况应该怎么操作呢？有没有人能指点一下，谢谢了

opconty commented 3 years ago

data_dir = 'path/to/data_lmdb_text_recognition'

config里配置一下数据集路径

xianyu-123 commented 3 years ago

您好，

data_dir = 'path/to/data_lmdb_text_recognition'

config里配置一下数据集路径

您好，我将数据放在DATA目录下，运行时候提示：lmdb.Error: /home/wgj/DATA/CUTE80_Dataset/evaluation/CUTE80: No such file or directory

yjLeeee commented 3 years ago

Did you fix it?

lyc728 commented 2 years ago

您好，

data_dir = 'path/to/data_lmdb_text_recognition' config里配置一下数据集路径

您好，我将数据放在DATA目录下，运行时候提示：lmdb.Error: /home/wgj/DATA/CUTE80_Dataset/evaluation/CUTE80: No such file or directory

你好，你解决了吗？

fangshuiyun commented 1 year ago

class Config(config.Config): train_data = os.path.join(config.data_dir, 'training') valid_data = os.path.join(config.data_dir, 'validation') saved_model = '' select_data = ['SJ', 'MJ'] # select training data 把select_data = ['SJ', 'MJ']改成select_data = ['ST', 'MJ']，数据集ST写错了！