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

lmdb.Error: Text_detection/Transformer_STR-master/data/evaluation/CUTE80/: No such file or directory #18

Open xianyu-123 opened 3 years ago

xianyu-123 commented 3 years ago

您好，我把验证数据集放在data目录下，执行evaluation.py时提示目录不存在，尝试了绝对路径也是存在这个问题。请问验证数据集应该使用什么样的存放路径，还是config.py需要修改其他的参数。

opconty commented 3 years ago

data_dir = 'path/to/data_lmdb_text_recognition'

config里的这个路径改成你保存数据的路径就好了

lyc728 commented 2 years ago 
assert len(datasets) > 0, 'datasets should not be an empty iterable'  # type: ignore

AssertionError: datasets should not be an empty iterable

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！