WenmuZhou / DBNet.pytorch

A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization
Apache License 2.0
956 stars 248 forks source link

IndexError #146

Open wwp-max opened 2 years ago

wwp-max commented 2 years ago

Traceback (most recent call last): File "C:/Users/Lenovo/DBNet.pytorch/tools/train.py", line 79, in main(config) File "C:/Users/Lenovo/DBNet.pytorch/tools/train.py", line 41, in main validate_loader = get_dataloader(config['dataset']['validate'], False) File "C:\Users\Lenovo\DBNet.pytorch\data_loader__init__.py", line 84, in get_dataloader _dataset = get_dataset(data_path=data_path, module_name=dataset_name, transform=img_transfroms, dataset_args=dataset_args) File "C:\Users\Lenovo\DBNet.pytorch\data_loader__init.py", line 23, in get_dataset s_dataset = getattr(dataset, module_name)(transform=transform, data_path=data_path, File "C:\Users\Lenovo\DBNet.pytorch\data_loader\dataset.py", line 17, in init super().init(data_path, img_mode, pre_processes, filter_keys, ignore_tags, transform) File "C:\Users\Lenovo\DBNet.pytorch\base\base_dataset.py", line 18, in init__ assert item in self.data_list[0], 'data_list from load_data must contains {}'.format(item_keys) IndexError: list index out of range

配置文件修改成功后,运行train.py就报了这个错误,请问有人知道是什么原因吗?

ming-eng commented 2 years ago

数据格式不对

KKjiaming commented 2 years ago

不是数据格式不对,是你的util里面的get_datalist写错了:line = line.strip('\n').replace('.jpg ', '.jpg\t').split('\t') 。train.txt 的格式是img \t gt 的话replace之后就有两个\t。作者改一下源码把replace去掉或者把train.txt 的格式改一下

Wangqi12138 commented 11 months ago

@KKjiaming 改完还是不太对

WenmuZhou commented 11 months ago

debug看看哦,很简单的