在mmsegmentation上训练自定义数据集。

huangapple go评论70阅读模式
英文:

Training custom dataset on mmsegmentation

问题

I am trying to do semantic segmentation on Freiburg Forest dataset using mmsegmentation repo on GitHub. The link to the same is attached below.

https://github.com/open-mmlab/mmsegmentation

我正在尝试在GitHub上使用mmsegmentation仓库对Freiburg Forest数据集进行语义分割。下面附上了相同的链接。

I have made config file for the Freiburg Forest dataset and I have also added dataset file to /mmsetg/datatsets folder. When I am trying to training with single GPU, I am getting following error.

我已经为Freiburg Forest数据集创建了配置文件,并将数据集文件添加到/mmsetg/datatsets文件夹中。但当我尝试使用单个GPU进行训练时,我遇到了以下错误。

I am not able to understand, where else should I add this custom dataset so that model will accept it.

我不明白,我还应该在哪里添加这个自定义数据集,以便模型接受它。

Can someone please help me with this? Thanks in advance.

可以有人帮我解决这个问题吗?提前感谢。

英文:

I am trying to do semantic segmentation on Freiburg Forest dataset using mmsegmentation repo on github. The link to the same is attached below.

https://github.com/open-mmlab/mmsegmentation

I have made config file for the Freiburg Forest dataset and I have also added dataset file to /mmsetg/datatsets folder. When I am trying to training with single GPU,I am getting following error.

I am not able to understand, where else should I add this custom dataset so that model will accept it.

Can someone please help me with this? Thanks in advance.

Traceback (most recent call last):
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 122, in build_from_cfg
    obj = obj_cls(**args)  # type: ignore
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 219, in __init__
    super().__init__(runner, dataloader)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/base_loop.py", line 26, in __init__
    self.dataloader = runner.build_dataloader(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1346, in build_dataloader
    dataset = DATASETS.build(dataset_cfg)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/registry/registry.py", line 548, in build
    return self.build_func(cfg, *args, **kwargs, registry=self)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 100, in build_from_cfg
    raise KeyError(
KeyError: 'FreiburgForestDataset is not in the dataset registry. Please check whether the value of `FreiburgForestDataset` is correct or it was registered as expected. More details can be found at https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module'

答案1

得分: 1

请参考以下翻译:

我相信你还需要在此处文件中导入它,并将其添加到__all__中。

英文:

I believe you also need to import it in this file and add it to __all__.

huangapple
  • 本文由 发表于 2023年5月21日 22:39:07
  • 转载请务必保留本文链接:https://go.coder-hub.com/76300439.html
匿名

发表评论

匿名网友

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen:

确定