[General Issue] How to train using custom dataset?

[sarmientoj24]

The README does not contain any instructions how to do this on custom data.

For example, how do I change these:

train_dataset:
  type: OpticDiscSeg
  dataset_root: 

[wuyefeilin]

参考文档进行自定义数据集的准备https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/docs/data/marker/marker_cn.md

[sarmientoj24]

i've already done that, but how do you add it there?

[wuyefeilin]

Use the Dataset class, https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/paddleseg/datasets/dataset.py like: train_dataset: type: Dataset dataset_root: xxx

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.