Results 22 comments of Le0v1n

1. Make sure to add meta_info to both train_dataloader and val_dataloader. 2. Ensure that model.bbox_head.head_module.num_classes is set correctly.

After running, a relatively complete `config.py` file will be generated. Check whether all the `class_name` related items in this file have been changed to your `class_name`.

@nyatorch And you, my friend, are a true hero.

现在的文档很多地方和代码对不上,难搞

For example, `blue_obj` may be displayed with a yellow box, while `yellow_obj` may be displayed with a blue box, which is very confusing 😭 .

`paddleseg/core/train.py`: - `avg_loss_list = [l[0] / log_iters for l in avg_loss_list]` --> `avg_loss_list = [l / log_iters for l in avg_loss_list]`

@Whilconn 当然可以,因为 Github 无法直接上传 `.html` 格式的文档,因此我压缩了一下。你可以看一下,插件不起作用。 [examples.zip](https://github.com/Whilconn/one-toc/files/14818813/examples.zip) 下面是生成这个 html 的 Markdown 原始内容: ``` # 1. Title 1 ## 1.1 Example11 一个示例文档。 ## 1.2 Example12 ```python import numpy as np print("Hello...

Thank you very much for your response! @glenn-jocher Actually, I didn't think of the RGBA image format, and your explanation has given me inspiration. I have another small question. When...