Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Doc] update faq #2476

Merged
merged 3 commits into from
May 17, 2023
Merged

[Doc] update faq #2476

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7e84868
[Doc] update faq
cir7 May 15, 2023
6b95331
fix typo
cir7 May 17, 2023
bcb5588
Update docs/en/get_started/faq.md
Dai-Wenxun May 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions docs/en/get_started/faq.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,15 @@ If the contents here do not cover your issue, please create an issue using the [
In MMAction2, We set `load_from=None` as default in `configs/_base_/default_runtime.py` and owing to [inheritance design](/docs/en/user_guides/config.md),
users can directly change it by setting `load_from` in their configs.

- **How to use `RawFrameDataset` for training?**

In MMAction2 1.x version, most of the configs take `VideoDataset` as the default dataset type, which is much more friendly to file storage. If you want to use `RawFrameDataset` instead, there are two steps to modify:

- Dataset: modify `dataset_type = 'VideoDataset'` to `dataset_type = 'RawFrameDataset'`, and please make sure that the variable has been passed to `dataset` in `train_dataloader`/`val_dataloader`/`test_dataloader`.
- Transforms: delete `dict(type='DecordInit', **file_client_args)`, modify `dict(type='DecordDecode')` to `dict(type='RawFrameDecode', **file_client_args)` in `train_pipeline`/`val_pipeline`/`test_pipeline`.

For More modifications about customizing datasets, please refer to [prepare dataset](../user_guides/prepare_dataset.md) and [customize dataset](../advanced_guides/customize_dataset.md).
Dai-Wenxun marked this conversation as resolved.
Show resolved Hide resolved

## Testing

- **How to make predicted score normalized by softmax within \[0, 1\]?**
Expand Down