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

docs(custom dataset): Add another essential step in CUSTOM_DATASET.md #114

Open
wants to merge 1 commit into
base: customdoc
Choose a base branch
from
Open

docs(custom dataset): Add another essential step in CUSTOM_DATASET.md #114

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 8 additions & 4 deletions CUSTOM_DATASET.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,9 +64,13 @@ We provide a step-by-step tutorial on how to train your custom dataset with Acti
- You may refer to the `libs/datasets/thumos14.py` for details.
- You may need to change some information in the dataset file, e.g., db_attributes to control the evaulation settings, e.g., the tIoU for evaluation.

6. Create a config file for THUMOS14.
- You may refer to the `configs/thumos14_i3d.py` for details.
- You may need to change some items in the config file, e.g., `train_split` and `val_split` for the subset name. `json_file` and `feat_folder` for dataset location, `feat_stride` (as `frequency` in step 3).
6. Add the dataset name to the Dataset Registry.

- In the `libs/__init__.py` file, include the dataset name you set in step 5 within `@register_dataset()`.

7. Create a config file for THUMOS14.
- You may refer to the `configs/thumos14_i3d.yaml` for details.
- You may need to change some items in the config file, e.g., `train_split` and `val_split` for the subset name. `json_file` and `feat_folder` for dataset location, `feat_stride` (as `frequency` in step 3).

7. Start to train and eval on your dataset.
- Please refer to `tools/run_all_exps.sh` to get some examples for training/testing.
- Please refer to `tools/run_all_exps.sh` to get some examples for training/testing.