arne/EV5_Beeldherk_Bomen
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added dataset splitter to readme

Browse Source
This commit is contained in:
Tom Selier 2023-10-22 19:07:57 +02:00
parent 0bd7b7809a
commit 39d30708ec
1 changed files with 13 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -113,7 +113,7 @@ $ python ./src/helpers/test/decision_tree.py -i ./out/result-(date/time).csv -o
### Template extraction ### Template extraction
> :warning: **Please note:** <br> > :warning: **Please note:** <br>
> This tool uses the legacy format for datasets.<br> > This tool uses the legacy format for datasets.<br>
> Images are sorted using folders, instead of by name > Images are sorted using folders, instead of by name.
1. Images should have four standard Aruco markers clearly visible 1. Images should have four standard Aruco markers clearly visible
2. Run the template extraction tool with an input directory as argument 2. Run the template extraction tool with an input directory as argument
@ -122,6 +122,18 @@ $ python ./src/experiments/template_extraction/script.py ./dataset
``` ```
3. The script generates new folders, ending with `_out` 3. The script generates new folders, ending with `_out`
4. The paths to any failed images are saved in `skipped.txt` 4. The paths to any failed images are saved in `skipped.txt`
### Dataset splitting
1. Ensure that the dataset is in `./res/dataset`
2. Run the dataset splitter tool:
```sh
$ python ./src/experiments/dataset.py
```
3. Three new folders will be created, containing the following percentage of images:
- `./res/dataset/training`, 70%
- `./res/dataset/validation`, 20%
- `./res/dataset/training`, 10%
4. Images are split pseudorandomly, thus will create the same datasets on different machines.
--- ---
Arne van Iterson<br> Arne van Iterson<br>