User Tools
Differences
This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
|
cs:vision:image_tagging:legacy [2018/02/28 08:00] Ryan Summers created |
cs:vision:image_tagging:legacy [2018/02/28 08:02] Ryan Summers |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | ===== Legacy Documentation ===== | ||
| + | === Sloth and Darknet === | ||
| + | Since we use Darknet, there are special configurations needed. After having cloned the [[https://github.com/PalouseRobosub/vision_dev|vision_dev]] repository, add the following line to your .bashrc, replacing the dummy path with the path to the vision_dev/sloth directory so that sloth can create darknet files. | ||
| + | |||
| + | export PYTHONPATH=/path/to/vision_dev/sloth:$PYTHONPATH | ||
| + | |||
| + | ---- | ||
| + | |||
| + | === Using sloth output with Darknet === | ||
| + | When attempting to use tagged images with darknet, the annotation file will need to be in the correct format. To convert to this format, use the following command | ||
| + | |||
| + | sloth convert <original file> <new_filename>.darknet | ||
| + | |||
| + | This will ask sloth to convert an annotation file in one format to the correct *.darknet format. | ||
| + | |||
| + | Once the file is in this format, you will need to run the `sloth_to_darknet.py` script which will generate the multiple files darknet requires based upon the compact information in the *.darknet file. | ||
| + | |||
| + | The following is an example command to generate said files. | ||
| + | |||
| + | ./sloth_to_darknet.py -f /path/to/label/file -o /path/to/annotation/dir/ (optional)[-t training_list_filename.txt] | ||
| + | |||
| + | ---- | ||
| === Getting Data to Label === | === Getting Data to Label === | ||
