This shows you the differences between two versions of the page.
Both sides previous revision Previous revision | Last revision Both sides next revision | ||
cs:vision:image_tagging:legacy [2018/02/28 08:00] Ryan Summers |
cs:vision:image_tagging:legacy [2018/02/28 08:01] Ryan Summers |
||
---|---|---|---|
Line 1: | Line 1: | ||
== Legacy Documentation == | == 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 === | ||