PASCAL VOC Format

Hi,

The required ImageSets and Annotations folders are created by CVAT already.
Please also create the labels.txt for all of your class manually.

https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-collect-detection.md#collecting-your-own-detection-datasets

note: if you want to label a set of images that you already have (as opposed to capturing them from camera), try using a tool like CVAT and export the dataset in Pascal VOC format. Then create a labels.txt in the dataset with the names of each of your object classes.

Thanks.

1 Like