Train Custom YOLOV4 using Tao Toolkit such as the annotation is in yolo format

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc)
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)

Hello Community,

I have dataset annotated in yolo format i.e for each label file and in each line I have 5 parameters:class_id x y width height

I would like to train yolov4 on this custom dataset and convert it ot elt and then trt
The problem yolo format annotation doesn’t exist in Tao toolkit any idea what to do in this case ?
in whoch format should I transform the annotation before I start the training?


There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Please prepare for KITTI format label. Refer to Data Annotation Format - NVIDIA Docs

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.