YuHengsss / YOLOV

This repo is an implementation of PyTorch version YOLOV Series
Apache License 2.0
283 stars 39 forks source link

Custom data #14

Closed Michelvl92 closed 1 year ago

Michelvl92 commented 1 year ago

Hi, it is unclear how I can format my custom dataset to your expected format, Can possibly provide information on how I can convert my dataset, and what are you expected format? For E.g. it is unclear to me what the context is of the video sequences.

YuHengsss commented 1 year ago

Hi, it is unclear how I can format my custom dataset to your expected format, Can possibly provide information on how I can convert my dataset, and what are you expected format? For E.g. it is unclear to me what the context is of the video sequences.

Hello, thanks for your attention. I'm sorry for my unclear description. The video sequences contain all of the file names from the VID dataset in list format, you can try to load it with the pickle package. The whole structure like : [VID1,VID2,...,VIDn], while in VID1 the structure is [frame1_path, ... , framen_path].