scaelles / OSVOS-TensorFlow

One-Shot Video Object Segmentation

Home Page:http://vision.ee.ethz.ch/~cvlsegmentation/osvos/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

question about training my own data

Adarine99 opened this issue · comments

commented

Hi,
Appreciate your remarkable work and I want to train my own video data,but how can I get the first Labeled image,Is there any software I can use?Thanks a lot.

commented

got it ,I'm using the GIMP.

Good to hear that you found a fix yourself! Otherwise, you could also use the LabelMe project.

  1. The label is 3-channel png? or has a palette as VOC?
  2. Every sampling video has to train a model?
    Thanks!
  1. It's a 1-channel binary image.
  2. That's correct. Every video needs online training.

Thanks for your reply!
I tested some video not from DAVIS, The evaluation results not well, even use on-line training for a long training steps.
How to improve the results? Re-train the parent work?

Thanks!