search

JingchunCheng / SegFlow

Demo code of the paper "SegFlow: Joint Learning for Video Object Segmentation and Optical Flow", in ICCV 2017
178 stars 41 forks source link

finetuning the segmentation network (online training) #6

Closed jakeoung closed 6 years ago

jakeoung commented 6 years ago

At the end of Section 4.1 in the paper, there is a description of online training for segmentation.

I want to finetune the segmentation. Can I know how to do it? Or, if I test

python infer_DAVIS.py VIDEO_NAME,

is it automatically finetuned, using the segmentation in the first frame?

wasidennis commented 6 years ago

Hi @jakeoung,

The code in this repository does not contain the finetuning part. If you want to finetune the model on a specific object, please take a look at our another repository for the example: https://github.com/JingchunCheng/Seg-with-SPN. They have different models but the methodology for finetuning is the same.