Closed Tomingz closed 4 years ago
Hello @Tomingz. My apologies for the delayed response.
If you want to adapt it to new videos, you need to fine-tune FgSegNet with a minimal training set (freeze the weights and fine-tune some layers based on the amount of your training set). Hope this gives you a hint.
(reopen issued as needed)
thanks a lot for your great work, but how to make my own data like the CDnet2014? and how to train it?