search

vickyFox / Region-wise-Inpainting

Region-wise GAN, image inpainting
MIT License
53 stars 17 forks source link

Training on custom dataset with custom mask #16

Open Akshay-Ijantkar opened 3 years ago

Akshay-Ijantkar commented 3 years ago

Hello @vickyFox @shihaobai Great work on the paper and even the results look amazing!

Can you please guide me with step by step process on how we need to prepare a dataset for a custom image dataset with a custom mask (if possible)?

How the masks will look like in the sense that whether it will be a colour image on which white patches (the part that will be inpainted from the model) is drawn or it will be a completely black image on which white patches (the part that will be inpainted from the model) is drawn? (in short how to prepare mask and then how to supply it for model training)

I referred to your steps but couldn't completely follow them. Thank you in advance!

tiwarikaran commented 3 years ago

Hi @Akshay-Ijantkar , I am facing the same issues. Have you tried anything before this for in painting?

shihaobai commented 3 years ago

@Akshay-Ijantkar Thanks for your attention! You can utilize the "mask.py" to generate the masks for each training images. Mask input to the model is binarized. The value in the missing area is set to 0, and the value in the known area is set to 1.