Loss Function

Want to understand the training process better? Got tips for which model to use and when? This is the place for you


Forum rules

Read the FAQs and search the forum before posting a new topic.

This forum is for discussing tips and understanding the process involved with Training a Faceswap model.

If you have found a bug are having issues with the Training process not working, then you should post in the Training Support forum.

Please mark any answers that fixed your problems so others can find the solutions.

Locked
User avatar
p96xl
Posts: 12
Joined: Wed Sep 18, 2019 11:45 pm
Answers: 1
Has thanked: 4 times

Loss Function

Post by p96xl »

Whats the difference between all the loss functions? and which one will give me the best results? Also, does Penalize Mask Loss improve results?

by torzdf » Fri Oct 04, 2019 9:35 pm

There is a training guide coming soon. In brief:

torzdf wrote:
  • Loss
    The loss function to use.

    There are various different ways to calculate Loss, or for a NN to discern how well it is doing at training a model. I won't go into details of each of the functions available, as it would be a somewhat lengthy process and there is plenty of information about each of these functions on the internet.

    • Loss Function - The most popular loss methods to use are MAE (Mean Absolute Error) and SSIM (Structural Similarity). My personal preference is to use SSIM.

    • Penalized Mask Loss - This option dictates whether areas of the image that fall outside of the face area should be given less importance than areas that fall inside the face area. This option should always be enabled

Go to full post
User avatar
torzdf
Posts: 2672
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 131 times
Been thanked: 625 times

Re: Loss Function

Post by torzdf »

There is a training guide coming soon. In brief:

torzdf wrote:
  • Loss
    The loss function to use.

    There are various different ways to calculate Loss, or for a NN to discern how well it is doing at training a model. I won't go into details of each of the functions available, as it would be a somewhat lengthy process and there is plenty of information about each of these functions on the internet.

    • Loss Function - The most popular loss methods to use are MAE (Mean Absolute Error) and SSIM (Structural Similarity). My personal preference is to use SSIM.

    • Penalized Mask Loss - This option dictates whether areas of the image that fall outside of the face area should be given less importance than areas that fall inside the face area. This option should always be enabled

My word is final

Locked