Why are the progressively posted loss numbers very different from the ones in the graph?

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
martinf
Posts: 27
Joined: Thu Sep 29, 2022 7:58 pm
Been thanked: 3 times

Why are the progressively posted loss numbers very different from the ones in the graph?

Post by martinf »

Using the Dfl Sae model at the moment. The graph shows numbers that are about 33% of the numbers posted at the save intervals. Is this something peculiar to this model as there are three graphs (32, 64 and 128). Are those to be added together to arrive at the save interval number?

User avatar
torzdf
Posts: 2649
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 128 times
Been thanked: 622 times

Re: Why are the progressively posted loss numbers very different from the ones in the graph?

Post by torzdf »

Because the loss values shown are a summing of all of the loss outputs. There are 3 outputs (using multiple outputs with that model) hence why the graphs each show about 33% of the total value

My word is final

Locked