So you guys don't think i'm pulling your leg. (Patreon)
Content
The devil really are in the details. Slowly been managing to improve the model, but each day there is something new to learn, how batch affect the model and what is the best values for the training.
The models that I have trained so far are pretty good, but it's seen that it only that the right value so they can become great. The test last night manage to make the model work a lot better for bigger motion, but it removed some of the details. So I'm trying something today that will keep the motion and details.
At least now I'm managing to train the RL model along the anime one. So both should be ready together.
After that (and the build release) I still need to make a new Dataset for RL, because the current datset is really limiting the RL model.