Open NourO93 opened 3 weeks ago
There is a while loop in the run_loop function of train_util.py. When it requires os.environ.get("DIFFUSION_TRAINING_TEST", "") and self.step > 0, it will break the training loop. You can set the number of epochs, and when self.step > epochs, break it.
As the title says. I assume that the number of epochs is different than "diffusion steps". Can you please guide me on how to change the number of epochs?