Closed praeclarumjj3 closed 3 years ago
Hi! I ran a few experiments on training the AOT-GAN on the places2 dataset. However, looking at the loss plots seems like the adversarial loss isn't affecting the learning. The magnitude remains the same during the whole course of training.
adversarial loss
You can see the experiment results here: https://github.com/praeclarumjj3/AOT-GAN-Experiments#5-experiments.
Ohh never mind, the results come out nice if we use the testing pconv dataset anyways. So it's cool!
Hi! I ran a few experiments on training the AOT-GAN on the places2 dataset. However, looking at the loss plots seems like the
adversarial loss
isn't affecting the learning. The magnitude remains the same during the whole course of training.You can see the experiment results here: https://github.com/praeclarumjj3/AOT-GAN-Experiments#5-experiments.