diff options
author | nunzip <np.scarh@gmail.com> | 2019-03-14 19:44:05 +0000 |
---|---|---|
committer | nunzip <np.scarh@gmail.com> | 2019-03-14 19:44:05 +0000 |
commit | d09995baa87c27472bd7bbc5c1d4ccf05cb02f8a (patch) | |
tree | 26c194a161cc3597027fbddb02849e365528a00c | |
parent | e45aef7b5df38948406b7a079b63cdedab94c423 (diff) | |
download | e4-gan-d09995baa87c27472bd7bbc5c1d4ccf05cb02f8a.tar.gz e4-gan-d09995baa87c27472bd7bbc5c1d4ccf05cb02f8a.tar.bz2 e4-gan-d09995baa87c27472bd7bbc5c1d4ccf05cb02f8a.zip |
Fix section 1
-rw-r--r-- | report/paper.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/report/paper.md b/report/paper.md index f22ad3b..9aaa278 100644 --- a/report/paper.md +++ b/report/paper.md @@ -16,7 +16,7 @@ Training a shallow GAN with no convolutional layers poses problems such as mode \end{center} \end{figure} -Mode collapse is achieved with our naive *vanilla GAN* (Appendix-\ref{fig:vanilla_gan}) implementation after 200,000 batches. The generated images observed during a mode collapse can be seen on figure \ref{fig:mode_collapse}. The output of the generator only represents few of the labels originally fed. When mode collapse is reached loss function of the generator stops improving as shown in figure \ref{fig:vanilla_loss}. We observe, the discriminator loss tends to zero as the discriminator learns to assume and classify the fake 1s, while the generator is stuck producing 1 and hence not able to improve. +Some of the main challanges faced when training a GAN are: **mode collapse**, **low quality** of images and **mismatch** between generator and discriminator loss. Mode collapse is achieved with our naive *vanilla GAN* (Appendix-\ref{fig:vanilla_gan}) implementation after 200,000 batches. The generated images observed during a mode collapse can be seen on figure \ref{fig:mode_collapse}. The output of the generator only represents few of the labels originally fed. When mode collapse is reached loss function of the generator stops improving as shown in figure \ref{fig:vanilla_loss}. We observe, the discriminator loss tends to zero as the discriminator learns to assume and classify the fake 1s, while the generator is stuck producing 1 and hence not able to improve. A significant improvement to this vanilla architecture is Deep Convolutional Generative Adversarial Networks (DCGAN). |