paul-corbalan
/
wasserstein-gan
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
martinarjovsky 2017-03-30 11:24:07 -04:00 committed by GitHub
parent 95ee389e31
commit e05cae9275
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -6,7 +6,7 @@ Code accompanying the paper ["Wasserstein GAN"](https://arxiv.org/abs/1701.07875
## A few notes ## A few notes
- The first time running on the LSUN dataset it can take a long time (up to an hour) to create the dataloader. After the first run a small cache file will be created and the process should take a matter of seconds. The cache is a list of indices in the lmdb database (of LSUN) - The first time running on the LSUN dataset it can take a long time (up to an hour) to create the dataloader. After the first run a small cache file will be created and the process should take a matter of seconds. The cache is a list of indices in the lmdb database (of LSUN)
- The only addition to the code (that we forgot, and will add, on the paper) are the [lines 166-169 of main.py](https://github.com/martinarjovsky/WassersteinGAN/blob/master/main.py#L166-L169). These lines act only on the first 25 generator iterations or very sporadically (once every 500 generator iterations). In such a case, they set the number of iterations on the critic to 100 instead of the default 5. This helps to start with the critic at optimum even in the first iterations. There shouldn't be a major difference in performance, but it can help, especially when visualizing learning curves (since otherwise you'd see the loss going up until the critic is properly trained). This is also why the first 25 iterations take significantly longer than the rest of the training as well. - The only addition to the code (that we forgot, and will add, on the paper) are the [lines 163-166 of main.py](https://github.com/martinarjovsky/WassersteinGAN/blob/master/main.py#L163-L166). These lines act only on the first 25 generator iterations or very sporadically (once every 500 generator iterations). In such a case, they set the number of iterations on the critic to 100 instead of the default 5. This helps to start with the critic at optimum even in the first iterations. There shouldn't be a major difference in performance, but it can help, especially when visualizing learning curves (since otherwise you'd see the loss going up until the critic is properly trained). This is also why the first 25 iterations take significantly longer than the rest of the training as well.
- If your learning curve suddenly takes a big drop take a look at [this](https://github.com/martinarjovsky/WassersteinGAN/issues/2). It's a problem when the critic fails to be close to optimum, and hence it's error stops being a good Wasserstein estimate. Known causes are high learning rates and momentum, and anything that helps the critic get back on track is likely to help with the issue. - If your learning curve suddenly takes a big drop take a look at [this](https://github.com/martinarjovsky/WassersteinGAN/issues/2). It's a problem when the critic fails to be close to optimum, and hence it's error stops being a good Wasserstein estimate. Known causes are high learning rates and momentum, and anything that helps the critic get back on track is likely to help with the issue.
## Prerequisites ## Prerequisites