From e732acc1cbb5b984a70c89de22e012e9f483ede5 Mon Sep 17 00:00:00 2001
From: robertfoerster <65739020+foersterrobert@users.noreply.github.com>
Date: Thu, 27 Jan 2022 20:30:07 +0100
Subject: [PATCH] Changing default b1 & b2 values.

In the paper, the proposed betas of Adam were set to 0.0 & 0.9, so I guess it makes sense to use those as default here as well. I also got more stable results during training using these. But maybe you tweaked the betas on purpose, and the old ones make more sense to you. TY for your implementations btw :).
---
 implementations/wgan_gp/wgan_gp.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/implementations/wgan_gp/wgan_gp.py b/implementations/wgan_gp/wgan_gp.py
index 17d5afbf..139d70b4 100644
--- a/implementations/wgan_gp/wgan_gp.py
+++ b/implementations/wgan_gp/wgan_gp.py
@@ -22,8 +22,8 @@
 parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")
 parser.add_argument("--batch_size", type=int, default=64, help="size of the batches")
 parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
-parser.add_argument("--b1", type=float, default=0.5, help="adam: decay of first order momentum of gradient")
-parser.add_argument("--b2", type=float, default=0.999, help="adam: decay of first order momentum of gradient")
+parser.add_argument("--b1", type=float, default=0.0, help="adam: decay of first order momentum of gradient")
+parser.add_argument("--b2", type=float, default=0.9, help="adam: decay of first order momentum of gradient")
 parser.add_argument("--n_cpu", type=int, default=8, help="number of cpu threads to use during batch generation")
 parser.add_argument("--latent_dim", type=int, default=100, help="dimensionality of the latent space")
 parser.add_argument("--img_size", type=int, default=28, help="size of each image dimension")