From 37046985faf7ddc327148f77a6b410e1bc491d5f Mon Sep 17 00:00:00 2001 From: Matt Cooper Date: Sat, 13 Aug 2016 00:53:53 -0400 Subject: Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 19481a1..2a4b0d1 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ While the adversarial network is clearly superior in terms of sharpness and cons -Using the error measurements outlined in the paper (Peak Signal to Noise Ratio and Sharp Difference) did not show significant difference between adversarial and non-adversarial training. I believe this is because sequential frames from the Ms. Pac-Man dataset have no motion in the majority of pixels. While I could not replicate the paper's results numerically, it is clear that adversarial training produces a qualitative improvement in the sharpness of the generated frames, especially over long time spans. You can view the loss and error statistics by running `tensorboard --logdir=./Results/Summaries/` from the root of this project. +Using the error measurements outlined in the paper (Peak Signal to Noise Ratio and Sharp Difference) did not show significant difference between adversarial and non-adversarial training. I believe this is because sequential frames from the Ms. Pac-Man dataset have no motion in the majority of pixels, while the original paper was trained on real-world video where there is motion in much of the frame. Despite this, it is clear that adversarial training produces a qualitative improvement in the sharpness of the generated frames, especially over long time spans. You can view the loss and error statistics by running `tensorboard --logdir=./Results/Summaries/` from the root of this project. ## Usage -- cgit v1.2.3-70-g09d2