From f68f04fb1c665630b97aff94980542aceec49576 Mon Sep 17 00:00:00 2001 From: "Alex J. Champandard" Date: Sun, 30 Oct 2016 10:50:57 +0100 Subject: [PATCH] Improve instructions to train custom models so a new file is output and existing one is not loaded. Use --model parameter! --- README.rst | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/README.rst b/README.rst index ebd797c..4e25bd8 100644 --- a/README.rst +++ b/README.rst @@ -58,16 +58,19 @@ Pre-trained models are provided in the GitHub releases. Training your own is a rm -f ne4x*.pkl.bz2 # Pre-train the model using perceptual loss from paper [1] below. - python3.4 enhance.py --train "data/*.jpg" --scales=2 --epochs=50 \ + python3.4 enhance.py --train "data/*.jpg" --model custom --scales=2 --epochs=50 \ --perceptual-layer=conv2_2 --smoothness-weight=1e7 --adversary-weight=0.0 \ --generator-blocks=4 --generator-filters=64 # Train the model using an adversarial setup based on [4] below. - python3.4 enhance.py --train "data/*.jpg" --scales=2 --epochs=250 \ + python3.4 enhance.py --train "data/*.jpg" --model custom --scales=2 --epochs=250 \ --perceptual-layer=conv5_2 --smoothness-weight=2e4 --adversary-weight=2e5 \ --generator-start=5 --discriminator-start=0 --adversarial-start=5 \ --discriminator-size=64 + # The newly trained model is output into this file... + ls ne4x-custom-*.pkl.bz2 + .. image:: docs/BankLobby_example.gif