Add training scripts, they take a while to run!

Author: alexjc

README.rst

@@ -94,7 +94,7 @@ Pre-trained models are provided in the GitHub releases.  Training your own is a
 
 The easiest way to get up-and-running is to `install Docker <https://www.docker.com/>`_. Then, you should be able to download and run the pre-built image using the ``docker`` command line tool.  Find out more about the ``alexjc/neural-enhance`` image on its `Docker Hub <https://hub.docker.com/r/alexjc/neural-enhance/>`_ page.
 
-Here's the simplest way you can call the script using ``docker``, assuming you're familiar with using ``-v` to mount folders you can use this directly to specify files to enhance:
+Here's the simplest way you can call the script using ``docker``, assuming you're familiar with using ``-v`` argument to mount folders you can use this directly to specify files to enhance:
 
 .. code:: bash
 
@@ -111,7 +111,7 @@ Here's the simplest way you can call the script using ``docker``, assuming you'r
     # Now run any of the examples above using this alias, without the `.py` extension.
     enhance --zoom=1 --model=repair images/broken.jpg
 
-**Multiple Images** — To enhance multiple images in a row (faster) from a folder or widlcard specification, make sure to quote the argument to the alias command:
+**Multiple Images** — To enhance multiple images in a row (faster) from a folder or wildcard specification, make sure to quote the argument to the alias command:
 
 .. code:: bash
     

scripts/ne1x-photo-repair.sh

@@ -0,0 +1,18 @@
+#!/bin/sh
+
+python3.4 enhance.py \
+    --train "$OPEN_IMAGES_PATH/*/*.jpg" --type photo --model repair \
+    --epochs=50 --batch-shape=256 --device=gpu1 \
+    --generator-downscale=2 --generator-upscale=2 \
+    --generator-blocks=8 --generator-filters=128 --generator-residual=0 \
+    --perceptual-layer=conv2_2 --smoothness-weight=1e7 --adversary-weight=0.0 \
+    --train-noise=2.0 --train-jpeg=30
+
+python3.4 enhance.py \
+    --train "$OPEN_IMAGES_PATH/*/*.jpg" --type photo --model repair \
+    --epochs=500 --batch-shape=240 --device=gpu1 \
+    --generator-downscale=2 --generator-upscale=2 \
+    --perceptual-layer=conv5_2 --smoothness-weight=5e3 --adversary-weight=5e1 \
+    --generator-start=10 --discriminator-start=0 --adversarial-start=10 \
+    --discriminator-size=48 \
+    --train-noise=2.0 --train-jpeg=30

scripts/ne2x-photo-default.sh

@@ -0,0 +1,18 @@
+#!/bin/sh
+
+python3.4 enhance.py \
+    --train "$OPEN_IMAGES_PATH/*/*.jpg" --type photo --model default \
+    --epochs=50 --batch-shape=256 --device=gpu0 \
+    --generator-downscale=0 --generator-upscale=1 \
+    --generator-blocks=8 --generator-filters=128 --generator-residual=0 \
+    --perceptual-layer=conv2_2 --smoothness-weight=1e7 --adversary-weight=0.0 \
+    --train-noise=1.0
+
+python3.4 enhance.py \
+    --train "$OPEN_IMAGES_PATH/*/*.jpg" --type photo --model default \
+    --epochs=500 --batch-shape=240 --device=gpu0 \
+    --generator-downscale=0 --generator-upscale=1 \
+    --perceptual-layer=conv5_2 --smoothness-weight=5e3 --adversary-weight=5e1 \
+    --generator-start=10 --discriminator-start=0 --adversarial-start=10 \
+    --discriminator-size=64 \
+    --train-noise=1.0