From 55e8c3f74f28cfe8af194bd5cc60e74bcb5a0ad0 Mon Sep 17 00:00:00 2001
From: Merrin Macleod <merrin.macleod@gmail.com>
Date: Tue, 28 Feb 2017 17:10:08 +1300
Subject: [PATCH] include instructions for exporting model

---
 README.md | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 32a53e7..8cf9eb7 100644
--- a/README.md
+++ b/README.md
@@ -137,7 +137,7 @@ python tools/process.py \
   --output_dir photos/resized
 ```
 
-No other processing is required, the colorzation mode (see Training section below) uses single images instead of image pairs.
+No other processing is required, the colorization mode (see Training section below) uses single images instead of image pairs.
 
 ## Training
 
@@ -168,6 +168,17 @@ python pix2pix.py \
 
 In this mode, image A is the black and white image (lightness only), and image B contains the color channels of that image (no lightness information).
 
+### Exporting the model
+
+You can export the model to be served or uploaded:
+
+```sh
+python pix2pix.py \
+  --mode export \
+  --output_dir facades_export \
+  --checkpoint facades_train
+```
+
 ### Tips
 
 You can look at the loss and computation graph using tensorboard:
-- 
GitLab