From 1f2e32b4216af1cd6ca7438ead81ff9d8392bc11 Mon Sep 17 00:00:00 2001
From: Scott Sievert <sieve121@umn.edu>
Date: Sun, 17 Apr 2016 10:59:43 -0500
Subject: [PATCH] provides monospace formatting for code/filenames

---
 README.md | 44 ++++++++++++++++++++++++++++----------------
 1 file changed, 28 insertions(+), 16 deletions(-)

diff --git a/README.md b/README.md
index 46aee4a..f85d89a 100644
--- a/README.md
+++ b/README.md
@@ -34,21 +34,23 @@ And this package is needed to create and manipulate netcdf data files with pytho
 
 To build RNNLIB do
 
+``` shell
 $ cmake -DCMAKE_BUILD_TYPE=Release .
 $ cmake --build .
+```
 
-Cmake run creates the binary files 'rnnlib', 'rnnsynth' and 'gradient_check' in the current directory. 
+Cmake run creates the binary files `rnnlib`, `rnnsynth` and `gradient_check` in the current directory. 
 
 It is recommended that you add the directory containing the 'rnnlib' binary to your path,
-as otherwise the tools in the 'utilities' directory will not work.
+as otherwise the tools in the `utilities` directory will not work.
 
-Project files for the integrated development environments can be generated by cmake. Run cmake --help
+Project files for the integrated development environments can be generated by cmake. Run `cmake --help`
 to get list of supported IDEs.
 
  
 # Handwriting synthesis
 
-Step in to examples/online_prediction and go through few steps below to prepare the 
+Step in to `examples/online_prediction` and go through few steps below to prepare the 
 training data, train the model and eventually plot the results of the synthesis
 
 ## Downloading online handwriting dataset
@@ -57,26 +59,28 @@ Start by registering and downloading pen strokes data from
 http://www.iam.unibe.ch/~fkiwww/iamondb/data/lineStrokes-all.tar.gz
 Text lables for strokes can be found here
 http://www.iam.unibe.ch/~fkiwww/iamondb/data/ascii-all.tar.gz
-Then unzip ./lineStrokes and ./ascii under examples/online_prediction.
+Then unzip `./lineStroke`s and `./ascii under examples/online_prediction`.
 Data format in the downloaded files can not be used as is 
 and requires further preprocessing to convert pen coordinates to offsets from
 previous point and merge them into the single file of netcdf format.
 
 ## Preparing the training data
 
-Run ./build_netcdf.sh to split dataset to training and validation sets. 
+Run `./build_netcdf.sh` to split dataset to training and validation sets. 
 The same script does all necessary preprocessing including normalisation
-of the input and makes corresponding online.nc and online_validation.nc 
+of the input and makes corresponding `online.nc` and `online_validation.nc` 
 files for use with rnnlib .
 
-Each point in the input sequences from online.nc consists of three numbers: 
+Each point in the input sequences from `online.nc` consists of three numbers: 
 the x and y offset from the previous point, and the binary end-of-stroke feature.
 
 ## Gradient check
 
 To gain some confidence that the build is fine run the gradient check:
 
+``` shell
 gradient_check --autosave=false check_synth2.config
+```
 
 ## Training
 
@@ -87,7 +91,9 @@ too slow convergence rate.
 
 ### Step 1
 
+``` shell
 rnnlib --verbose=false  synth1d.config
+```
 
 Where synth1d.config is 1st step configuration file that defines network topology:
 3 LSTM hidden layers of 400 cells, 20 gaussian mixtures as output layer, 10 mixtures
@@ -96,7 +102,7 @@ Somewhere between training epoch 10-15 it will find optimal solution and will do
 "early stopping" w/o improvement for 20 epoch. "Early" here takes 3 days on Intel
 Sandybridge CPU. Normally training can be stopped as long as loss starts rising up
 for 2-3 consequent epochs.
-The best solution found is stored in synth1d@<time step>.best_loss.save file
+The best solution found is stored in `synth1d@<time step>.best_loss.save` file
 
 ### Step 2
 
@@ -106,14 +112,18 @@ training unlike in Step 1. Therefore one must be more patient to declare early s
 wait for 20 epochs with loss worse then the best result so far. Rnnlib has implementation
 of MDL regulariser which is used in this step. The command line is as following:
 
+``` shell
 rnnlib --mdl=true --mdlOptimiser=rmsprop from_step1.best_loss.save
+```
 
 ### Synthesis
 
 Handwriting synthesis is done by rnnsynth binary using network parameters obtained by
 step 2:
 
+``` shell
 rnnsynth from_step2.best_loss.save
+```
 
 The character sequence is given to stdin and output is written to stdout. The output sequence
 is the same as input where each data point has x,y offsets and end-of-stroke flag.
@@ -121,21 +131,23 @@ is the same as input where each data point has x,y offsets and end-of-stroke fla
 ### Plotting the results
 
 Rnnsynth output is the sequence of x,y offsets and end-of-stroke flags. To visualise it one
-can use show_pen.m Octave script:
+can use `show_pen.m` Octave script:
 
+``` shell
 octave:>show_pen('/tmp/trace1')
+```
 
-Where /tmp/trace1 contains stdout from rnnsynth.
+Where `/tmp/trace1` contains stdout from rnnsynth.
 
 ### Rnnlib configuration file
 
 Configuration options are exlained in http://sourceforge.net/p/rnnl/wiki/Home/. Since then
 there are few things added:
-* lstm1d as hiddenType layer type - optimised LSTM layer when input dimension is 1d
-* rmsprop optimizer type
-* mixtures=N where N is number of gaussians in the output layer
-* charWindowSize=N where N is the number of gaussians in the character window layer
-* skipConnections=true|false - whether to add skip connections; default is true
+* `lstm1d` as hiddenType layer type - optimised LSTM layer when input dimension is 1d
+* `rmsprop` optimizer type
+* `mixtures`=N where N is number of gaussians in the output layer
+* `charWindowSize`=N where N is the number of gaussians in the character window layer
+* `skipConnections` =true|false - whether to add skip connections; default is true
 
 # Contact