X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?p=pysvrt.git;a=blobdiff_plain;f=README.md;h=a4ea4fd956284572b20fdc650a9023021687a13b;hp=cb77899c768cf5d2567e9bbc817858cc41e00db4;hb=HEAD;hpb=1a92e486e3ac15239a23e373ba38939399e93827

diff --git a/README.md b/README.md
index cb77899..a4ea4fd 100644
--- a/README.md
+++ b/README.md
@@ -1,8 +1,8 @@
 # Introduction #
 
-This is a port of the Synthetic Visual Reasoning Test problems to the
-pytorch framework, with an implementation of two convolutional
-networks to solve them.
+This is a wrapper for [`PyTorch`](http://pytorch.org) for the
+[`Synthetic Visual Reasoning Test,`](https://fleuret.org/git/svrt)
+with an implementation of two convolutional networks to solve them.
 
 # Installation and test #
 
@@ -26,24 +26,25 @@ slow as 40 on a 4GHz i7-6700K.
 ## Vignette sets ##
 
 The file [`svrtset.py`](https://fleuret.org/git-extract/pysvrt/svrtset.py) implements the classes `VignetteSet` and
-`CompressedVignetteSet` with the following constructor
+`CompressedVignetteSet` both with a constructor
 
 ```
 __init__(problem_number, nb_samples, batch_size, cuda = False, logger = None)
 ```
 
-and the following method to return one batch
+and a method
 
 ```
 (torch.FloatTensor, torch.LongTensor) get_batch(b)
 ```
 
-as a pair composed of a 4d 'input' Tensor (i.e. single channel 128x128
-images), and a 1d 'target' Tensor (i.e. Boolean labels).
+which returns a pair composed of a 4d 'input' Tensor (i.e. single
+channel 128x128 images), and a 1d 'target' Tensor (i.e. Boolean
+labels).
 
 ## Low-level functions ##
 
-The main function for genering vignettes is
+The main function for generating vignettes is
 
 ```
 torch.ByteTensor svrt.generate_vignettes(int problem_number, torch.LongTensor labels)