Cleaned up code references in README

README.md

@@ -252,15 +252,15 @@ beam pipelines provided for generating datasets and running inference on a
 larger scale. To use these scripts, it would be necessary to hook up your own
 beam backend.
 
-There is also very limited PyTorch support in the ldif/torch directory. This code
+There is also very limited PyTorch support in the `ldif/torch` directory. This code
 is a basic implementation of SIF that can't train new SIF models, but can load
 and evaluate SIFs generated by the tensorflow training+evaluation code. It is mainly
 intended for using SIF correspondences as a building block of another unrelated
-project in PyTorch. Note that PyTorch is not included in the requirements.txt, and
-the torch/ subdirectory is independent from the rest of the code base (it interacts
-only through the .txt files written by the tensorflow code and takes no dependencies
+project in PyTorch. Note that PyTorch is not included in the `requirements.txt`, and
+the `torch/` subdirectory is independent from the rest of the code base (it interacts
+only through the `.txt` files written by the tensorflow code and takes no dependencies
 on the rest of this codebase). To use it, it is probably easiest to just download
-the torch/ folder and import the sif.py file as a module.
+the `torch/` folder and import the `sif.py` file as a module.
 
 ## Updates to the code