add a note for mac users

README.md

@@ -101,4 +101,12 @@ python evaluate.py with weight_file=<arg> reconstruction=<arg> device=<arg>
 * `dataset`: which dataset to evaluate on, can be either `MAPS` or `MAESTRO` or `MusicNet`.
 * `device`: the device to be trained on. Either `cpu` or `cuda:0`
 
-The transcripted midi files, accuracy reports are saved inside the `results` folder.
+The transcripted midi files, accuracy reports are saved inside the `results` folder.
+
+## Other notes
+For Mac users, you need to add the following code in helper_functions.py
+
+```python
+import matplotlib
+matplotlib.use('TkAgg')
+```