Added comment about the exclusion of problematic patches

README.md

@@ -45,6 +45,8 @@ After downloading the raw images from https://www.bigearth.net, they need to be
 
 To run the script, either the GDAL or the rasterio package should be installed. The TensorFlow package should also be installed. The script is tested with Python 2.7, TensorFlow 1.3 and Ubuntu 16.04. 
 
+**Note**: In the provided splits files, problematic tiles are already excluded, such as ones covered by snow or clouds (see the corresponding patch lists [here](http://bigearth.net/static/documents/patches_with_seasonal_snow.csv) and [here](http://bigearth.net/static/documents/patches_with_cloud_and_shadow.csv) respectively). When using custom splits, please make sure to pay attention to handling these patches.
+
 Authors
 -------
 

prep_splits.py

@@ -114,7 +114,7 @@ if __name__ == "__main__":
     parser.add_argument('-o', '--out_folder', dest = 'out_folder', 
                         help = 'folder path containing resulting TFRecord files')
     parser.add_argument('-n', '--splits', dest = 'splits', help = 
-                        'csv files each of which contain list of patch names', nargs = '+')
+                        'csv files each of which contain list of patch names, problematic patches already excluded', nargs = '+')
 
     args = parser.parse_args()