Update README

Author: Smellly

README.md

@@ -70,13 +70,13 @@ P.S. Please clone the repository with the `--recursive` flag:
 ### CUB-200-2011 with Descriptions
 #### Feature Extraction
 1. Run the script `./download_cub.sh` to download the images in CUB-200-2011.
-2. Please modify the input/output path in `data-prepro/MSCOCO_preprocess/extract_resnet_coco.py` to extract and pack features in CUB-200-2011.
+2. Please modify the input/output path in `data-prepro/MSCOCO_preprocess/extract_resnet_cub.py` to extract and pack features in CUB-200-2011.
 
 #### Captions Tokenization
 1. Download the [description data](https://drive.google.com/open?id=0B0ywwgffWnLLZW9uVHNjb2JmNlE).
 2. Run `python get_split.py` to generate dataset split following the ECCV16 paper "Generating Visual Explanations".
 3. Run `python prepro_cub_annotation.py` to generate annotation json file for testing. 
-4. Run `python CUB_preprocess_token.py` for tokenization.
+4. Run `python CUB_preprocess_token.py [train/val/test]` for tokenization.
 
 
 ## Models from the paper