update readme

readme.md

@@ -1,14 +1,15 @@
 ## Attribute-Aware Attention Model
 Code for ACM Multimedia 2018 oral paper: Attribute-Aware Attention Model for Fine-grained Representation Learning
 
-<img src="./fig/title.png" width="50%" height="50%">
+<img src="./fig/title.png" width="70%" height="70%">
+
 
 ### Usage
 Requires: Keras 1.2.1 ("image_data_format": "channels_first")
 
 Run in two steps:
 
-1. Download CUB-200-2011 dataset [here](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) and unzip it to `$CUB`; Copy file `tools/processed_attributes.txt` in `$CUB`.
+1. Download CUB-200-2011 dataset [here](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) and unzip it to `$CUB`; Copy file `tools/processed_attributes.txt` to `$CUB`.
 
 - The `$CUB` dir should be like this:
 <img src="./fig/cub-dir.png" width="30%" height="30%">
@@ -19,8 +20,8 @@ Run in two steps:
 
 <img src="./fig/result.png" width="50%" height="50%">
 
-### Citation
 
+### Citation
 Please use the following bibtex to cite our work:
 ```
 @inproceedings{han2018attribute,

tools/readme.md

@@ -1 +1 @@
-The processed attribute labels file `processed_attributes.txt` is generated by `attributes_process.py`.
+The processed attribute labels file `processed_attributes.txt` is generated by `attributes_process.py`. Please run it under `$CUB`.