Sync README

README.md

@@ -8,12 +8,12 @@ An open source framework for generative image inpainting task, with the support
 
 **For the code of previous version (DeepFill v1), please checkout branch [v1.0.0](https://github.com/JiahuiYu/generative_inpainting/tree/v1.0.0).**
 
-[CVPR 2018 Paper](https://arxiv.org/abs/1801.07892) | [ICCV 2019 Oral Paper](https://arxiv.org/abs/1806.03589)| [Project](http://jiahuiyu.com/deepfill) | [Demo](http://jiahuiyu.com/deepfill) | [YouTube v1](https://youtu.be/xz1ZvcdhgQ0) | [YouTube v2](https://youtu.be/uZkEi9Y2dj4) | [BibTex](#citing)
+[CVPR 2018 Paper](https://arxiv.org/abs/1801.07892) | [ICCV 2019 Oral Paper](https://arxiv.org/abs/1806.03589) | [Project](http://jiahuiyu.com/deepfill) | [Demo](http://jiahuiyu.com/deepfill) | [YouTube v1](https://youtu.be/xz1ZvcdhgQ0) | [YouTube v2](https://youtu.be/uZkEi9Y2dj4) | [BibTex](#citing)
 
-<img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case1_raw.png" width="280"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case1_input.png" width="280"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case1_output.png" width="280"/> 
-<img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case4_raw.png" width="280"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case4_input.png" width="280"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case4_output.png" width="280"/>
+<img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case1_raw.png" width="33%"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case1_input.png" width="33%"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case1_output.png" width="33%"/>
+<img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case4_raw.png" width="33%"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case4_input.png" width="33%"/> <img src="https://raw.githubusercontent.com/JiahuiYu/generative_inpainting/v2.0.0/examples/places2/case4_output.png" width="33%"/>
 
-Free-form image inpainting results by our system built on gated convolution. Each triad shows original image, free-form input and our result from left to right. The system supports free-form mask and guidance like user sketch. It helps user remove distracting objects, modify image layouts and edit faces in images.
+Free-form image inpainting results by our system built on gated convolution. Each triad shows original image, free-form input and our result from left to right.
 
 ## Run
 
@@ -22,7 +22,7 @@ Free-form image inpainting results by our system built on gated convolution. Eac
     * Install [tensorflow](https://www.tensorflow.org/install/) (tested on Release 1.3.0, 1.4.0, 1.5.0, 1.6.0, 1.7.0).
     * Install tensorflow toolkit [neuralgym](https://github.com/JiahuiYu/neuralgym) (run `pip install git+https://github.com/JiahuiYu/neuralgym`).
 1. Training:
-    * Prepare training images filelist and shuffle it ([example](https://github.com/JiahuiYu/generative_inpainting/issues/15)). 
+    * Prepare training images filelist and shuffle it ([example](https://github.com/JiahuiYu/generative_inpainting/issues/15)).
     * Modify [inpaint.yml](/inpaint.yml) to set DATA_FLIST, LOG_DIR, IMG_SHAPES and other parameters.
     * Run `python train.py`.
 2. Resume training: