From ae72623a08f304e9a2d82a00056321be3a147972 Mon Sep 17 00:00:00 2001
From: yunjey <yunjey47@naver.com>
Date: Tue, 21 Mar 2017 20:05:51 +0900
Subject: [PATCH] Create README.md

---
 tutorials/09 - Image Captioning/README.md | 42 +++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 tutorials/09 - Image Captioning/README.md

diff --git a/tutorials/09 - Image Captioning/README.md b/tutorials/09 - Image Captioning/README.md
new file mode 100644
index 0000000..65938fb
--- /dev/null
+++ b/tutorials/09 - Image Captioning/README.md	
@@ -0,0 +1,42 @@
+## Usage 
+
+
+#### 1. Clone the repositories
+```bash
+$ git clone https://github.com/pdollar/coco.git
+$ git clone https://github.com/yunjey/pytorch-tutorial.git
+$ cd pytorch-tutorial/tutorials/09 - Image Captioning
+```
+
+#### 2. Download the dataset
+
+```bash
+$ pip install -r requirements
+$ chmod +x download.sh
+$ ./donwload.sh
+```
+
+#### 3. Preprocessing
+
+```bash
+$ python vocab.py    
+```
+
+#### 4. Train the model
+
+```bash
+$ python train.py    
+```
+
+#### 5. Generate captions
+If you want to generate captions from MSCOCO validation dataset, see [evaluate_model.ipynb](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/09%20-%20Image%20Captioning/evaluate_model.ipynb). Otherwise, if you want to generate captions from custom image file, run command as below.
+
+```bash
+$ python sample.py --image=sample_image.jpg     
+```
+
+<br>
+
+## Pretrained model 
+
+If you do not want to train the model yourself, you can use a pretrained model. I have provided the pretrained model as a zip file. You can download the file [here](https://www.dropbox.com/s/cngzozkk73imjdh/trained_model.zip?dl=0) and extract it to `model` directory.