From 4098e346def27648f69258d1175070c38a5e987d Mon Sep 17 00:00:00 2001 From: yunjey Date: Thu, 13 Apr 2017 20:12:18 +0900 Subject: [PATCH] Update README.md --- tutorials/09 - Image Captioning/README.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tutorials/09 - Image Captioning/README.md b/tutorials/09 - Image Captioning/README.md index e35fc14..4d2b00d 100644 --- a/tutorials/09 - Image Captioning/README.md +++ b/tutorials/09 - Image Captioning/README.md @@ -4,6 +4,9 @@ #### 1. Clone the repositories ```bash $ git clone https://github.com/pdollar/coco.git +$ cd coco/PythonAPI/ +$ make +$ cd ../../ $ git clone https://github.com/yunjey/pytorch-tutorial.git $ cd pytorch-tutorial/tutorials/09 - Image Captioning ``` @@ -19,7 +22,8 @@ $ ./donwload.sh #### 3. Preprocessing ```bash -$ python vocab.py +$ python build_vocab.py +$ python resize.py ``` #### 4. Train the model @@ -32,11 +36,11 @@ $ python train.py ```bash -$ python sample.py --image=sample_image.jpg +$ python sample.py --image='path_for_image' ```
## 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. +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/btubjo73dc953zo/trained_model.egg?dl=0) and extract it to `./models/` directory.