From fbe094a46a0012f2b764ee39c34054a0beaa8ca5 Mon Sep 17 00:00:00 2001 From: Akash kumar singh Date: Wed, 5 Sep 2018 22:15:15 +0530 Subject: [PATCH] Update README.md --- README.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 65e11bb..c56b019 100644 --- a/README.md +++ b/README.md @@ -1,15 +1,15 @@ -###Generative Adversarial Text-to-Image Synthesis +### Generative Adversarial Text-to-Image Synthesis Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, Honglak Lee This is the code for our ICML 2016 paper on text-to-image synthesis using conditional GANs. You can use it to train and sample from text-to-image models. The code is adapted from the excellent [dcgan.torch](https://github.com/soumith/dcgan.torch). -####Setup Instructions +#### Setup Instructions You will need to install [Torch](http://torch.ch/docs/getting-started.html), CuDNN, and the [display](https://github.com/szym/display) package. -####How to train a text to image model: +#### How to train a text to image model: 1. Download the [birds](https://drive.google.com/file/d/0B0ywwgffWnLLLUc2WHYzM0Q2eWc/view?usp=sharing) and [flowers](https://drive.google.com/file/d/0B0ywwgffWnLLMl9uOU91MV80cVU/view?usp=sharing) and [COCO](https://drive.google.com/open?id=0B0ywwgffWnLLamltREhDRjlaT3M) caption data in Torch format. 2. Download the [birds](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) and [flowers](http://www.robots.ox.ac.uk/~vgg/data/flowers/102) and [COCO](http://mscoco.org/dataset/#download) image data. @@ -17,7 +17,7 @@ You will need to install [Torch](http://torch.ch/docs/getting-started.html), CuD 4. Modify the `CONFIG` file to point to your data and text encoder paths. 5. Run one of the training scripts, e.g. `./scripts/train_cub.sh` -####How to generate samples: +#### How to generate samples: * For flowers: `./scripts/demo_flowers.sh`. Add text descriptions to `scripts/flowers_queries.txt`. * For birds: `./scripts/demo_cub.sh`. @@ -28,19 +28,19 @@ You will need to install [Torch](http://torch.ch/docs/getting-started.html), CuD -####Pretrained models: +#### Pretrained models: * [CUB GAN-INT-CLS](https://drive.google.com/open?id=0B0ywwgffWnLLSW84ZXRjdXhObzQ) * [Flowers GAN-INT-CLS](https://drive.google.com/open?id=0B0ywwgffWnLLV0U4MGwzZ2JKT3c) * [COCO GAN-CLS](https://drive.google.com/open?id=0B0ywwgffWnLLT0JqcEFrOG1iVVk) -####How to train a text encoder from scratch: +#### How to train a text encoder from scratch: * You may want to do this if you have your own new dataset of text descriptions. * For flowers and birds: follow the instructions [here](https://github.com/reedscot/cvpr2016). * For MS-COCO: `./scripts/train_coco_txt.sh`. -####Citation +#### Citation If you find this useful, please cite our work as follows: