Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/paarthneekhara/text-to-image
Text to image synthesis using thought vectors
https://github.com/paarthneekhara/text-to-image
deep-learning generative-adversarial-network skip-thought-vectors tensorflow
Last synced: 28 days ago
JSON representation
Text to image synthesis using thought vectors
- Host: GitHub
- URL: https://github.com/paarthneekhara/text-to-image
- Owner: paarthneekhara
- License: mit
- Created: 2016-08-16T20:12:54.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-01-30T16:29:57.000Z (almost 7 years ago)
- Last Synced: 2024-10-10T14:23:22.311Z (about 1 month ago)
- Topics: deep-learning, generative-adversarial-network, skip-thought-vectors, tensorflow
- Language: Python
- Homepage:
- Size: 6.03 MB
- Stars: 2,161
- Watchers: 84
- Forks: 394
- Open Issues: 46
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Text To Image Synthesis Using Thought Vectors
[](https://gitter.im/text-to-image/Lobby?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
This is an experimental tensorflow implementation of synthesizing images from captions using [Skip Thought Vectors][1]. The images are synthesized using the GAN-CLS Algorithm from the paper [Generative Adversarial Text-to-Image Synthesis][2]. This implementation is built on top of the excellent [DCGAN in Tensorflow][3]. The following is the model architecture. The blue bars represent the Skip Thought Vectors for the captions.
Image Source : [Generative Adversarial Text-to-Image Synthesis][2] Paper
## Requirements
- Python 2.7.6
- [Tensorflow][4]
- [h5py][5]
- [Theano][6] : for skip thought vectors
- [scikit-learn][7] : for skip thought vectors
- [NLTK][8] : for skip thought vectors
## Datasets
- All the steps below for downloading the datasets and models can be performed automatically by running `python download_datasets.py`. Several gigabytes of files will be downloaded and extracted.
- The model is currently trained on the [flowers dataset][9]. Download the images from [this link][9] and save them in ```Data/flowers/jpg```. Also download the captions from [this link][10]. Extract the archive, copy the ```text_c10``` folder and paste it in ```Data/flowers```.
- Download the pretrained models and vocabulary for skip thought vectors as per the instructions given [here][13]. Save the downloaded files in ```Data/skipthoughts```.
- Make empty directories in Data, ```Data/samples```, ```Data/val_samples``` and ```Data/Models```. They will be used for sampling the generated images and saving the trained models.
## Usage
- Data Processing : Extract the skip thought vectors for the flowers data set using :
```
python data_loader.py --data_set="flowers"
```
- Training
* Basic usage `python train.py --data_set="flowers"`
* Options
- `z_dim`: Noise Dimension. Default is 100.
- `t_dim`: Text feature dimension. Default is 256.
- `batch_size`: Batch Size. Default is 64.
- `image_size`: Image dimension. Default is 64.
- `gf_dim`: Number of conv in the first layer generator. Default is 64.
- `df_dim`: Number of conv in the first layer discriminator. Default is 64.
- `gfc_dim`: Dimension of gen untis for for fully connected layer. Default is 1024.
- `caption_vector_length`: Length of the caption vector. Default is 1024.
- `data_dir`: Data Directory. Default is `Data/`.
- `learning_rate`: Learning Rate. Default is 0.0002.
- `beta1`: Momentum for adam update. Default is 0.5.
- `epochs`: Max number of epochs. Default is 600.
- `resume_model`: Resume training from a pretrained model path.
- `data_set`: Data Set to train on. Default is flowers.
- Generating Images from Captions
* Write the captions in text file, and save it as ```Data/sample_captions.txt```. Generate the skip thought vectors for these captions using:
```
python generate_thought_vectors.py --caption_file="Data/sample_captions.txt"
```
* Generate the Images for the thought vectors using:
```
python generate_images.py --model_path= --n_images=8
```
```n_images``` specifies the number of images to be generated per caption. The generated images will be saved in ```Data/val_samples/```. ```python generate_images.py --help``` for more options.
## Sample Images Generated
Following are the images generated by the generative model from the captions.
| Caption | Generated Images |
| ------------- | -----:|
| the flower shown has yellow anther red pistil and bright red petals |  |
| this flower has petals that are yellow, white and purple and has dark lines |  |
| the petals on this flower are white with a yellow center |  |
| this flower has a lot of small round pink petals. |  |
| this flower is orange in color, and has petals that are ruffled and rounded. |  |
| the flower has yellow petals and the center of it is brown |  |
## Implementation Details
- Only the uni-skip vectors from the skip thought vectors are used. I have not tried training the model with combine-skip vectors.
- The model was trained for around 200 epochs on a GPU. This took roughly 2-3 days.
- The images generated are 64 x 64 in dimension.
- While processing the batches before training, the images are flipped horizontally with a probability of 0.5.
- The train-val split is 0.75.
## Pre-trained Models
- Download the pretrained model from [here][14] and save it in ```Data/Models```. Use this path for generating the images.
## TODO
- Train the model on the MS-COCO data set, and generate more generic images.
- Try different embedding options for captions(other than skip thought vectors). Also try to train the caption embedding RNN along with the GAN-CLS model.
## References
- [Generative Adversarial Text-to-Image Synthesis][2] Paper
- [Generative Adversarial Text-to-Image Synthesis][11] Code
- [Skip Thought Vectors][1] Paper
- [Skip Thought Vectors][12] Code
- [DCGAN in Tensorflow][3]
- [DCGAN in Tensorlayer][15]
## Alternate Implementations
- [Text to Image in Torch by Scot Reed][11]
- [Text to Image in Tensorlayer by Dong Hao][16]
## License
MIT
[1]:http://arxiv.org/abs/1506.06726
[2]:http://arxiv.org/abs/1605.05396
[3]:https://github.com/carpedm20/DCGAN-tensorflow
[4]:https://github.com/tensorflow/tensorflow
[5]:http://www.h5py.org/
[6]:https://github.com/Theano/Theano
[7]:http://scikit-learn.org/stable/index.html
[8]:http://www.nltk.org/
[9]:http://www.robots.ox.ac.uk/~vgg/data/flowers/102/
[10]:https://drive.google.com/file/d/0B0ywwgffWnLLcms2WWJQRFNSWXM/view
[11]:https://github.com/reedscot/icml2016
[12]:https://github.com/ryankiros/skip-thoughts
[13]:https://github.com/ryankiros/skip-thoughts#getting-started
[14]:https://bitbucket.org/paarth_neekhara/texttomimagemodel/raw/74a4bbaeee26fe31e148a54c4f495694680e2c31/latest_model_flowers_temp.ckpt
[15]:https://github.com/zsdonghao/dcgan
[16]:https://github.com/zsdonghao/text-to-image