Text To Image Synthesis Using Thought Vectors

This is an experimental tensorflow implementation of synthesizing Images from captions using Skip Thought Vectors. The images are synthesized using the GAN-CLS Algorithm from the paper Generative Adversarial Text-to-Image Synthesis. This implementation is built on top of the excellent DCGAN in Tensorflow. The following is the model architecture. The blue bars represent the text encoding using Skip Thought Vectors.

Image Source : Generative Adversarial Text-to-Image Synthesis Paper

Requirements

• Python 2.7.6
• Tensorflow
• h5py
• Theano : for skip thought vectors
• scikit-learn : for skip thought vectors
• NLTK : for skip thought vectors

Datasets

• The model is currently trained on the flowers dataset. Download the images from this link and save them in Data/flowers/jpg. Also download the captions from this link. Extract the archive, copy the text_c_10 folder and paste it in Data/flowers.
• Download the pretrained models and vocabulary for skip thought vectors as per the instructions give here. 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, while training.

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=<path to the trained model>
  

Sample Images Generated

Caption	Actual Image	Generated Images

TODO

• Train the model on MS-COCO data set. The dataset is huge and with the resource I have, it will take several days to train the model.
• Try out different caption embeddings. Also try to train the caption embedding RNN along with the model.

References

• Generative Adversarial Text-to-Image Synthesis Paper
• Generative Adversarial Text-to-Image Synthesis Code
• Skip Thought Vectors Paper
• Skip Thought Vectors Code
• DCGAN in Tensorflow