|Project Name||Stars||Downloads||Repos Using This||Packages Using This||Most Recent Commit||Total Releases||Latest Release||Open Issues||License||Language|
|Text To Image||1,941||5 years ago||45||mit||Python|
|Text to image synthesis using thought vectors|
|Vectorsynthesis||232||a year ago||mit||Python|
|This library allows the creation and manipulation of vector shapes using audio signals sent directly to oscilloscopes, modified Vectrex consoles, ILDA laser displays, and oscilloscope emulation software using the Pure Data programming environment. Please scroll down for more info in the README below.|
|Neural_wavetable_synthesizer||51||4 years ago||C++|
|Neural Wavetable: a playable wavetable synthesizer using neural networks|
|Angrysparrow||4||9 years ago||gpl-3.0||C++|
|My private C++ sound synthesis library.|
|Stoca||3||2 years ago||C++|
|STOCA: Stochastic Circuit Synthesis by Cube Assignment|
|Newimage From Textandimage||2||5 years ago||mit||Python|
|Speechrec||2||3 years ago||C++|
|Continuous Dictation Speech Recognition and Speech Synthesis in Win32|
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 Skip Thought Vectors for the captions.
Image Source : Generative Adversarial Text-to-Image Synthesis Paper
python download_datasets.py. Several gigabytes of files will be downloaded and extracted.
Data/flowers/jpg. Also download the captions from this link. Extract the archive, copy the
text_c10folder and paste it in
Data/Models. They will be used for sampling the generated images and saving the trained models.
python data_loader.py --data_set="flowers"
python train.py --data_set="flowers"
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
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
Data/sample_captions.txt. Generate the skip thought vectors for these captions using:
python generate_thought_vectors.py --caption_file="Data/sample_captions.txt"
python generate_images.py --model_path=<path to the trained model> --n_images=8
n_images specifies the number of images to be generated per caption. The generated images will be saved in
python generate_images.py --help for more options.
Following are the images generated by the generative model from the captions.
|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|
Data/Models. Use this path for generating the images.