We have collection of more than 1 Million open source products ranging from Enterprise product to
small libraries in all platforms. We aggregate information from all open source repositories.
Search and find the best for your needs. Check out projects section.
Collection of Keras implementations of Generative Adversarial Networks (GANs) suggested in research papers. These models are in some cases simplified versions of the ones ultimately described in the papers, but I have chosen to focus on getting the core ideas covered instead of getting every layer configuration right. Contributions and suggestions of GAN varieties to implement are very welcomed. Implementation of Auxiliary Classifier Generative Adversarial Network.
Grenade is a composable, dependently typed, practical, and fast recurrent neural network library for concise and precise specifications of complex networks in Haskell. And that's it. Because the types are so rich, there's no specific term level code required to construct this network; although it is of course possible and easy to construct and deconstruct the networks and layers explicitly oneself.
Tensorbag is a collection of tensorflow tutorial on different Deep Learning and Machine Learning algorithms. The tutorials are organised as jupyter notebooks and require tensorflow >= 1.5. There is a subset of notebooks identified with the tag [quiz] that directly ask to the reader to complete part of the code. In the same folder there is always a complementary notebook with the complete solution.
Welcome to my GitHub repo. I am a Data Scientist and I code in Python. Here you will find some Machine Learning, Deep Learning, Natural Language Processing, Artificial Intelligence and Computer Vision models I developed.
The key added value of this code is its implementation two GANS that minimize not the KL-divergence or the WGAN-GP divergence, but the First Order Wasserstein Divergence, leading to better stability and perfomance. The FID is the performance measure used to evaluate the experiments in the paper. There, a detailed description can be found in the experiment section as well as in the the appendix in section A1.
This code implements Periodic Spatial Generative Adversarial Networks (PSGANs) on top of Lasagne/Theano. The code was tested on top of Lasagne (version 0.2.dev1) and Theano (0.9.0dev2). PSGANs can generate sample textures of arbitrary size that look strikingly similar - but not exactly the same - compared to a single (or several) source image(s).