Stars
StyleGAN - Official TensorFlow Implementation
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Super Resolution for images using deep learning.
An open access book on scientific visualization using python and matplotlib
An open source multi-tool for exploring and publishing data
eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee
Keras implementations of Generative Adversarial Networks.
A system for quickly generating training data with weak supervision
StarGAN - Official PyTorch Implementation (CVPR 2018)
🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
A deep neural net toolkit for emotion analysis via Facial Expression Recognition (FER)
Generate your own cartoon-style images with CartoonGAN (CVPR 2018), powered by TensorFlow 2.0 Alpha.
NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)
pySMT: A library for SMT formulae manipulation and solving
Our implementation of "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" (Egor Zakharov et al.)
Naszilla is a Python library for neural architecture search (NAS)
NPI(Neural Programmer-Interpreters) implementation with Keras
Conditional implementation for NVIDIA's StyleGAN architecture
pytorch implementation of "Mask-Guided Portrait Editing with Conditional GANs"
Optimizing control variates for black-box gradient estimation
💫 PyScaffold extension for data-science projects
Revealing example of self-attention, the building block of transformer AI models
Python package supporting heavy functional programming through currying. Translation of the Ramda library from javascript to python.
Pytorch implementation of GANimation with pretrained weights.
Blazing fast symbolic regresison