Deep Learning

Frameworks for Neural Networks and Deep Learning.

Newest releases

MAIF Shapash is a Python library which aims to make machine learning interpretable and understandable by everyone. It provides several types of visualization that display explicit labels that everyone can understand.

xv44586 ccf 2020 qa match competition top1

clvrai A comprehensive list of categorized reinforcement learning environments.

cvdfoundation Fashionpedia is a new dataset which consists of two parts: (1) an ontology built by fashion experts containing 27 main apparel categories, 19 apparel parts, 294 fine-grained attributes and their relationships; (2) a dataset with e

amitness Chrome extension that adds video explanations to research papers on

WangLiwen1994 Deep Relighting Network for Image Light Source Manipulation

zju3dv EasyMocap is an open-source toolbox for markerless human motion capture.

YunYang1994 🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

auto-flow UltraOpt is a simple and efficient library to minimize expensive and noisy black-box functions, it can be used in many fields, such as HyperParameter Optimization(HPO) and Automatic Machine Learning(AutoML).

jrieke 🏆 A ranked gallery of awesome streamlit apps built by the community

nums-project NumS is a Numerical computing library for Python that Scales your workload to the cloud.

openai CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly o

lucidrains Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch

XuyangBai A curated list of resources on point cloud registration inspired by awesome-computer-vision. Work-in-progress. All contributions are welcome and appreciated.

lab-ml 🧠 Minimal implementations of neural network architectures and layers in PyTorch with side-by-side notes

dfm This repository is meant as a tutorial demonstrating the infrastructure required to provide custom ops in JAX when you have an existing implementation in C++ and, optionally, CUDA.

MontaEllis This repository is an unoffical PyTorch implementation of Medical segmentation in 3D and 2D.

EleutherAI Open-AI's DALL-E for large scale training in mesh-tensorflow.

TencentYoutuResearch Code for ACM MM 2020 paper "NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination"

jbhuang0604 A curated list of awesome computer vision resources

SeanPedersen File organization made easy. HyperTag let's humans intuitively express how they think about their files using tags.

gupta-abhay Implementation of Segmentation Transformer in PyTorch, a new model to achieve SOTA in semantic segmentation while using transformer style encoders.

huybery The PyTorch implementation of paper Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing.

joelee Face and Car detector from video streams using Computer Vision with Face Recognition and Car Number Plate detection for integration with MQTT and Home Assistant

NuviLabs Effective trash detection model for AI Grand Challenge 2020 track 3 round 1.

anpatton Welcome to my repo for some commonly requested coding questions relating to NBA statistics/analysis. We're going to hopefully cover a wide range of topics of varying complexity, but nothing too crazy.

lucidrains Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch. They propose to have the main recurrent neural network interact with the input image representations only through a set of memory key / values.

infer-actively An implementation of predictive coding in Python, utilising pytorch for GPU acceleration.

toshas This repository implements the Householder transformation algorithm for calculating orthogonal matrices and Stiefel frames. The algorithm is implemented as a Python package with differentiable bindings to PyTorch

tensorwerk Stockroom is a platform to version models, data, parameters, experiment artifacts etc.

Albert-Ma PROP, Pre-training with Representative wOrds Prediction, is a new pre-training method tailored for ad-hoc retrieval.

m-bemana X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation

INK-USC Code and data for the project "Visually grounded continual learning of compositional semantics"