Deep Learning

Frameworks for Neural Networks and Deep Learning.

Newest releases

Python3WebSpider Deep LearningImage Captcha 2

TeaPearce ArXiv paper 'Counter-Strike Deathmatch with Large-Scale Behavioural Cloning'

PeizhuoLi An end-to-end library for automatic character rigging, skinning, and blend shapes generation, as well as a visualization tool. [SIGGRAPH 2021]

hujiecpp ISTR: End-to-End Instance Segmentation with Transformers

Duankaiwen The trained models are temporarily unavailable, but you can train the code using reasonable computational resource.

enriccorona Implementation for the paper SMPLicit: Topology-aware Generative Model for Clothed People (CVPR 2021)

michiyasunaga QA-GNN: Question Answering using Language Models and Knowledge Graphs

Mukosame Anime2Sketch: A sketch extractor for illustration, anime art, manga

geekjr QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.

AIcrowd Starter kit for getting started in the Music Demixing Challenge.

sradc SmallPebble is a minimal automatic differentiation and deep learning library written from scratch in Python, using NumPy/CuPy.

ebartrum GAN models (including 3D controllable models) implemented with Pytorch Lightning and Hydra configuration.

facebookresearch PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

yinyunie This library includes the tools for rendering multi-view color and depth images of ShapeNet models. Physically based rendering (PBR) is featured based on blender2.79.

zinuok This is the dataset for testing the robustness of various VO/VIO methods

zfchenUnique This repo contains the pytorch implementation for Dynamic Concept Learner (accepted by ICLR 2021).

Colin97 DeepMetaHandles is a shape deformation technique. It learns a set of meta-handles for each given shape. The disentangled meta-handles factorize all the plausible deformations of the shape, while each of them corresponds to an intu

locuslab DC3: A Learning Method for Optimization with Hard Constraints

Meituan-AutoML Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks

junzhezhang [CVPR 2021] Unsupervised 3D Shape Completion through GAN Inversion

Jia-Research-Lab This project provides the implementation for the CVPR 2021 paper "Scale-aware Automatic Augmentation for Object Detection". Scale-aware AutoAug provides a new search space and search metric to find effective data agumentation poli

Xingyu-Lin A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

Alan-D-Chen CDIoU and CDIoU loss is like a convenient plug-in that can be used in multiple models. CDIoU and CDIoU loss have different excellent performances in several models such as Faster R-CNN, YOLOv4, RetinaNet and . There is a maximum A

Luisrosario2604 Prototype of automated store (Machine Learning + Color and Shape detection)

saif2020 It was an Unbelievable WeekEnd For me as I won Challenges#3 in UmojaHack Africa 2021 with my amazing Teammate @ASSAZZIN. this repository contains Code Solutions on how to get Top1 Place in Financial Resilience Challenge . Enjoy !

google SeqIO is a library for processing sequential data to be fed into downstream sequence models. It uses to create scalable data pipelines but requires minimal use of TensorFlow. In particular, with one line of code, t

deepmind Mixed precision training [0] is a technique that mixes the use of full and half precision floating point numbers during training to reduce the memory bandwidth requirements and improve the computational efficiency of a given model

Ximilar-com Minimalistic open-source library for metric learning written in TensorFlow2, TF-Addons, Numpy, OpenCV(CV2) and Annoy. This repository contains a TensorFlow2+/tf.keras implementation some of the loss functions and miners. This repo

mindee Document Text Recognition (DocTR) made seamless, high-performing & accessible to anyone using Deep Learning for OCR-related tasks.

torchsynth A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.

tzxiang A curated list of awesome resources for semantic understanding of aerial scene, e.g. tutorials, papers, books, datasets, libraries and software.

nttcslab BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

hila-chefer Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.