793 Open source projects that are alternatives of or similar to Digits

Train a state-of-the-art yolov3 object detector from scratch!

Implementation for <Large-Margin Softmax Loss for Convolutional Neural Networks> in ICML'16.

Cross-platform GPU-oriented C++ application/game framework

Optimized (for size and speed) Caffe lib for iOS and Android with out-of-the-box demo APP.

Deep Learning Visualization Toolkit（『飞桨』深度学习可视化工具 ）

Next-generation HTML renderer for apps and games

Thin C++-flavored wrappers for the CUDA Runtime API

GPGPU Javascript library 🐸

This repository contains information about Cloud GPU offerings for Machine Learning practitioners.

phi: gpu accelerated code-editor; definitely not to be confused phonetically with vi.

NormFace: L2 HyperSphere Embedding for Face Verification, 99.21% on LFW

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

OctNet: Learning Deep 3D Representations at High Resolutions

Grokking Deep Reinforcement Learning

RealSR super resolution implemented with ncnn library

Implementation of "Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning"

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

List of Deep Learning Cloud Providers

ImageNet pre-trained models with batch normalization for the Caffe framework

An open-source, low-code machine learning library in Python

This repo is implemented based on detectron2 and centernet

iOS 弹幕库 OCBarrage, 同时渲染5000条弹幕也不卡, 轻量, 可拓展, 高度自定义动画, 超高性能, 简单易上手; A barrage render-engine with high performance for iOS. At the same time, rendering 5000 barrages is also very smooth, lightweight, scalable, highly custom animation, ultra high performance, simple and easy to use!

全平台实时人脸检测和姿态估计，提供无需任何框架实现Realtime Face Detection and Head pose estimation on Windows、Ubuntu、Mac、Android and iOS

Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.

增值税发票OCR识别，使用flask微服务架构，识别type：增值税电子普通发票，增值税普通发票，增值税专用发票；识别字段为：发票代码、发票号码、开票日期、校验码、税后金额等

The RWTH extensible training framework for universal recurrent neural networks

Tensorflow Implementation of Yahoo's Open NSFW Model

gprMax is open source software that simulates electromagnetic wave propagation using the Finite-Difference Time-Domain (FDTD) method for numerical modelling of Ground Penetrating Radar (GPR)

DeepNude with DreamNet improvements.

Temporal Segments LSTM and Temporal-Inception for Activity Recognition

A simple realtime graphics playground for experimentations.

A curated list of awesome Distributed Deep Learning resources.

『ゼロから作る Deep Learning ❸』(O'Reilly Japan, 2020)

An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.

High-performance Bayesian Data Analysis on the GPU in Clojure

This is a repository for an object detection inference API using the Tensorflow framework.

This library apply video filter on generate an Mp4 and on ExoPlayer video and Video Recording with Camera2.

A Caffe-based implementation of very deep convolution network for image super-resolution

Faster neural doodle

Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original Caffe architecture which users deploy their applications seamlessly.

Implementation of SYCL for CPUs, AMD GPUs, NVIDIA GPUs

How to: Run Rust code on your NVIDIA GPU

Generate human faces with neural networks

Vulkan compute for people

Climate Machine: an Earth System Model that automatically learns from data

load caffe prototxt and weights directly in pytorch

深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)

ILGPU JIT Compiler for high-performance .Net GPU programs

MBPMid2010_GPUFix is an utility program that allows to fix MacBook Pro (15-inch, Mid 2010) intermittent black screen or loss of video. The algorithm is based on a solution provided by user fabioroberto on MacRumors forums.

A PyTorch Implementation of "Watch Your Step: Learning Node Embeddings via Graph Attention" (NeurIPS 2018).

🧠 A tool that makes AI easier.

No dependency caffe replacement

PopSift is an implementation of the SIFT algorithm in CUDA.

CUDA programming in Julia.

Machine Learning Platform for Kubernetes (MLOps tools for experimentation and automation)

An Open Source, Self-Hosted Platform For Applied Deep Learning Development

Convert Caffe models to PyTorch

Neural Network Tools: Converter and Analyzer. For caffe, pytorch, draknet and so on.

C++ project to implement MTCNN, a perfect face detect algorithm, on different DL frameworks. The most popular frameworks: caffe/mxnet/tensorflow, are all suppported now

An android caffe demo app exploiting caffe pre-trained ImageNet model for image classification