491 Open source projects that are alternatives of or similar to Pedestrian_alignment

MTCNN Face Detection & Alignment

Fast Neural Machine Translation in C++ - development repository

Dragon: A Computation Graph Virtual Machine Based Deep Learning Framework.

Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

Single C file, Realtime CPU/GPU Profiler with Remote Web Viewer

LLVM backend for Accelerate

A C++ Compute/Graphics Library and Toolchain enabling same-source CUDA/Host/Metal/OpenCL/Vulkan C++ programming and execution.

The C++ Standard Library for your entire system.

A simple GPU hash table implemented in CUDA using lock free techniques

Execution primitives for C++

Sparse Optimisation Research Code

py-faster-rcnn that can compile on windows directly

Calculate Root-mean-square deviation (RMSD) of two molecules, using rotation, in xyz or pdb format

kaldi-asr/kaldi is the official location of the Kaldi project.

JCuda - Java bindings for CUDA

Fully Convolutional Instance-aware Semantic Segmentation

Self-hosted NVR with object detection

oneAPI Math Kernel Library (oneMKL) Interfaces

Examples demonstrating available options to program multiple GPUs in a single node or a cluster

Fast K-Nearest Neighbor search with GPU

SmartSystemMenu extends system menu of all windows in the system

Stream Processing with OCaml

a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)

CLTune: An automatic OpenCL & CUDA kernel tuner

Collective Knowledge workflow for Caffe to automate installation across diverse platforms and to collaboratively evaluate and optimize Caffe-based workloads across diverse hardware, software and data sets (compilers, libraries, tools, models, inputs):

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

Clojure library for CUDA development

a reimplementation of UnFlow in PyTorch that matches the official TensorFlow version

Image-processing software for cryo-electron microscopy

Official source code for our paper "AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation" (CVPR 2020)

A structured light scanner

CUDA Homomorphic Encryption Library

Set up CUDA for machine learning (and gaming) on macOS using a NVIDIA eGPU

SortMeRNA: next-generation sequence filtering and alignment tool

CUDA Matrix Factorization Library with Alternating Least Square (ALS)

World's fastest and most advanced password recovery utility

HIP: C++ Heterogeneous-Compute Interface for Portability

Chamfer Distance in Pytorch with f-score

Domain-invariant Stereo Matching Networks

A curated list of awesome resources for image alignment and stitching ...

Examples of C# code compiled to GPU by hybridizer

Deep.Net machine learning framework for F#

Helmut Hoffer von Ankershoffen experimenting with arm64 based NVIDIA Jetson (Nano and AGX Xavier) edge devices running Kubernetes (K8s) for machine learning (ML) including Jupyter Notebooks, TensorFlow Training and TensorFlow Serving using CUDA for smart IoT.

Extending JAX with custom C++ and CUDA code

TIGRE: Tomographic Iterative GPU-based Reconstruction Toolbox

A Python wrapper of NVIDIA Video Loader (NVVL) with CuPy for fast video loading with Python

Numerical linear algebra software package

This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.

cuML - RAPIDS Machine Learning Library

Ubuntu 18.04 How to install Nvidia driver + CUDA + CUDNN + build tensorflow for gpu step by step command line

A dataset of 15 million CAD sketches with geometric constraint graphs.

MatConvNet: CNNs for MATLAB

☁️ Volumetric path tracer using cuda

an implementation of softmax splatting for differentiable forward warping using PyTorch

Super simple & easy Windows 10 cryptocurrency miner made by NiceHash.

Flexbox & CSS-style Layout in Swift.

OneFlow is a performance-centered and open-source deep learning framework.

Burstcoin C++ CPU and GPU Miner

Molecular dynamics and Monte Carlo soft matter simulation on GPUs.