771 Open source projects that are alternatives of or similar to Region Conv

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

pytorch knn [cuda version]

HPC solver for nonlinear optimization problems

An extensible HPC framework for CUDA, OpenCL and native CPU.

Implementation of RefineNet to perform real time instance segmentation in the browser using TensorFlow.js

End-to-end image segmentation kit based on PaddlePaddle.

Tools to Design or Visualize Architecture of Neural Network

Deep Learning library using GPU(CUDA/cuBLAS)

An open source framework for deep learning on satellite and aerial imagery.

The source code of ECCV16 'Deep Joint Image Filtering'.

Tutorial on how to build your own research envirorment for Deep Learning with OpenCV, Python, Tensorfow

deformable convolution 2D 3D DeformableConvolution DeformConv Modulated Pytorch CUDA

Weighted MinHash implementation on CUDA (multi-gpu).

A PyTorch-based library for working with 3D and 2D convolutional neural networks, with focus on semantic segmentation of volumetric biomedical image data

Minimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.

Julia wrapper for CUDA runtime API

A community run, 5-day PyTorch Deep Learning Bootcamp

This work is based on our paper "DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes", which appeared at the IEEE Conference On Computer Vision And Pattern Recognition (CVPR) 2020.

Deep learning applied to georeferenced datasets

CNNs for semantic segmentation using Keras library

FrostNet: Towards Quantization-Aware Network Architecture Search

GPU database engine

Weighted Softmax Loss Layer for Caffe

This is an ongoing re-implementation of DeepLab_v3_plus on pytorch which is trained on VOC2012 and use ResNet101 for backbone.

Segmentation of ID Cards using Semantic Segmentation

Gradient Boosting powered by GPU(NVIDIA CUDA)

Applying UNET Model on TGS Salt Identification Challenge hosted on Kaggle

ThunderSVM: A Fast SVM Library on GPUs and CPUs

A CUDA Extension of Neural Network Libraries

MatConvNet: CNNs for MATLAB

ICCV2015 Image Super-Resolution Using Deep Convolutional Networks

ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation

Some CUDA design patterns and a bit of template magic for CUDA

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

PSPNet in Chainer

DoubleU-Net for Semantic Image Segmentation in TensorFlow Keras

DeepLab-ResNet rebuilt in TensorFlow

Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation

segmentation repo using pytorch

custom opencv_contrib module which exposes opencv cuda optical flow methods with python bindings

A high-performance CUDA-based physics simulation sandbox for soft robotics and reinforcement learning.

Numeric Erlang - vector and matrix operations with CUDA. Heavily inspired by Pteracuda - https://github.com/kevsmith/pteracuda

The deep semantic segmentation network for lane segmentation.

Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images

CURRENNNT codes and scripts

A fast and highly scalable GPU dynamic memory allocator

Efficient reservoir sampling implementation for PyTorch

Reference implementation for "Massively Parallel Rendering of Complex Closed-Form Implicit Surfaces" (SIGGRAPH 2020)

Tensorflow 2 implementation of complete pipeline for multiclass image semantic segmentation using UNet, SegNet and FCN32 architectures on Cambridge-driving Labeled Video Database (CamVid) dataset.

📚 A collection of papers about Referring Image Segmentation.

Semantic segmentation on iPhone using ESPNetv2

Project to train/test convolutional neural networks to extract buildings from SpaceNet satellite imageries.

AutoDock for GPUs and other accelerators

WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].

A Julia wrapper for the CUDA driver API.

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.

Real-time dense visual SLAM system

Deep learning with cats (^._.^)