403 Open source projects that are alternatives of or similar to Weighted_softmax_loss

CME 213 Class Material

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification (ICCV 2019) - Official PyTorch Implementation

Gradient Boosting powered by GPU(NVIDIA CUDA)

OptiX Path Tracer

Deep Object Co-Segmentation

Efficient reservoir sampling implementation for PyTorch

torch data augmentation toolbox (supports affine transform)

ICCV2015 Image Super-Resolution Using Deep Convolutional Networks

Hornet data structure for sparse dynamic graphs and matrices

CUDA Templates for Linear Algebra Subroutines

Simulating on GPU using Material Point Method and rendering.

Large octree map construction and rendering with CUDA and OpenGL

CURRENNNT codes and scripts

K-Nearest Neighbor in Pytorch

deformable convolution 2D 3D DeformableConvolution DeformConv Modulated Pytorch CUDA

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

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

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

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

An GPU/CUDA implementation of the Hungarian algorithm

GPU-Suite

Superpixel SLIC for GPU (CUDA)

HPC solver for nonlinear optimization problems

Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.

GPU Accelerated t-SNE for CUDA with Python bindings

CUDA integration for Python, plus shiny features

N body gravity attraction problem solver

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

PyTorch bindinga for Baidu's Warp-CTC

PyTorch 1.0 implementation of the approximate Earth Mover's Distance

Flattened convolutional neural networks (1D convolution modules for Torch nn)

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

Collection of Docker images for ML/DL and video processing projects

A community run, 5-day PyTorch Deep Learning Bootcamp

Concurrent CPU-GPU Programming using Task Models

GPU database engine

NVBIO is a library of reusable components designed to accelerate bioinformatics applications using CUDA.

A CUDA Extension of Neural Network Libraries

点云深度学习框架 | Point cloud Deep learning Framework

AutoDock for GPUs and other accelerators

deformable_conv2d layer implemented in pytorch

ThunderSVM: A Fast SVM Library on GPUs and CPUs

CARLsim is an efficient, easy-to-use, GPU-accelerated software framework for simulating large-scale spiking neural network (SNN) models with a high degree of biological detail.

A Julia wrapper for the CUDA driver API.

Introduction to Parallel Programming class code

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

Tutorial for using Singularity containers

@ICCV2017: For exploiting second-order statistics, we propose Matrix Power Normalized Covariance pooling (MPN-COV) ConvNets, different from and outperforming those using global average pooling.

pytorch knn [cuda version]

Torch7 bindings for cuda-convnet2 kernels!

GGNN: State of the Art Graph-based GPU Nearest Neighbor Search

How fast can we brute force a 64-bit comparison?

Julia wrapper for CUDA runtime API

Application of machine learning to the Coinbase (GDAX) orderbook

Deep learning with cats (^._.^)

Weighted MinHash implementation on CUDA (multi-gpu).

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

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

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