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

The purpose of this tutorial is to learn how to install and prepare TensorFlow framework to train your own convolutional neural network object detection classifier for multiple objects, starting from scratch

Chamfer Distance in Pytorch with f-score

A GPU benchmark tool for evaluating GPUs on mixed operational intensity kernels (CUDA, OpenCL, HIP, SYCL)

Stream Processing with OCaml

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade

CUDA Homomorphic Encryption Library

Molecular dynamics and Monte Carlo soft matter simulation on GPUs.

Detail-Preserving Pooling in Deep Networks (CVPR 2018)

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

Fast K-Nearest Neighbor search with GPU

Real-time dense visual SLAM system

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

CLTune: An automatic OpenCL & CUDA kernel tuner

Python library for Room Impulse Response (RIR) simulation with GPU acceleration

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

No description or website provided.

World's fastest and most advanced password recovery utility

CNN accelerated by cuda. Test on mnist and finilly get 99.76%

PyGraphistry is a Python library to quickly load, shape, embed, and explore big graphs with the GPU-accelerated Graphistry visual graph analyzer

SUPRA: Software Defined Ultrasound Processing for Real-Time Applications - An Open Source 2D and 3D Pipeline from Beamforming to B-Mode

A library for high performance deep learning inference on NVIDIA GPUs.

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

Fully Convolutional Instance-aware Semantic Segmentation

STREAM, for lots of devices written in many programming models

MatConvNet: CNNs for MATLAB

Fast Neural Machine Translation in C++ - development repository

TensorFlow wheels built for latest CUDA/CuDNN and enabled performance flags: SSE, AVX, FMA; XLA

☁️ Volumetric path tracer using cuda

A C++ Cuda Tensor Lazy Computing Library

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

Extension package for spatial propagation network in pytorch.

Numerical linear algebra software package

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

LLVM backend for Accelerate

💥💻💥 A data-parallel functional programming language

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

The C++ Standard Library for your entire system.

DaCe - Data Centric Parallel Programming

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.

Fast CUDA Kernels for ResNet Inference.

Execution primitives for C++

Deep.Net machine learning framework for F#

[ARCHIVED] C GPU DataFrame Library

Extending JAX with custom C++ and CUDA code

py-faster-rcnn that can compile on windows directly

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

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

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.

C++ Code to run waveglow inference in cuda

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

Fast inference engine for OpenNMT models

CUDA-Warp RNN-Transducer

A binary library for very fast face detection using compact CNNs.

A real time optical flow algorithm implemented on GPU

Agenium Scale vectorization library for CPUs and GPUs

oneAPI Math Kernel Library (oneMKL) Interfaces