MinkowskiengineMinkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
Stars: ✭ 1,110 (+1068.42%)
Knn cudapytorch knn [cuda version]
Stars: ✭ 86 (-9.47%)
HiopHPC solver for nonlinear optimization problems
Stars: ✭ 75 (-21.05%)
ParenchymaAn extensible HPC framework for CUDA, OpenCL and native CPU.
Stars: ✭ 71 (-25.26%)
Realtime Semantic SegmentationImplementation of RefineNet to perform real time instance segmentation in the browser using TensorFlow.js
Stars: ✭ 79 (-16.84%)
PaddlesegEnd-to-end image segmentation kit based on PaddlePaddle.
Stars: ✭ 1,244 (+1209.47%)
Deeppipe2Deep Learning library using GPU(CUDA/cuBLAS)
Stars: ✭ 90 (-5.26%)
Raster VisionAn open source framework for deep learning on satellite and aerial imagery.
Stars: ✭ 1,248 (+1213.68%)
DeepjointfilterThe source code of ECCV16 'Deep Joint Image Filtering'.
Stars: ✭ 68 (-28.42%)
Modulated Deform Convdeformable convolution 2D 3D DeformableConvolution DeformConv Modulated Pytorch CUDA
Stars: ✭ 81 (-14.74%)
MinhashcudaWeighted MinHash implementation on CUDA (multi-gpu).
Stars: ✭ 88 (-7.37%)
Elektronn3A PyTorch-based library for working with 3D and 2D convolutional neural networks, with focus on semantic segmentation of volumetric biomedical image data
Stars: ✭ 78 (-17.89%)
AuroraMinimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.
Stars: ✭ 90 (-5.26%)
Cudart.jlJulia wrapper for CUDA runtime API
Stars: ✭ 75 (-21.05%)
Dcm NetThis 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.
Stars: ✭ 75 (-21.05%)
Geo Deep LearningDeep learning applied to georeferenced datasets
Stars: ✭ 91 (-4.21%)
Deep SegmentationCNNs for semantic segmentation using Keras library
Stars: ✭ 69 (-27.37%)
FrostnetFrostNet: Towards Quantization-Aware Network Architecture Search
Stars: ✭ 85 (-10.53%)
AlenkaGPU database engine
Stars: ✭ 1,150 (+1110.53%)
Deeplab v3 plusThis is an ongoing re-implementation of DeepLab_v3_plus on pytorch which is trained on VOC2012 and use ResNet101 for backbone.
Stars: ✭ 83 (-12.63%)
ArboretumGradient Boosting powered by GPU(NVIDIA CUDA)
Stars: ✭ 64 (-32.63%)
Unet TgsApplying UNET Model on TGS Salt Identification Challenge hosted on Kaggle
Stars: ✭ 81 (-14.74%)
ThundersvmThunderSVM: A Fast SVM Library on GPUs and CPUs
Stars: ✭ 1,282 (+1249.47%)
Nnabla Ext CudaA CUDA Extension of Neural Network Libraries
Stars: ✭ 79 (-16.84%)
MatconvnetMatConvNet: CNNs for MATLAB
Stars: ✭ 1,299 (+1267.37%)
2016 super resolutionICCV2015 Image Super-Resolution Using Deep Convolutional Networks
Stars: ✭ 78 (-17.89%)
EsnetESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
Stars: ✭ 88 (-7.37%)
Cuda Design PatternsSome CUDA design patterns and a bit of template magic for CUDA
Stars: ✭ 78 (-17.89%)
2020 Cbms Doubleu NetDoubleU-Net for Semantic Image Segmentation in TensorFlow Keras
Stars: ✭ 86 (-9.47%)
SeanetSelf-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation
Stars: ✭ 90 (-5.26%)
Python Opencv Cudacustom opencv_contrib module which exposes opencv cuda optical flow methods with python bindings
Stars: ✭ 86 (-9.47%)
TitanA high-performance CUDA-based physics simulation sandbox for soft robotics and reinforcement learning.
Stars: ✭ 73 (-23.16%)
NumerNumeric Erlang - vector and matrix operations with CUDA. Heavily inspired by Pteracuda - https://github.com/kevsmith/pteracuda
Stars: ✭ 91 (-4.21%)
Keras IcnetKeras implementation of Real-Time Semantic Segmentation on High-Resolution Images
Stars: ✭ 85 (-10.53%)
HallocA fast and highly scalable GPU dynamic memory allocator
Stars: ✭ 89 (-6.32%)
Torch samplingEfficient reservoir sampling implementation for PyTorch
Stars: ✭ 68 (-28.42%)
MprReference implementation for "Massively Parallel Rendering of Complex Closed-Form Implicit Surfaces" (SIGGRAPH 2020)
Stars: ✭ 84 (-11.58%)
Multiclass Semantic Segmentation CamvidTensorflow 2 implementation of complete pipeline for multiclass image semantic segmentation using UNet, SegNet and FCN32 architectures on Cambridge-driving Labeled Video Database (CamVid) dataset.
Stars: ✭ 67 (-29.47%)
Espnetv2 CoremlSemantic segmentation on iPhone using ESPNetv2
Stars: ✭ 66 (-30.53%)
Spacenet building detectionProject to train/test convolutional neural networks to extract buildings from SpaceNet satellite imageries.
Stars: ✭ 83 (-12.63%)
Autodock GpuAutoDock for GPUs and other accelerators
Stars: ✭ 65 (-31.58%)
Wb color augmenterWB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
Stars: ✭ 89 (-6.32%)
Cudadrv.jlA Julia wrapper for the CUDA driver API.
Stars: ✭ 64 (-32.63%)
Fbtt EmbeddingThis 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.
Stars: ✭ 92 (-3.16%)
ElasticfusionReal-time dense visual SLAM system
Stars: ✭ 1,298 (+1266.32%)