Micronetmicronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
Stars: ✭ 1,232 (+885.6%)
MivisionxMIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX also delivers a highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions.
Stars: ✭ 100 (-20%)
NeanderthalFast Clojure Matrix Library
Stars: ✭ 927 (+641.6%)
PrinPointwise Rotation-Invariant Network (AAAI 2020)
Stars: ✭ 81 (-35.2%)
SimpleopenclsamplesSimple OpenCL Samples that Build with Khronos Headers and Libs
Stars: ✭ 22 (-82.4%)
Tf2An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (-9.6%)
GansegFramework for medical image segmentation using deep neural networks
Stars: ✭ 18 (-85.6%)
Pointclouddatasets3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.
Stars: ✭ 80 (-36%)
TvmOpen deep learning compiler stack for cpu, gpu and specialized accelerators
Stars: ✭ 7,494 (+5895.2%)
Pytorch FcnPyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
Stars: ✭ 1,351 (+980.8%)
PyopenclOpenCL integration for Python, plus shiny features
Stars: ✭ 790 (+532%)
QrackComprehensive, GPU accelerated framework for developing universal virtual quantum processors
Stars: ✭ 79 (-36.8%)
Tf CorianderOpenCL 1.2 implementation for Tensorflow
Stars: ✭ 775 (+520%)
JuiceThe Hacker's Machine Learning Engine
Stars: ✭ 743 (+494.4%)
SpvgentwoSpvGenTwo is a SPIR-V building and parsing library written in plain C++17 without any dependencies. No STL or other 3rd-Party library needed.
Stars: ✭ 74 (-40.8%)
Deeplabv3 PlusTensorflow 2.3.0 implementation of DeepLabV3-Plus
Stars: ✭ 32 (-74.4%)
Face swapEnd-to-end, automatic face swapping pipeline
Stars: ✭ 722 (+477.6%)
Setr PytorchRethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Stars: ✭ 96 (-23.2%)
TorchioMedical image preprocessing and augmentation toolkit for deep learning
Stars: ✭ 708 (+466.4%)
CekirdeklerMulti-device OpenCL kernel load balancer and pipeliner API for C#. Uses shared-distributed memory model to keep GPUs updated fast while using same kernel on all devices(for simplicity).
Stars: ✭ 76 (-39.2%)
LightnetLightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 698 (+458.4%)
MasktrackImplementation of MaskTrack method which is the baseline of several state-of-the-art video object segmentation methods in Pytorch
Stars: ✭ 110 (-12%)
Sota MedsegSOTA medical image segmentation methods based on various challenges
Stars: ✭ 677 (+441.6%)
ComputeA C++ GPU Computing Library for OpenCL
Stars: ✭ 1,192 (+853.6%)
Depth clustering🚕 Fast and robust clustering of point clouds generated with a Velodyne sensor.
Stars: ✭ 657 (+425.6%)
Retina FeaturesProject for segmentation of blood vessels, microaneurysm and hardexudates in fundus images.
Stars: ✭ 95 (-24%)
VexclVexCL is a C++ vector expression template library for OpenCL/CUDA/OpenMP
Stars: ✭ 626 (+400.8%)
ParenchymaAn extensible HPC framework for CUDA, OpenCL and native CPU.
Stars: ✭ 71 (-43.2%)
Vc4clOpenCL implementation running on the VideoCore IV GPU of the Raspberry Pi models
Stars: ✭ 611 (+388.8%)
BabelstreamSTREAM, for lots of devices written in many programming models
Stars: ✭ 121 (-3.2%)
Compute RuntimeIntel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver
Stars: ✭ 593 (+374.4%)
Deep SegmentationCNNs for semantic segmentation using Keras library
Stars: ✭ 69 (-44.8%)
BisenetAdd bisenetv2. My implementation of BiSeNet
Stars: ✭ 589 (+371.2%)
Neural ApiCAI NEURAL API - Pascal based neural network API optimized for AVX, AVX2 and AVX512 instruction sets plus OpenCL capable devices including AMD, Intel and NVIDIA.
Stars: ✭ 94 (-24.8%)
CilantroA lean C++ library for working with point cloud data
Stars: ✭ 577 (+361.6%)
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 (-46.4%)
ClblastTuned OpenCL BLAS
Stars: ✭ 559 (+347.2%)
Video analystA series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
Stars: ✭ 550 (+340%)
Torch Points3dPytorch framework for doing deep learning on point clouds.
Stars: ✭ 1,135 (+808%)
Silk.netThe high-speed OpenAL, OpenGL, Vulkan, and GLFW bindings library your mother warned you about.
Stars: ✭ 534 (+327.2%)
Superpoint graphLarge-scale Point Cloud Semantic Segmentation with Superpoint Graphs
Stars: ✭ 533 (+326.4%)
Autodock GpuAutoDock for GPUs and other accelerators
Stars: ✭ 65 (-48%)
CtcdecoderConnectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python.
Stars: ✭ 529 (+323.2%)
MotsfusionMOTSFusion: Track to Reconstruct and Reconstruct to Track
Stars: ✭ 118 (-5.6%)
Vicword 一个纯php分词
Stars: ✭ 516 (+312.8%)
Geniepath PytorchThis is a PyTorch implementation of the GeniePath model in <GeniePath: Graph Neural Networks with Adaptive Receptive Paths> (https://arxiv.org/abs/1802.00910)
Stars: ✭ 63 (-49.6%)
KnlmeansclAn optimized OpenCL implementation of the Non-local means de-noising algorithm
Stars: ✭ 92 (-26.4%)
Pytorch ToolbeltPyTorch extensions for fast R&D prototyping and Kaggle farming
Stars: ✭ 942 (+653.6%)
Tensorflow FcnAn Implementation of Fully Convolutional Networks in Tensorflow.
Stars: ✭ 1,116 (+792.8%)
HyperdensenetThis repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-0.8%)
OpenvehiclevisionAn opensource lib. for vehicle vision applications (written by MATLAB), lane marking detection, road segmentation
Stars: ✭ 120 (-4%)
CltuneCLTune: An automatic OpenCL & CUDA kernel tuner
Stars: ✭ 114 (-8.8%)
Vc4cCompiler for the VC4CL OpenCL implementation
Stars: ✭ 101 (-19.2%)