LightseqLightSeq: A High Performance Inference Library for Sequence Processing and Generation
Stars: ✭ 501 (+196.45%)
CubertFast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
Stars: ✭ 395 (+133.73%)
fastT5⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
Stars: ✭ 421 (+149.11%)
Onnxt5Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
Stars: ✭ 143 (-15.38%)
Turbotransformersa fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Stars: ✭ 826 (+388.76%)
Bmw Labeltool LiteThis repository provides you with a easy to use labeling tool for State-of-the-art Deep Learning training purposes.
Stars: ✭ 145 (-14.2%)
GhostnetCV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
Stars: ✭ 1,744 (+931.95%)
Embedding As ServiceOne-Stop Solution to encode sentence to fixed length vectors from various embedding techniques
Stars: ✭ 151 (-10.65%)
Nlp researchNLP research:基于tensorflow的nlp深度学习项目,支持文本分类/句子匹配/序列标注/文本生成 四大任务
Stars: ✭ 141 (-16.57%)
ConformerImplementation of the convolutional module from the Conformer paper, for use in Transformers
Stars: ✭ 103 (-39.05%)
MmsegmentationOpenMMLab Semantic Segmentation Toolbox and Benchmark.
Stars: ✭ 2,875 (+1601.18%)
MediapipeCross-platform, customizable ML solutions for live and streaming media.
Stars: ✭ 15,338 (+8975.74%)
CjstoesmA tool that can transform CommonJS to ESM
Stars: ✭ 109 (-35.5%)
EmlearnMachine Learning inference engine for Microcontrollers and Embedded devices
Stars: ✭ 154 (-8.88%)
Yolov5 Rt StackYet another yolov5, with its runtime stack for libtorch, onnx, tvm and specialized accelerators. You like torchvision's retinanet? You like yolov5? You love yolort!
Stars: ✭ 107 (-36.69%)
Medical TransformerPytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation"
Stars: ✭ 153 (-9.47%)
Esbuild JestA Jest transformer using esbuild
Stars: ✭ 100 (-40.83%)
Compute EngineHighly optimized inference engine for Binarized Neural Networks
Stars: ✭ 138 (-18.34%)
Bert ocr.pytorchUnofficial PyTorch implementation of 2D Attentional Irregular Scene Text Recognizer
Stars: ✭ 101 (-40.24%)
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 (-40.83%)
BigbirdTransformers for Longer Sequences
Stars: ✭ 146 (-13.61%)
Ml Model CiMLModelCI is a complete MLOps platform for managing, converting, profiling, and deploying MLaaS (Machine Learning-as-a-Service), bridging the gap between current ML training and serving systems.
Stars: ✭ 122 (-27.81%)
KglabGraph-Based Data Science: an abstraction layer in Python for building knowledge graphs, integrated with popular graph libraries – atop Pandas, RDFlib, pySHACL, RAPIDS, NetworkX, iGraph, PyVis, pslpython, pyarrow, etc.
Stars: ✭ 98 (-42.01%)
Symfony JsonapiJSON API Transformer Bundle for Symfony 2 and Symfony 3
Stars: ✭ 114 (-32.54%)
The Story Of HeadsThis is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the paper "Analyzing Source and Target Contributions to NMT Predictions".
Stars: ✭ 146 (-13.61%)
Tf2An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (-33.14%)
Bert Ner TfNamed Entity Recognition with BERT using TensorFlow 2.0
Stars: ✭ 155 (-8.28%)
Overlappredator[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
Stars: ✭ 106 (-37.28%)
Ncnnncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+7814.79%)
KissCode for the paper "KISS: Keeping it Simple for Scene Text Recognition"
Stars: ✭ 108 (-36.09%)
Hey JetsonDeep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.
Stars: ✭ 161 (-4.73%)
Transformers🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Stars: ✭ 55,742 (+32883.43%)
TupeTransformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
Stars: ✭ 143 (-15.38%)
CnstreamCNStream is a streaming framework for building Cambricon machine learning pipelines http://forum.cambricon.com https://gitee.com/SolutionSDK/CNStream
Stars: ✭ 104 (-38.46%)
ForwardA library for high performance deep learning inference on NVIDIA GPUs.
Stars: ✭ 136 (-19.53%)
DeltaDELTA is a deep learning based natural language and speech processing platform.
Stars: ✭ 1,479 (+775.15%)
ServerThe Triton Inference Server provides an optimized cloud and edge inferencing solution.
Stars: ✭ 2,994 (+1671.6%)
LightnerInference with state-of-the-art models (pre-trained by LD-Net / AutoNER / VanillaNER / ...)
Stars: ✭ 102 (-39.64%)
Json AutotypeAutomatic Haskell type inference from JSON input
Stars: ✭ 139 (-17.75%)
Etaggerreference tensorflow code for named entity tagging
Stars: ✭ 100 (-40.83%)
Embedded Ai.benchbenchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.
Stars: ✭ 131 (-22.49%)
Hrnet Semantic SegmentationThe OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
Stars: ✭ 2,369 (+1301.78%)
Njunmt TfAn open-source neural machine translation system developed by Natural Language Processing Group, Nanjing University.
Stars: ✭ 97 (-42.6%)
Setr PytorchRethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Stars: ✭ 96 (-43.2%)
Laravel Oh GeneratorsThis package extends the core file generators that are included with Laravel 5 or later.
Stars: ✭ 96 (-43.2%)
Owl RlA simple implementation of the OWL2 RL Profile on top of RDFLib: it expands the graph with all possible triples that OWL RL defines. It can be used together with RDFLib to expand an RDFLib Graph object, or as a stand alone service with its own serialization.
Stars: ✭ 95 (-43.79%)
Tre[AKBC 19] Improving Relation Extraction by Pre-trained Language Representations
Stars: ✭ 95 (-43.79%)
NnpackAcceleration package for neural networks on multi-core CPUs
Stars: ✭ 1,538 (+810.06%)
Ml privacy meterMachine Learning Privacy Meter: A tool to quantify the privacy risks of machine learning models with respect to inference attacks, notably membership inference attacks
Stars: ✭ 167 (-1.18%)