optimum🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools
Stars: ✭ 567 (+34.68%)
Onnxt5Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
Stars: ✭ 143 (-66.03%)
onnxruntime-rsRust wrapper for Microsoft's ONNX Runtime (version 1.8)
Stars: ✭ 149 (-64.61%)
Tf2An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (-73.16%)
deformer[ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering
Stars: ✭ 111 (-73.63%)
YOLOv5-Lite🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
Stars: ✭ 1,230 (+192.16%)
deepvacPyTorch Project Specification.
Stars: ✭ 507 (+20.43%)
Pinto model zooA repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
Stars: ✭ 634 (+50.59%)
KitanaQAKitanaQA: Adversarial training and data augmentation for neural question-answering models
Stars: ✭ 58 (-86.22%)
t5-japaneseCodes to pre-train Japanese T5 models
Stars: ✭ 39 (-90.74%)
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 (+192.64%)
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 (-74.58%)
serving-runtimeExposes a serialized machine learning model through a HTTP API.
Stars: ✭ 15 (-96.44%)
ai-servingServing AI/ML models in the open standard formats PMML and ONNX with both HTTP (REST API) and gRPC endpoints
Stars: ✭ 122 (-71.02%)
DistillerNeural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Stars: ✭ 3,760 (+793.11%)
LightseqLightSeq: A High Performance Inference Library for Sequence Processing and Generation
Stars: ✭ 501 (+19%)
Multi Model ServerMulti Model Server is a tool for serving neural net models for inference
Stars: ✭ 770 (+82.9%)
Rust BertRust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
Stars: ✭ 510 (+21.14%)
mediapipe plusThe purpose of this project is to apply mediapipe to more AI chips.
Stars: ✭ 38 (-90.97%)
CubertFast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
Stars: ✭ 395 (-6.18%)
Awesome EmdlEmbedded and mobile deep learning research resources
Stars: ✭ 554 (+31.59%)
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 (-71.02%)
Ncnnncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+3077.2%)
graphsignalGraphsignal Python agent
Stars: ✭ 158 (-62.47%)
ppqPPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Stars: ✭ 281 (-33.25%)
sparsifyEasy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint
Stars: ✭ 138 (-67.22%)
text2keywordsTrained T5 and T5-large model for creating keywords from text
Stars: ✭ 53 (-87.41%)
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 (-76.25%)
image-classificationA collection of SOTA Image Classification Models in PyTorch
Stars: ✭ 70 (-83.37%)
Volksdepvolksdep is an open-source toolbox for deploying and accelerating PyTorch, ONNX and TensorFlow models with TensorRT.
Stars: ✭ 195 (-53.68%)
ONNX-Mobile-Human-Pose-3DPython scripts for performing 3D human pose estimation using the Mobile Human Pose model in ONNX.
Stars: ✭ 69 (-83.61%)
vs-mlrtEfficient ML Filter Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2, and Real-CUGAN)
Stars: ✭ 34 (-91.92%)
verseagilityRamp up your custom natural language processing (NLP) task, allowing you to bring your own data, use your preferred frameworks and bring models into production.
Stars: ✭ 23 (-94.54%)
Turbotransformersa fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Stars: ✭ 826 (+96.2%)
LibonnxA lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.
Stars: ✭ 217 (-48.46%)
unsupervised-qaTemplate-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering
Stars: ✭ 47 (-88.84%)
SegSwap(CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
Stars: ✭ 46 (-89.07%)
rankqaThis is the PyTorch implementation of the ACL 2019 paper RankQA: Neural Question Answering with Answer Re-Ranking.
Stars: ✭ 83 (-80.29%)
MASTER-pytorchCode for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)
Stars: ✭ 263 (-37.53%)
websocketWebSocket for fasthttp
Stars: ✭ 51 (-87.89%)
BMTSource code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
Stars: ✭ 192 (-54.39%)
ZAQ-codeCVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)
Stars: ✭ 59 (-85.99%)
sb-nmtCode for Synchronous Bidirectional Neural Machine Translation (SB-NMT)
Stars: ✭ 66 (-84.32%)
MashaRoBotMashaRoBot : 📑Editor's choice
Stars: ✭ 39 (-90.74%)
hcrn-videoqaImplementation for the paper "Hierarchical Conditional Relation Networks for Video Question Answering" (Le et al., CVPR 2020, Oral)
Stars: ✭ 111 (-73.63%)
examineeLaravel Quiz and Exam System clone of udemy
Stars: ✭ 151 (-64.13%)
Transformers-RLAn easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"
Stars: ✭ 107 (-74.58%)
object-flaw-detector-cppDetect various irregularities of a product as it moves along a conveyor belt.
Stars: ✭ 19 (-95.49%)
DFPlayerMini FastFast and easy to understand Arduino library to use the DFPlayer Mini MP3 module from DFRobot.com. This is a huge improvement (both in terms of execution speed and simplicity) to the standard library provided by DFRobot.com.
Stars: ✭ 164 (-61.05%)
muparserssemuparsersse a math parser for windows using just in time compilations of the expression
Stars: ✭ 14 (-96.67%)
seq2seq-pytorchSequence to Sequence Models in PyTorch
Stars: ✭ 41 (-90.26%)
query-selectorLONG-TERM SERIES FORECASTING WITH QUERYSELECTOR – EFFICIENT MODEL OF SPARSEATTENTION
Stars: ✭ 63 (-85.04%)