1237 Open source projects that are alternatives of or similar to fastT5

🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools

Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.

Rust wrapper for Microsoft's ONNX Runtime (version 1.8)

An Open Source Deep Learning Inference Engine Based on FPGA

[ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering

🍅🍅🍅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~

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

PyTorch Project Specification.

A 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]

KitanaQA: Adversarial training and data augmentation for neural question-answering models

Codes to pre-train Japanese T5 models

micronet, 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

Yet another yolov5, with its runtime stack for libtorch, onnx, tvm and specialized accelerators. You like torchvision's retinanet? You like yolov5? You love yolort!

Exposes a serialized machine learning model through a HTTP API.

Serving AI/ML models in the open standard formats PMML and ONNX with both HTTP (REST API) and gRPC endpoints

Docker scripts for building ONNX Runtime with TensorRT and OpenVINO in manylinux environment

Python scripts form performing stereo depth estimation using the HITNET model in ONNX.

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

Multi Model Server is a tool for serving neural net models for inference

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

The purpose of this project is to apply mediapipe to more AI chips.

Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

Embedded and mobile deep learning research resources

MLModelCI 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.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Graphsignal Python agent

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint

Trained T5 and T5-large model for creating keywords from text

MIVisionX 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.

A collection of SOTA Image Classification Models in PyTorch

volksdep is an open-source toolbox for deploying and accelerating PyTorch, ONNX and TensorFlow models with TensorRT.

Python scripts for performing 3D human pose estimation using the Mobile Human Pose model in ONNX.

Efficient ML Filter Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2, and Real-CUGAN)

Ramp up your custom natural language processing (NLP) task, allowing you to bring your own data, use your preferred frameworks and bring models into production.

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Running BERT without Padding

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering

No description or website provided.

(CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery

This is the PyTorch implementation of the ACL 2019 paper RankQA: Neural Question Answering with Answer Re-Ranking.

A curated list of resources for Low-level Vision Tasks

Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

WebSocket for fasthttp

Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

Code for Synchronous Bidirectional Neural Machine Translation (SB-NMT)

MashaRoBot : 📑Editor's choice

Implementation for the paper "Hierarchical Conditional Relation Networks for Video Question Answering" (Le et al., CVPR 2020, Oral)

Laravel Quiz and Exam System clone of udemy

TianChi AIEarth Contest Solution

An easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"

Detect various irregularities of a product as it moves along a conveyor belt.

Fast 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.

muparsersse a math parser for windows using just in time compilations of the expression

Sequence to Sequence Models in PyTorch

fast.com API / CLI tool

LONG-TERM SERIES FORECASTING WITH QUERYSELECTOR – EFFICIENT MODEL OF SPARSEATTENTION