Onnxsim

onnxsim este un optimizator de grafuri de deep learning și un simplificator de modele conceput pentru a reduce complexitatea grafurilor de calcul ONNX. Funcționează ca un compresor de modele care înlocuiește secvențele complexe de operatori cu ieșiri constante simplificate pentru a reduce overhead-ul operațional.

Proiectul obține simplificarea prin inferența constant folding, care înlocuiește subgrafurile de operatori constanți cu tensori constanți pre-calculați. Utilizează rescrierea grafurilor bazată pe modele și analiza statică a grafurilor de calcul pentru a identifica și elimina nodurile redundante sau operațiunile inaccesibile.

Instrumentul acoperă capabilități largi de optimizare a modelelor, inclusiv eliminarea redundanței operatorilor și eliminarea nodurilor inutile de reshape sau identity. Aceste procese eficientizează fluxul de execuție și reduc amprenta de memorie a modelului.

Features

Model Graph Optimizers - Simplifies and optimizes model graphs to reduce operational overhead and improve inference performance.
ONNX Model Optimizers - Cleans up ONNX model structures by removing unnecessary nodes to streamline execution flow.
Operator - Eliminates identity operations and unnecessary reshape nodes that do not alter mathematical output.
Model Compression - Decreases the memory footprint of models by replacing complex operator sequences with constant outputs.
ONNX Intermediate Representation Manipulators - Provides direct manipulation of the ONNX intermediate representation to optimize model structure.
Constant Folding - Implements constant folding to replace complex operator subgraphs with pre-computed constant tensors.
Graph Pattern Rewriters - Uses pattern-based rewriting to replace operator sequences with simplified equivalent structures.
Deep Learning Optimization - Prepares neural networks for production by simplifying computational graphs to improve efficiency.
Execution Graph Analysis - Analyzes the execution graph to identify unreachable operations and redundant nodes for removal.

Istoric stele

onnxsimonnxsim

Name: onnxsim/onnxsim
Author: onnxsim

View on GitHub

4,353 stele430 fork-uriC++Apache-2.06 vizualizărionnxsim.github.io/onnxsim

Onnxsim

Features

Model Graph Optimizers - Simplifies and optimizes model graphs to reduce operational overhead and improve inference performance.
ONNX Model Optimizers - Cleans up ONNX model structures by removing unnecessary nodes to streamline execution flow.
Operator - Eliminates identity operations and unnecessary reshape nodes that do not alter mathematical output.
Model Compression - Decreases the memory footprint of models by replacing complex operator sequences with constant outputs.
ONNX Intermediate Representation Manipulators - Provides direct manipulation of the ONNX intermediate representation to optimize model structure.
Constant Folding - Implements constant folding to replace complex operator subgraphs with pre-computed constant tensors.
Graph Pattern Rewriters - Uses pattern-based rewriting to replace operator sequences with simplified equivalent structures.
Deep Learning Optimization - Prepares neural networks for production by simplifying computational graphs to improve efficiency.
Execution Graph Analysis - Analyzes the execution graph to identify unreachable operations and redundant nodes for removal.

Alternative open-source pentru Onnxsim

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Onnxsim.

nvidia/tensorrt
NVIDIA/TensorRT
13,076Vezi pe GitHub
TensorRT is a deep learning inference engine and software development kit designed to optimize and deploy neural networks for high-performance execution on NVIDIA GPUs. It functions as a GPU acceleration framework that reduces latency and increases throughput for trained models during production deployment. The toolkit imports models from the Open Neural Network Exchange format and transforms them into optimized engines. It utilizes graph-based model optimization, layer-fusion kernel generation, and precision-based quantization to convert floating point weights into lower precision formats.
C++deep-learninggpu-accelerationinference
Vezi pe GitHub13,076
paddlepaddle/paddle
PaddlePaddle/Paddle
23,632Vezi pe GitHub
Paddle is a deep learning framework designed for building, training, and deploying neural networks. It provides a platform for constructing models using tensor-based computations and supports both dynamic and static execution graphs to facilitate research and production workflows. The platform functions as a distributed machine learning system, enabling the scaling of training workloads across multiple nodes and hardware clusters. It includes a comprehensive toolkit for model deployment and optimization, allowing users to convert external model formats, compress trained models for resource-co
C++deep-learningdistributed-trainingefficiency
Vezi pe GitHub23,632
tingsongyu/pytorch_tutorial
TingsongYu/PyTorch_Tutorial
8,018Vezi pe GitHub
This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene
Python
Vezi pe GitHub8,018

Întrebări frecvente

Ce face onnxsim/onnxsim?

Care sunt principalele funcționalități ale onnxsim/onnxsim?

Principalele funcționalități ale onnxsim/onnxsim sunt: Model Graph Optimizers, ONNX Model Optimizers, Operator, Model Compression, ONNX Intermediate Representation Manipulators, Constant Folding, Graph Pattern Rewriters, Deep Learning Optimization.

Care sunt câteva alternative open-source pentru onnxsim/onnxsim?

Alternativele open-source pentru onnxsim/onnxsim includ: nvidia/tensorrt — TensorRT is a deep learning inference engine and software development kit designed to optimize and deploy neural… paddlepaddle/paddle — Paddle is a deep learning framework designed for building, training, and deploying neural networks. It provides a… tingsongyu/pytorch_tutorial — This project is a comprehensive collection of educational examples and reference implementations for building vision… tingsongyu/pytorch-tutorial-2nd — This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It… pytorch/executorch — ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It… apple/coremltools — coremltools is a conversion toolkit and translator designed to transform machine learning models from various…

Onnxsim

Features

Istoric stele

Onnxsim

Features

Alternative open-source pentru Onnxsim

NVIDIA/TensorRT

PaddlePaddle/Paddle

TingsongYu/PyTorch_Tutorial

Întrebări frecvente

Istoric stele

Întrebări frecvente

Alternative open-source pentru Onnxsim

NVIDIA/TensorRT

PaddlePaddle/Paddle

TingsongYu/PyTorch_Tutorial

TingsongYu/PyTorch-Tutorial-2nd