Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.

Last update: Dec 16, 2022

Overview

Optimum Transformers

Accelerated NLP pipelines for fast inference 🚀 on CPU and GPU. Built with 🤗 Transformers, Optimum and ONNX runtime.

Installation:

With PyPI:

pip install optimum-transformers

Or directly from GitHub:

pip install git+https://github.com/AlekseyKorshuk/optimum-transformers

Usage:

The pipeline API is similar to transformers pipeline with just a few differences which are explained below.

Just provide the path/url to the model, and it'll download the model if needed from the hub and automatically create onnx graph and run inference.

from optimum_transformers import pipeline

# Initialize a pipeline by passing the task name and 
# set onnx to True (default value is also True)
nlp = pipeline("sentiment-analysis", use_onnx=True)
nlp("Transformers and onnx runtime is an awesome combo!")
# [{'label': 'POSITIVE', 'score': 0.999721109867096}]

Or provide a different model using the model argument.

from optimum_transformers import pipeline

nlp = pipeline("question-answering", model="deepset/roberta-base-squad2", use_onnx=True)
nlp(question="What is ONNX Runtime ?",
         context="ONNX Runtime is a highly performant single inference engine for multiple platforms and hardware")
# {'answer': 'highly performant single inference engine for multiple platforms and hardware', 'end': 94,
# 'score': 0.751201868057251, 'start': 18}

from optimum_transformers import pipeline

nlp = pipeline("ner", model="mys/electra-base-turkish-cased-ner", use_onnx=True, optimize=True,
                    grouped_entities=True)
nlp("adana kebap ülkemizin önemli lezzetlerinden biridir.")
# [{'entity_group': 'B-food', 'score': 0.869149774312973, 'word': 'adana kebap'}]

Set use_onnx to False for standard torch inference. Set optimize to True for quantize with ONNX. ( set use_onnx to True)

Supported pipelines

You can create Pipeline objects for the following down-stream tasks:

feature-extraction: Generates a tensor representation for the input sequence
ner and token-classification: Generates named entity mapping for each word in the input sequence.
sentiment-analysis: Gives the polarity (positive / negative) of the whole input sequence. Can be used for any text classification model.
question-answering: Provided some context and a question referring to the context, it will extract the answer to the question in the context.
text-classification: Classifies sequences according to a given number of classes from training.
zero-shot-classification: Classifies sequences according to a given number of classes directly in runtime.
fill-mask: The task of masking tokens in a sequence with a masking token, and prompting the model to fill that mask with an appropriate token.
text-generation: The task of generating text according to the previous text provided.

Calling the pipeline for the first time loads the model, creates the onnx graph, and caches it for future use. Due to this, the first load will take some time. Subsequent calls to the same model will load the onnx graph automatically from the cache.

Benchmarks

Note: For some reason, onnx is slow on colab notebook, so you won't notice any speed-up there. Benchmark it on your own hardware.

Check our example of benchmarking: example.

For detailed benchmarks and other information refer to this blog post and notebook.

Note: These results were collected on my local machine. So if you have high performance machine to benchmark, please contact me.

Benchmark sentiment-analysis pipeline

Benchmark zero-shot-classification pipeline

Benchmark token-classification pipeline

Benchmark question-answering pipeline

Benchmark fill-mask pipeline

About

Built by Aleksey Korshuk

🚀 If you want to contribute to this project OR create something cool together — contact me: link

Star this repository:

Resources

Inspired by Huggingface Infinity
First step done by Suraj Patil
Optimum
ONNX

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

ONNX Runtime is a cross-platform inference and training machine-learning accelerator. ONNX Runtime inference can enable faster customer experiences an

8k Jan 4, 2023

Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel order of RGB and BGR. Simple Channel Converter for ONNX.

scc4onnx Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel

16 Dec 22, 2022

A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX.

sam4onnx A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for

6 May 15, 2022

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]

PINTO_model_zoo Please read the contents of the LICENSE file located directly under each folder before using the model. My model conversion scripts ar

2.4k Jan 5, 2023

ONNX-GLPDepth - Python scripts for performing monocular depth estimation using the GLPDepth model in ONNX

18 Nov 6, 2022

ONNX-PackNet-SfM: Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

14 Dec 9, 2022

A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want.

sne4onnx A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or

10 Aug 30, 2022

Simple ONNX operation generator. Simple Operation Generator for ONNX.

sog4onnx Simple ONNX operation generator. Simple Operation Generator for ONNX. https://github.com/PINTO0309/simple-onnx-processing-tools Key concept V

Simple tool to combine(merge) onnx models. Simple Network Combine Tool for ONNX.

snc4onnx Simple tool to combine(merge) onnx models. Simple Network Combine Tool for ONNX. https://github.com/PINTO0309/simple-onnx-processing-tools 1.

8 Oct 13, 2022

v0.2.1-upd(Apr 1, 2022)

Source code(tar.gz)
Source code(zip)
v0.2.1(Apr 1, 2022)

Source code(tar.gz)
Source code(zip)
v0.2.0(Mar 31, 2022)

Source code(tar.gz)
Source code(zip)
1.0.1(Mar 26, 2022)
Full Changelog

Added text-generation pipeline

Source code(tar.gz)
Source code(zip)
1.0.0(Mar 24, 2022)

Source code(tar.gz)
Source code(zip)

Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.

Related tags

Overview

Optimum Transformers

Installation:

Usage:

Supported pipelines

Benchmarks

About

Resources

You might also like...

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel order of RGB and BGR. Simple Channel Converter for ONNX.

A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX.

ONNX-GLPDepth - Python scripts for performing monocular depth estimation using the GLPDepth model in ONNX

ONNX-PackNet-SfM: Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want.

Simple ONNX operation generator. Simple Operation Generator for ONNX.

Simple tool to combine(merge) onnx models. Simple Network Combine Tool for ONNX.

Releases(v0.2.1-upd)

v0.2.1-upd(Apr 1, 2022)

v0.2.1(Apr 1, 2022)

v0.2.0(Mar 31, 2022)

1.0.1(Mar 26, 2022)

1.0.0(Mar 24, 2022)

Owner

Aleksey Korshuk

Deep Image Matting implementation in PyTorch

Implementation for "Conditional entropy minimization principle for learning domain invariant representation features"

I-BERT: Integer-only BERT Quantization

[ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

Generalized Decision Transformer for Offline Hindsight Information Matching

This is the face keypoint train code of project face-detection-project

Parris, the automated infrastructure setup tool for machine learning algorithms.

Real-time analysis of intracranial neurophysiology recordings.

A Parameter-free Deep Embedded Clustering Method for Single-cell RNA-seq Data

Code for our ACL 2021 paper "One2Set: Generating Diverse Keyphrases as a Set"

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

OpenAi's gym environment wrapper to vectorize them with Ray

Customizable RecSys Simulator for OpenAI Gym

Ranger deep learning optimizer rewrite to use newest components

DeconvNet : Learning Deconvolution Network for Semantic Segmentation

Molecular Sets (MOSES): A benchmarking platform for molecular generation models

Accompanying code for the paper "A Kernel Test for Causal Association via Noise Contrastive Backdoor Adjustment".

Implementation of "Bidirectional Projection Network for Cross Dimension Scene Understanding" CVPR 2021 (Oral)

Codes for our IJCAI21 paper: Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization