Easily train or fine-tune SOTA computer vision models with one open source training library

---

Website • Why Use SG? • User Guide • Docs • SOTA Pretrained Models • Community • License • Deci Lab

SuperGradients

Introduction

Welcome to SuperGradients, a free, open-source training library for PyTorch-based deep learning models. SuperGradients allows you to train or fine-tune SOTA pre-trained models for all the most commonly applied computer vision tasks with just one training library. We currently support object detection, image classification and semantic segmentation for videos and images.

Docs and full user guide

Why use SuperGradients?

Built-in SOTA Models

Easily load and fine-tune production-ready, pre-trained SOTA models that incorporate best practices and validated hyper-parameters for achieving best-in-class accuracy.

Easily Reproduce our Results

Why do all the grind work, if we already did it for you? leverage tested and proven recipes & code examples for a wide range of computer vision models generated by our team of deep learning experts. Easily configure your own or use plug & play hyperparameters for training, dataset, and architecture.

Production Readiness and Ease of Integration

All SuperGradients models’ are production ready in the sense that they are compatible with deployment tools such as TensorRT (Nvidia) and OpenVino (Intel) and can be easily taken into production. With a few lines of code you can easily integrate the models into your codebase.

What's New

• 【07/02/2022】 We added RegSeg recipes and pre-trained models to our Semantic Segmentation models.
• 【01/02/2022】 We added issue templates for feature requests and bug reporting.
• 【20/01/2022】 STDC family - new recipes added with even higher mIoU💪
• 【17/01/2022】 We have released transfer learning example notebook for object detection (YOLOv5).

Check out SG full release notes.

Comming soon

• YOLOX models (recipes, pre-trained checkpoints).
• SSD MobileNet models (recipes, pre-trained checkpoints) for edge devices deployment.
• Transfer learning example notebook for semantic segmentation (STDC).
• Dali implementation.
• Integration with professional tools.

---

Table of Content

See Table

• Getting Started
  • Quick Start Notebook - classification example
  • Quick Start Notebook - object detection example
  • Walkthrough Notebook
  • Transfer Learning with SG Notebook - Object detection example
• Installation Methods
  • Prerequisites
  • Quick Installation
• Computer Vision Models - Pretrained Checkpoints
  • Pretrained Classification PyTorch Checkpoints
  • Pretrained Object Detection PyTorch Checkpoints
  • Pretrained Semantic Segmentation PyTorch Checkpoints
• Contributing
• Citation
• Community
• License
• Deci Lab

Getting Started

Quick Start Notebook - Classification

Get started with our quick start notebook for image classification tasks on Google Colab for a quick and easy start using free GPU hardware.

SuperGradients Quick Start in Google Colab

Download notebook

View source on GitHub

Quick Start Notebook - Object Detection

Get started with our quick start notebook for object detection tasks on Google Colab for a quick and easy start using free GPU hardware.

SuperGradients Quick Start in Google Colab

Download notebook

View source on GitHub

SuperGradients Complete Walkthrough Notebook

Learn more about SuperGradients training components with our walkthrough notebook on Google Colab for an easy to use tutorial using free GPU hardware

SuperGradients Walkthrough in Google Colab

Download notebook

View source on GitHub

Transfer Learning with SG Notebook - Object Detection

Learn more about SuperGradients transfer learning or fine tuning abilities with our COCO pre-trained YoloV5nano fine tuning into a sub-dataset of PASCAL VOC example notebook on Google Colab for an easy to use tutorial using free GPU hardware

SuperGradients Transfer Learning in Google Colab

Download notebook

View source on GitHub

Installation Methods

Prerequisites

General requirements

• Python 3.7, 3.8 or 3.9 installed.
• torch>=1.9.0
  • https://pytorch.org/get-started/locally/
• The python packages that are specified in requirements.txt;

To train on nvidia GPUs

• Nvidia CUDA Toolkit >= 11.2
• CuDNN >= 8.1.x
• Nvidia Driver with CUDA >= 11.2 support (≥460.x)

Quick Installation

Install stable version using PyPi

See in PyPi

pip install super-gradients

That's it !

Install using GitHub

pip install git+https://github.com/Deci-AI/super-gradients.git@stable

Documentation

Check SuperGradients Docs for full documentation, user guide, and examples.

Computer Vision Models - Pretrained Checkpoints

Pretrained Classification PyTorch Checkpoints

Model	Dataset	Resolution	Top-1	Top-5	Latency b1T4	Throughput b1T4
EfficientNet B0	ImageNet	224x224	77.62	93.49	1.16ms	862fps
RegNetY200	ImageNet	224x224	70.88	89.35	1.07ms	928.3fps
RegNetY400	ImageNet	224x224	74.74	91.46	1.22ms	816.5fps
RegNetY600	ImageNet	224x224	76.18	92.34	1.19ms	838.5fps
RegNetY800	ImageNet	224x224	77.07	93.26	1.18ms	841.4fps
ResNet18	ImageNet	224x224	70.6	89.64	0.599ms	1669fps
ResNet34	ImageNet	224x224	74.13	91.7	0.89ms	1123fps
ResNet50	ImageNet	224x224	79.47	93.0	0.94ms	1063fps
MobileNetV3_large-150 epochs	ImageNet	224x224	73.79	91.54	0.87ms	1149fps
MobileNetV3_large-300 epochs	ImageNet	224x224	74.52	91.92	0.87ms	1149fps
MobileNetV3_small	ImageNet	224x224	67.45	87.47	0.75ms	1333fps
MobileNetV2_w1	ImageNet	224x224	73.08	91.1	0.58ms	1724fps

NOTE: Performance measured on T4 GPU with TensorRT, using FP16 precision and batch size 1

Pretrained Object Detection PyTorch Checkpoints

Model	Dataset	Resolution	mAPval 0.5:0.95	Latency b1T4	Throughput b64T4
YOLOv5 nano	COCO	640x640	27.7	6.55ms	177.62fps
YOLOv5 small	COCO	640x640	37.3	7.13ms	159.44fps
YOLOv5 medium	COCO	640x640	45.2	8.95ms	121.78fps
YOLOv5 large	COCO	640x640	48.0	11.49ms	95.99fps

NOTE: Performance measured on T4 GPU with TensorRT, using FP16 precision and batch size 1 (latency) and batch size 64 (throughput)

Pretrained Semantic Segmentation PyTorch Checkpoints

Model	Dataset	Resolution	mIoU	Latency b1T4	Throughput b1T4	Latency b1T4 including IO
DDRNet23	Cityscapes	1024x2048	78.65	7.62ms	131.3fps	25.94ms
DDRNet23 slim	Cityscapes	1024x2048	76.6	3.56ms	280.5fps	22.80ms
STDC1-Seg50	Cityscapes	512x1024	74.36	2.83ms	353.3fps	12.57ms
STDC1-Seg75	Cityscapes	768x1536	76.87	5.71ms	175.1fps	26.70ms
STDC2-Seg50	Cityscapes	512x1024	75.27	3.74ms	267.2fps	13.89ms
STDC2-Seg75	Cityscapes	768x1536	78.93	7.35ms	135.9fps	28.18ms
RegSeg (exp48)	Cityscapes	1024x2048	78.15	13.09ms	76.4fps	41.88ms
Larger RegSeg (exp53)	Cityscapes	1024x2048	79.2	24.82ms	40.3fps	51.87ms
ShelfNet_LW_34	COCO Segmentation (21 classes from PASCAL including background)	512x512	65.1	-	-	-

NOTE: Performance measured on T4 GPU with TensorRT, using FP16 precision and batch size 1 (latency), and not including IO

Contributing

To learn about making a contribution to SuperGradients, please see our Contribution page.

Our awesome contributors:

Made with contrib.rocks.

Citation

If you are using SuperGradients library or benchmarks in your research, please cite SuperGradients deep learning training library.

Community

If you want to be a part of SuperGradients growing community, hear about all the exciting news and updates, need help, request for advanced features, or want to file a bug or issue report, we would love to welcome you aboard!

• Slack is the place to be and ask questions about SuperGradients and get support. Click here to join our Slack

• To report a bug, file an issue on GitHub.

• Join the SG Newsletter for staying up to date with new features and models, important announcements, and upcoming events.

• For a short meeting with us, use this link and choose your preferred time.

License

This project is released under the Apache 2.0 license.

---

Deci Lab

Deci Lab is our end to end platform for building, optimizing and deploying deep learning models to production.

Sign up for our FREE Community Tier to enjoy immediate improvement in throughput, latency, memory footprint and model size.

Features:

• Automatically compile and quantize your models with just a few clicks (TrT, OpenVino).
• Gain up to 10X improvement in throughput, latency, memory and model size.
• Easily benchmark your models’ performance on different hardware and batch sizes.
• Invite co-workers to collaborate on models and communicate your progress.
• Deci supports all common frameworks and Hardware, from Intel CPUs to Nvidia's GPUs and Jetsons.

Sign up for Deci Lab for free here