Build, train, and fine-tune production-ready deep learning SOTA vision models

Version 3 is out! Notebooks have been updated!

---

Website • User Guide • Docs • Getting Started • Pretrained Models • Community • License • Deci Platform

Build with SuperGradients

---

Support various computer vision tasks

Ready to deploy pre-trained SOTA models

# Load model with pretrained weights
model = models.get("yolox_s", pretrained_weights="coco")

Classification

Semantic Segmentation

Object Detection

All Computer Vision Models - Pretrained Checkpoints can be found here

Easy to train 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. For more information on how to do it go to Getting Started

Plug and play recipes

python -m super_gradients.train_from_recipe --config-name=imagenet_regnetY architecture=regnetY800 dataset_interface.data_dir=<YOUR_Imagenet_LOCAL_PATH> ckpt_root_dir=<CHEKPOINT_DIRECTORY>

More example on how and why to use recipes can be found in Recipes

Production readiness

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.

# Load model with pretrained weights
model = models.get("yolox_s", pretrained_weights="coco")

# Prepare model for conversion
# Input size is in format of [Batch x Channels x Width x Height] where 640 is the standart COCO dataset dimensions
model.eval()
model.prep_model_for_conversion(input_size=[1, 3, 640, 640])
    
# Create dummy_input

# Convert model to onnx
torch.onnx.export(model, dummy_input,  "yolox_s.onnx")

More information on how to take your model to production can be found in Getting Started notebooks

Quick Installation

---

pip install super-gradients

What's New

---

• 【06/9/2022】 PP-LiteSeg - new pre-trained checkpoints for Cityscapes with SOTA mIoU scores (~1.5% above paper)🎯
• 【07/08/2022】DDRNet23 - new pre-trained checkpoints and recipes for Cityscapes with SOTA mIoU scores (~1% above paper)🎯
• 【27/07/2022】YOLOX models (object detection) - recipes and pre-trained checkpoints.
• 【07/07/2022】SSD Lite MobileNet V2,V1 - Training recipes and pre-trained checkpoints on COCO - Tailored for edge devices! 📱
• 【07/07/2022】 STDC - new pre-trained checkpoints and recipes for Cityscapes with super SOTA mIoU scores (~2.5% above paper)🎯

Check out SG full release notes.

Coming soon

---

• PP-LiteSeg recipes for Cityscapes with SOTA mIoU scores (~1.5% above paper)🎯
• Single class detectors (recipes, pre-trained checkpoints) for edge devices deployment.
• Single class segmentation (recipes, pre-trained checkpoints) for edge devices deployment.
• QAT capabilities (Quantization Aware Training).
• Integration with more professional tools.

Table of Content

---

• Getting Started
• Advanced Features
• Installation Methods
  • Prerequisites
  • Quick Installation
• Implemented Model Architectures
• Contributing
• Citation
• Community
• License
• Deci Platform

Getting Started

---

Start Training with Just 1 Command Line

The most simple and straightforward way to start training SOTA performance models with SuperGradients reproducible recipes. Just define your dataset path and where you want your checkpoints to be saved and you are good to go from your terminal!

python -m super_gradients.train_from_recipe --config-name=imagenet_regnetY architecture=regnetY800 dataset_interface.data_dir=<YOUR_Imagenet_LOCAL_PATH> ckpt_root_dir=<CHEKPOINT_DIRECTORY>

Quickly Load Pre-Trained Weights for Your Desired Model with SOTA Performance

Want to try our pre-trained models on your machine? Import SuperGradients, initialize your Trainer, and load your desired architecture and pre-trained weights from our SOTA model zoo

# The pretrained_weights argument will load a pre-trained architecture on the provided dataset
    
import super_gradients

model = models.get("model-name", pretrained_weights="pretrained-model-name")

Classification

Transfer Learning

Classification Transfer Learning

GitHub source

Semantic Segmentation

Quick Start

Segmentation Quick Start

GitHub source

Transfer Learning

Segmentation Transfer Learning

GitHub source

How to Connect Custom Dataset

Segmentation How to Connect Custom Dataset

GitHub source

Object Detection

Transfer Learning

Detection Transfer Learning

GitHub source

How to Connect Custom Dataset

Detection How to Connect Custom Dataset

GitHub source

How to Predict Using Pre-trained Model

Segmentation, Detection and Classification Prediction

How to Predict Using Pre-trained Model

GitHub source

Advanced Features

---

Knowledge Distillation Training

Knowledge Distillation is a training technique that uses a large model, teacher model, to improve the performance of a smaller model, the student model. Learn more about SuperGradients knowledge distillation training with our pre-trained BEiT base teacher model and Resnet18 student model on CIFAR10 example notebook on Google Colab for an easy to use tutorial using free GPU hardware

Knowledge Distillation Training

GitHub source

Recipes

To train a model, it is necessary to configure 4 main components. These components are aggregated into a single "main" recipe .yaml file that inherits the aforementioned dataset, architecture, raining and checkpoint params. It is also possible (and recomended for flexibility) to override default settings with custom ones. All recipes can be found here

How to Use Recipes

GitHub source

Using DDP

from super_gradients import init_trainer
from super_gradients.common import MultiGPUMode
from super_gradients.training.utils.distributed_training_utils import setup_gpu_mode

# Initialize the environment
init_trainer()

# Launch DDP on 1 device (node) of 4 GPU's
setup_gpu_mode(gpu_mode=MultiGPUMode.DISTRIBUTED_DATA_PARALLEL, num_gpus=4)

# Define the objects

# The trainer will run on DDP without anything else to change

Easily change architectures parameters

from super_gradients.training import models

# instantiate default pretrained resnet18
default_resnet18 = models.get(name="resnet18", num_classes=100, pretrained_weights="imagenet")

# instantiate pretrained resnet18, turning DropPath on with probability 0.5
droppath_resnet18 = models.get(name="resnet18", arch_params={"droppath_prob": 0.5}, num_classes=100, pretrained_weights="imagenet")

# instantiate pretrained resnet18, without classifier head. Output will be from the last stage before global pooling
backbone_resnet18 = models.get(name="resnet18", arch_params={"backbone_mode": True}, pretrained_weights="imagenet")

Using phase callbacks

from super_gradients import Trainer
from torch.optim.lr_scheduler import ReduceLROnPlateau
from super_gradients.training.utils.callbacks import Phase, LRSchedulerCallback
from super_gradients.training.metrics.classification_metrics import Accuracy

# define PyTorch train and validation loaders and optimizer

# define what to be called in the callback
rop_lr_scheduler = ReduceLROnPlateau(optimizer, mode="max", patience=10, verbose=True)

# define phase callbacks, they will fire as defined in Phase
phase_callbacks = [LRSchedulerCallback(scheduler=rop_lr_scheduler,
                                       phase=Phase.VALIDATION_EPOCH_END,
                                       metric_name="Accuracy")]

# create a trainer object, look the declaration for more parameters
trainer = Trainer("experiment_name")

# define phase_callbacks as part of the training parameters
train_params = {"phase_callbacks": phase_callbacks}

Integration to Weights and Biases

from super_gradients import Trainer

# create a trainer object, look the declaration for more parameters
trainer = Trainer("experiment_name")

train_params = { ... # training parameters
                "sg_logger": "wandb_sg_logger", # Weights&Biases Logger, see class WandBSGLogger for details
                "sg_logger_params": # paramenters that will be passes to __init__ of the logger 
                  {
                    "project_name": "project_name", # W&B project name
                    "save_checkpoints_remote": True
                    "save_tensorboard_remote": True
                    "save_logs_remote": True
                  } 
               }

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

Implemented Model Architectures

---

Detailed list can be found here

Image Classification

• DensNet (Densely Connected Convolutional Networks)
• DPN
• EfficientNet
• LeNet
• MobileNet
• MobileNet v2
• MobileNet v3
• PNASNet
• Pre-activation ResNet
• RegNet
• RepVGG
• ResNet
• ResNeXt
• SENet
• ShuffleNet
• ShuffleNet v2
• VGG

Semantic Segmentation

• PP-LiteSeg
• DDRNet (Deep Dual-resolution Networks)
• LadderNet
• RegSeg
• ShelfNet
• STDC

Object Detection

• CSP DarkNet
• DarkNet-53
• SSD (Single Shot Detector)
• YOLOX

---

Documentation

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

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 Platform

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

Request free trial to enjoy immediate improvement in throughput, latency, memory footprint and model size.

Features:

• Automatically compile and quantize your models with just a few clicks (TensorRT, 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. ֿ

Request free trial here