Maximize Your Model’s Performance with SuperGradients

An open-source library for training PyTorch-based computer vision models. Developed by Deci’s deep learning experts for the benefit of the AI community.

Boost Performance with Advanced Techniques

Simplify Training

Easy to Use Pre-trained 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.

Plug Your Data with Ease

Integrate any custom dataset, losses, metrics to SuperGradients.

Compatible with PyTorch Dataset, Losses & Metrics

Easy plug and play your own PyTorch data loaders. Compatible with PyTorch dataset, losses, and metrics instead of PyTorch based data loader.

Error Tip

Save time with better insight into the most common training errors. Quickly understand how to overcome them with suggested remediations tips.

Shorten Training Time

Easily Integrate with Your Existing MLOps Stack

Accuracy Comparison Table

Get Started Now

Implemented
Architectures

Find open source computer vision model architectures for your needs.

Pre-trained
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.

Join the
Community

Join the Deep Learning Daily community to ask questions, learn from other practitioners and grow your professional network.

Live Coding: How ResNet Changed Computer Vision

ResNet is an artificial neural network. It is a gateless or open-gated variant of the HighwayNet, the first working very deep feedforward neural network with hundreds of layers. In this walkthrough, Harpreet Sahota, DevRel Manager at Deci, demonstrates ResNet in action. You can check out the notebook here and follow along!

Live Coding: The EfficientNet family: Power, Speed, Accuracy and Efficiency

EfficientNet is a convolutional neural network architecture and scaling method that uniformly scales all dimensions of depth/width/resolution using a compound coefficient. Join Harpreet Sahota, DevRel Manager at Deci, for a walkthrough of ResNet in action. You can check out the notebook and follow along!

Live Coding: RegNet- The Most Flexible Network Architecture For Computer Vision

RegNet is a highly flexible network design space defined by a quantized linear function. It can be specified and scaled for high efficiency or high accuracy. Join Harpreet Sahota, DevRel Manager at Deci, for a walkthrough of RegNet in action, using it to determine whether an image is Santa or not. You can check out the notebook and follow along!

Share
Add Your Heading Text Here
				
					from transformers import AutoFeatureExtractor, AutoModelForImageClassification

extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")

model = AutoModelForImageClassification.from_pretrained("microsoft/resnet-50")