Book a Demo
Get Started

Pruning

Share

A relatively straightforward approach that prunes less important weights or filters from a trained model. It can compress the weights of shallow and simple networks, such as LeNet-5 and AlexNet, by an order of magnitude, without forfeiting accuracy.

 

Filter terms by

Alphabetical
Glossary Alphabetical filter

Related resources

sg-w&b-integration
Training
Track Your Experiments in SuperGradients Using Weights & Biases
Read More
featured image for how to measure inference time
Deployment
The Correct Way to Measure Inference Time of Deep Neural Networks
Read More
resnet50-how-to-achieve-SOTA-accuracy-on-imagenet
Computer Vision
How to Achieve SOTA Accuracy on ImageNet with ResNet50
Read More

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Deci is ISO 27001
Certified

Linkedin-in Twitter Vimeo-v Youtube Facebook-f
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")