Transfer Learning


Transfer learning is a method in machine learning that reuses a model developed for a task on a new but related problem. It is a popular approach to start off common deep learning tasks, such as computer vision and natural language processing, that require huge compute and resources in terms of time and skills. Transfer Learning can train deep neural networks with little data by using the knowledge gained from a pre-trained model.

Filter terms by

Glossary Alphabetical filter

Related resources

featured image for how to measure inference time
Computer Vision
Add Your Heading Text Here
					from transformers import AutoFeatureExtractor, AutoModelForImageClassification

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

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