Concept

Computational Benefits of Freezing Pretrained Parameters

When utilizing a pretrained model solely as a feature extractor, its parameters are explicitly frozen to prevent them from being updated during training. Because these feature extraction layers remain fixed, the optimization algorithm does not need to compute or store their gradients during backpropagation. This approach substantially reduces the overall training time and minimizes the memory footprint required for storing gradients, making it highly efficient for adapting large models to new tasks.

0

1

Updated 2026-05-23

Contributors are:

Who are from:

Tags

D2L

Dive into Deep Learning @ D2L