Concept

Number of Layers to Freeze When Using a Pre-trained Model for Transfer Deep Learning

The decision of how many layers to freeze or replace when using a pre-trained model for transfer learning depends on the size of the dataset:

  • Small dataset: Replace only the last layer.
  • Large dataset: Replace multiple of the last layers with new layers.
  • Extremely large dataset: If sufficient computational power is available, the pre-trained network can be used for weight initialization, and all the weights across the entire network can be trained.

0

1

Updated 2026-07-01

Tags

Data Science