Transfer learning & fine-tuning - Deepstash
Transfer learning & fine-tuning

Transfer learning & fine-tuning

Curated from: keras.io

Ideas, facts & insights covering these topics:

1 idea

·

22 reads

Transfer learning and fine tuning

Transfer learning consists of taking features learned on one problem, and leveraging them on a new, similar problem. For instance, features from a model that has learned to identify racoons may be useful to kick-start a model meant to identify tanukis.

  1. Take layers from a previously trained model.
  2. Freeze them, so as to avoid destroying any of the information they contain during future training rounds.
  3. Add some new, trainable layers on top of the frozen layers. They will learn to turn the old features into predictions on a new dataset.
  4. Train the new layers on your dataset.

Layers & models have three weight attributes:

  • weights is the list of all weights variables of the layer.
  • trainable_weights is the list of those that are meant to be updated (via gradient descent) to minimize the loss during training.
  • non_trainable_weights is the list of those that aren't meant to be trained. Typically they are updated by the model during the forward pass.

7

22 reads

IDEAS CURATED BY

samuelbancroft

Keep reading, keep studying, the more you learn the more you change. If you are doing the Python lessons please join this discord channel https://discord.gg/kugXx9KY but please follow the rules

samuel bancroft's ideas are part of this journey:

Mood Boosters: Put Yourself in a Happy Mood

Learn more about personaldevelopment with this collection

The power of gratitude and positive thinking

Ways to improve your mood

Simple daily habits for a happier life

Related collections

Read & Learn

20x Faster

without
deepstash

with
deepstash

with

deepstash

Personalized microlearning

—

100+ Learning Journeys

—

Access to 200,000+ ideas

—

Access to the mobile app

—

Unlimited idea saving

—

—

Unlimited history

—

—

Unlimited listening to ideas

—

—

Downloading & offline access

—

—

Supercharge your mind with one idea per day

Enter your email and spend 1 minute every day to learn something new.

Email

I agree to receive email updates