The Levers of Deep Learning
Experimenting with various 'levers' that can be switched on in a deep learning project.
The Levers of Deep Learning
Intro
The Data
The Model
Fitting vs. Fine-Tuning
1cycle Policy and the Learning Rate Finder
Discriminative Learning Rates
from fastai.vision.all import *
path = untar_data(URLs.PETS)
Path.BASE_PATH = path
Formatting text as shell commands:
echo "hello world"
./some_script.sh --option "value"
wget https://example.com/cat_photo1.png
Formatting text as YAML:
key: value
- another_key: "another value"
Tables
Column 1 | Column 2 |
---|---|
A thing | Another thing |
Tweetcards
Altair 4.0 is released! https://t.co/PCyrIOTcvv
— Jake VanderPlas (@jakevdp) December 11, 2019
Try it with:
pip install -U altair
The full list of changes is at https://t.co/roXmzcsT58 ...read on for some highlights. pic.twitter.com/vWJ0ZveKbZ