fast.ai 2020 — Lesson 1

Deep learning is the best known approach in these areas
It’s possible to write markdown and code into the same Jupyter Notebook and code can be run one cell at a time
training machine learning model
from fastai2.vision.all import *
path = untar_data(URLs.PETS)/'images'
def is_cat(x): return x[0].isupper()
dls = ImageDataLoaders.from_name_func(
path, get_image_files(path), valid_pct=0.2, seed=42,
label_func=is_cat, item_tfms=Resize(224))
learn = cnn_learner(dls, resnet34, metrics=error_rate)
Overfiting means that the function is fitted exactly to the training data but for real use case it’s not going to use well
learn.fine_tune(1)
doc(ImageDataLoaders.from_name_func)
Almost the same code…
…but totally different purpose
nlp
tabular
recommendation

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store