Learn practical skills, build real-world projects, and advance your career

CIFAR-10 with Fast.AI

alt

I will be testing Resnet-18, Resnet-34, Resnet-50, and Resnet-101 to see which achieves the highest accuracy rate.

#@title Importing libraries: { display-mode: "form" }
%%capture
! [ -e /content ] && pip install -Uqq fastbook
import fastbook
fastbook.setup_book()
!pip install nbdev
from fastbook import *
from fastai.vision.widgets import *
import nbdev
from fastai.vision import *
from pathlib import Path
import PIL

Downloading the data:

path = untar_data(URLs.CIFAR)

Creating data loader template and dataloaders: