Datasets
by @stats385 · 5 nodes · curated
Canonical vision benchmarks used throughout the course: MNIST, CIFAR-10, ImageNet.
untagged
Karpathy — Competing Against a ConvNet on ImageNet
karpathy.github.io · Sep 24
Human-vs-convnet notes — useful perspective piece for students.
ImageNet (overview)
en.wikipedia.org · Sep 24
Background on ILSVRC and why ImageNet mattered historically for deep learning.
ImageNet
image-net.org · Sep 24
Large-scale image database that powered AlexNet and the modern deep learning boom.
CIFAR-10
cs.toronto.edu · Sep 24
60k 32×32 color images, 10 classes. Standard small-scale vision benchmark for theory papers.
MNIST
yann.lecun.com · Sep 24
60k train / 10k test handwritten digits, 28×28. The ‘hello world’ of classification.
Suggested Links
Generating suggestions...
This may take 5-10 seconds
Clean titles
Analyzing titles...
This may take 5-10 seconds