Buy Me a Coffee☕
*My post explains MNIST, EMNIST, QMNIST, ETLCDB, Kuzushiji and Moving MNIST.
(1) Fashion-MNIST(2017):
- has the 70,000 fashion images each connected to a label from 10 classes with 10 classes:
*Memos:
- 60,000 for train and 10,000 for test.
- Each image is 28x28 pixels.
- is FashionMNIST() in PyTorch.
(2) Caltech 101(2003):
- has the 8,677 object images each connected to a label from 101 categories(classes). *Each image is roughly 300x200 pixels.
- is Caltech101() in PyTorch.
(3) Caltech 256(2007):
- has the 30,607 object images connected to a label from 257 categories(classes). *Actually, it has 257 categories(classes) against the name Caltech 256.
- is Caltech256() in PyTorch.
(4) CelebA(Large-scale CelebFaces Attributes)(2015):
- has the 202,599 celebrity face images each connected to 40 attributes:
*Memos:
- 162,770 for train, 19,867 for validation and 19,962 for test.
- Directly downloading it from Google Drive is recommended because downloading it with Google Drive API from Google Drive is too crowded.
- is CelebA() in PyTorch.
(5) CIFAR-10(Canadian Institute For Advanced Research-10)(2009):
- has the 60,000 vehicle and animal images each connected to a label from 10 classes:
*Memos:
- 50,000 for train and 10,000 for test.
- Each image is 32x32 pixels.
- is CIFAR10() in PyTorch.
(6) CIFAR-100(Canadian Institute For Advanced Research-100)(2009):
- has the 60,000 object images each connected to a label from 100 classes:
*Memos:
- 50,000 for train and 10,000 for test.
- Each image is 32x32 pixels.
- is CIFAR100() in PyTorch.
The above is the detailed content of Datasets for Computer Vision (2). For more information, please follow other related articles on the PHP Chinese website!