深度学习神经网络数据集模型合集

本文收集新手入门常用的数据集、模型的下载地址，如果源下载速度较慢，也会提供镜像加速。

数据集

只搜集最新版，如果需要以前版本可以到官网中找

名称	加速地址	大小	格式	数量
MS COCO (Microsoft Common Objects in Context) 2017		500G
Pascal VOC Data 2012版		1.9G 训练 + 1.8G 测试	20 classes. The train/val data has 11,530 images containing 27,450 ROI annotated objects and 6,929 segmentations.
Open Images dataset V6		0.5T
ImageNet	kaggle中
CIFAR-10		162M	bin	60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.
CIFAR-100		160M	bin	100 classes containing 600 images each. There are 500 training images and 100 testing images per class. The 100 classes in the CIFAR-100 are grouped into 20 superclasses.
SUN 2010 数据集		39.7G	contains 899 categories and 130,519 images. We use 397 well-sampled categories
ADE20K			25.574 images train 2.000 images test