计算机视觉--常用数据库

summary

dataset im_size class*num download task example code
mnist 28*28 70000
CIFAR-10 32x32 10*6000
CIFAR-100 32x32 170M 100*600
Pascal VOC (05-12) 2GB voc2012
coco 40GB
imagenet2012 尺寸不固定,但多数比较清晰 1000类,训练集1.2m,验证集50k,测试集100k
imagenet2016 1400多万幅图片,涵盖2万多个类别 1TB
places
12306 约80*80

分类结果汇总

task_code: 1. 图像分类(image classification) 1. 目标检测(object detection) 1. 目标识别(object recognition) 1. 语义分割(semantic segmentation) 1. 实例分割(instance segmentation)

来自pytorch vision github的data

LSUN http://lsun.cs.princeton.edu_ dataset Local Image Descriptors Data <http://phototour.cs.washington.edu/patches/default.htm>_ Dataset. SEMEION http://archive.ics.uci.edu/ml/datasets/semeion+handwritten+digit_ Dataset. STL10 <https://cs.stanford.edu/~acoates/stl10/>_ Dataset. SVHN http://ufldl.stanford.edu/housenumbers/`_ Dataset.