机器学习笔记1——深度学习的数据库和目前一些流行的软件

一、首先我先查阅了深度学习的数据库：

1、mnist手写字符库

2、cifar10(caffe.theano)数据集分为5个训练块和1个测试块，每个块有10000个图像。测试块包含从每类随机选择的1000个图像。训练块以随机的顺序包含这些图像，但一些训练块可能比其它类包含更多的图像。训练块每类包含5000个图像。类与类之间完全互斥。

airplane,automobile,bird,cat,deer,dog,frog,horse,ship,truck

3、cifar100（有python版，matlab版，和用于c++的二值化版本）

数据集包含100小类，每小类包含600个图像，其中有500个训练图像和100个测试图像。100类被分组为20个大类。每个图像带有1个小类的“fine”标签和1个大类“coarse”标签。

Superclass	Classes
aquatic mammals	beaver, dolphin, otter, seal, whale
fish	aquarium fish, flatfish, ray, shark, trout
flowers	orchids, poppies, roses, sunflowers, tulips
food containers	bottles, bowls, cans, cups, plates
fruit and vegetables	apples, mushrooms, oranges, pears, sweet peppers
household electrical devices	clock, computer keyboard, lamp, telephone, television
household furniture	bed, chair, couch, table, wardrobe
insects	bee, beetle, butterfly, caterpillar, cockroach
large carnivores	bear, leopard, lion, tiger, wolf
large man-made outdoor things	bridge, castle, house, road, skyscraper
large natural outdoor scenes	cloud, forest, mountain, plain, sea
large omnivores and herbivores	camel, cattle, chimpanzee, elephant, kangaroo
medium-sized mammals	fox, porcupine, possum, raccoon, skunk
non-insect invertebrates	crab, lobster, snail, spider, worm
people	baby, boy, girl, man, woman
reptiles	crocodile, dinosaur, lizard, snake, turtle
small mammals	hamster, mouse, rabbit, shrew, squirrel
trees	maple, oak, palm, pine, willow
vehicles 1	bicycle, bus, motorcycle, pickup truck, train
vehicles 2	lawn-mower, rocket, streetcar, tank, tractor

4、imagenet

大规模视觉识别挑战的识别任务之一便是对 1000 类、120 万张互联网图像进行分类。

物体检测是视觉挑战中最难的任务，它要求从四万张图像中准确检测到 200 类物体的具体位置，并且一幅图像往往包含多个不同类别的物体。

二、研究深度学习的库和软件

http://deeplearning.net/software_links/