Deep learning datasets + model Descriptions

1, Mnist

Corinna Cortes of Google Labs and a handwritten digital database built by Yann LeCun of the Crown Institute of New York University, the training library has 60,000 handwritten digital images and 10,000 test libraries. The corresponding handwriting recognition model is lenet.

Data address: http://yann.lecun.com/exdb/mnist/

2, Cifar10

A data set for universal object recognition, collected by Hinton's two great disciples Alex Krizhevsky, Ilya Sutskever. Cifar is an advanced Science project Research Institute that led the investment in Canada.

The CIFAR-10 dataset contains 60,000 32*32 color images, a total of 10 categories. There are 50,000 training images and 10,000 test images. The dataset is divided into 5 training blocks and a test block with 10,000 images per block. The test block contains 1000 images randomly selected from each class. The training blocks contain these images in a random order, but some training blocks may contain more images than other classes. Training blocks Each class contains 5,000 images. Completely mutually exclusive between classes. The biggest feature of this data set is the migration of recognition to ubiquitous objects, and it is applied to multiple classifications (the sister dataset Cifar-100 reaches 100 classes, and the ILSVRC game is 1000 classes). Compared with the mature face recognition, pervasive object recognition is a huge challenge, and the data contains a large number of features, noises, and different proportions of the object of recognition, and the classification is huge.

3, cifar100

The dataset contains 100 small classes, each of which contains 600 images, with 500 training images and 100 test images. Class 100 is grouped into 20 large classes. Each image has 1 small class "fine" labels and 1 large class "coarse" labels.

4, ImageNet

ImageNet is a computer vision system recognition project that is currently the largest database in the world like recognition. In 2010, scientists from Stanford University, Princeton University and Columbia University launched the ImageNet Mass Visual Identification Challenge (ImageNet Large Scale visual recognition CHALLENGE,ILSVRC). ILSVRC2012 was the 2012 game data set, and in the contest, Alex's ALEXNET network structure model won the championship, and ILSVRC2014 was the 2014 match data set, in which Googlenet,vggnet was crowned runner-up.

Deep learning datasets + model Descriptions