caffe初探之-caffe使用CIFAR-10数据集训练网络

文章示例来自caffe官网http://caffe.berkeleyvision.org/gathered/examples/cifar10.html

The CIFAR-10 dataset

The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

1. 获取数据

cd caffe./data/cifar10/get_cifar10.sh

2. 创建两个数据集cifar10_train_lmdb和cifar10_test_lmdb

cd caffe./examples/cifar10/create_cifar10.sh 

3. 训练和测试数据

里面有两个训练模型‘’full‘’和‘’quick‘’

这里训练''full''模型

cd caffe./examples/cifar10/train_full.sh

开始训练