mnist测试

第一步：进入caffe目录

第二步：获取mnist数据集

./data/mnist/get_mnist.sh

第三步：创建lmdb

./examples/mnist/create_mnist.sh

第四步：训练

./examples/mnist/train_lenet.sh

运行完结果如下：

生成四个文件

lenet_iter_10000.caffemodel

lenet_iter_10000.solverstate    
 
lenet_iter_5000.caffemodel    
    
lenet_iter_5000.solverstate

屏幕显示：

I0918 14:43:05.602397  8647 solver.cpp:317] Iteration 10000, loss = 0.00291481
I0918 14:43:05.602445  8647 solver.cpp:337] Iteration 10000, Testing net (#0)
I0918 14:43:11.950065  8647 solver.cpp:404]     Test net output #0: accuracy = 0.9904
I0918 14:43:11.950124  8647 solver.cpp:404]     Test net output #1: loss = 0.0309935 (* 1 = 0.0309935 loss)
I0918 14:43:11.950135  8647 solver.cpp:322] Optimization Done.
I0918 14:43:11.950142  8647 caffe.cpp:254] Optimization Done.