caffe 学习笔记-模型训练与测试

以LeNet 手写字体识别为例,首先进入caffe安装目录,并下载手写字体训练数据:

cd $CAFFE_ROOT
sudo ./data/mnist/get_mnist.sh

将图片转换成lmdb文件:

sudo ./examples/mnist/create_mnist.sh

运行后得到 mnist_train_lmdb和mnist_test_lmdb.

/examples/mnist/lenet_solver.prototxt文件定义了训练参数,模型文件net,迭代次数max_iter,学习率base_lr等,solver_mode配置是否使用GPU:

# The train/test net protocol buffer definition
net: "examples/mnist/lenet_train_test.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 100
# Carry out testing every 500 training iterations.
test_interval: 500
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.01
momentum: 0.9
weight_decay: 0.0005
# The learning rate policy
lr_policy: "inv"
gamma: 0.0001
power: 0.75
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 10000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "examples/mnist/lenet"
# solver mode: CPU or GPU
solver_mode: GPU

训练:

sudo ./examples/mnist/train_lenet.sh

也可以直接执行训练命令:

./build/tools/caffe train –solver=examples/mnist/lenet_solver.prototxt

caffe输入参数train表示训练.

训练结果:



学习率更新,可以通过lr_policy: “multistep”实现,例如要实现在step值分别为 5000,7000,8000,9000,9500时,按照decay=0.9更新学习率,可以修改solver.ptototxt文件如下:

# The train/test net protocol buffer definition
net: "examples/mnist/lenet_train_test.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 100
# Carry out testing every 500 training iterations.
test_interval: 500
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.01
momentum: 0.9
weight_decay: 0.0005
# The learning rate policy
lr_policy: "multistep"
gamma: 0.9
stepvalue: 5000
stepvalue: 7000
stepvalue: 8000
stepvalue: 9000
stepvalue: 9500
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 10000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "examples/mnist/lenet_multistep"
# solver mode: CPU or GPU
solver_mode: GPU