Caffe学习笔记(四)：使用pycaffe生成train.prototxt、test.prototxt文件
转载请注明作者和出处：http://blog.csdn.net/c406495762
Python版本： Python2.7
运行平台： Ubuntu14.04
一、前言
了解到上一篇笔记的内容，就可以尝试自己编写python程序生成prototxt文件了，当然也可以直接创建文件进行编写，不过显然，使用python生成这个配置文件更为简洁。之前已说过cifar10是使用cifar10_quick_solver.prototxt配置文件来生成model。cifar10_quick_solver.prototxt的内容如下：
# reduce the learning rate after 8 epochs (4000 iters) by a factor of 10
# The train/test net protocol buffer definition
net: "examples/cifar10/cifar10_quick_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: 0.001
momentum: 0.9
weight_decay: 0.004
# The learning rate policy
lr_policy: "fixed"
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 4000
# snapshot intermediate results
snapshot: 4000
snapshot_format: HDF5
snapshot_prefix: "examples/cifar10/cifar10_quick"
# solver mode: CPU or GPU
solver_mode: GPU从以上代码中可以看出，第四行的net参数，指定了训练时使用的prototxt文件。这个prototxt文件也是可以分开写的，分为train.prototxt和test.prototxt。例如，第四行的配置可以改写为：
train_net = "examples/cifar10/cifar10_quick_train.prototxt"
test_net = "examples/cifar10/cifar10_quick_test.prototxt"二、Pycaffe API小试
solver.prototxt文件如何生成，在后续的笔记中讲解，先学习如何使用python生成简单的train.prtotxt文件和test.prototxt文件。
1.Data Layer：
# -*- coding: UTF-8 -*-
import caffe #导入caffe包
caffe_root = "/home/Jack-Cui/caffe-master/my-caffe-project/" #my-caffe-project目录
train_lmdb = caffe_root + "img_train.lmdb" #train.lmdb文件的位置
mean_file = caffe_root + "mean.binaryproto" #均值文件的位置
#网络规范
net = caffe.NetSpec()
#第一层Data层
net.data, net.label = caffe.layers.Data(source = train_lmdb, backend = caffe.params.Data.LMDB, batch_size = 64, ntop=2,
transform_param = dict(crop_size = 40,mean_file = mean_file,mirror = True))
print str(net.to_proto())运行结果：
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
transform_param {
mirror: true
crop_size: 40
mean_file: "/home/Jack-Cui/caffe-master/my-caffe-project/mean.binaryproto"
}
data_param {
source: "/home/Jack-Cui/caffe-master/my-caffe-project/img_train.lmdb"
batch_size: 64
backend: LMDB
}
}
2.Convolution Layer：
添加卷积层：
# -*- coding: UTF-8 -*-
import caffe #导入caffe包
caffe_root = "/home/Jack-Cui/caffe-master/my-caffe-project/" #my-caffe-project目录
train_lmdb = caffe_root + "img_train.lmdb" #train.lmdb文件的位置
mean_file = caffe_root + "mean.binaryproto" #均值文件的位置
#网络规范
net = caffe.NetSpec()
#第一层Data层
net.data, net.label = caffe.layers.Data(source = train_lmdb, backend = caffe.params.Data.LMDB, batch_size = 64, ntop=2,
transform_param = dict(crop_size = 40,mean_file = mean_file,mirror = True))
#第二层Convolution层
net.conv1 = caffe.layers.Convolution(net.data, num_output=20, kernel_size=5,weight_filler={"type": "xavier"},
bias_filler={"type": "constant"})
print str(net.to_proto())
运行结果：
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
transform_param {
mirror: true
crop_size: 40
mean_file: "/home/Jack-Cui/caffe-master/my-caffe-project/mean.binaryproto"
}
data_param {
source: "/home/Jack-Cui/caffe-master/my-caffe-project/img_train.lmdb"
batch_size: 64
backend: LMDB
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
convolution_param {
num_output: 20
kernel_size: 5
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
}
}
}
3.ReLU Layer：
添加ReLu激活层：
# -*- coding: UTF-8 -*-
import caffe #导入caffe包
caffe_root = "/home/Jack-Cui/caffe-master/my-caffe-project/" #my-caffe-project目录
train_lmdb = caffe_root + "img_train.lmdb" #train.lmdb文件的位置
mean_file = caffe_root + "mean.binaryproto" #均值文件的位置
#网络规范
net = caffe.NetSpec()
#第一层Data层
net.data, net.label = caffe.layers.Data(source = train_lmdb, backend = caffe.params.Data.LMDB, batch_size = 64, ntop=2,
transform_param = dict(crop_size = 40,mean_file = mean_file,mirror = True))
#第二层Convolution视觉层
net.conv1 = caffe.layers.Convolution(net.data, num_output=20, kernel_size=5,weight_filler={"type": "xavier"},
bias_filler={"type": "constant"})
#第三层ReLU激活层
net.relu1 = caffe.layers.ReLU(net.conv1, in_place=True)
print str(net.to_proto())
运行结果：
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
transform_param {
mirror: true
crop_size: 40
mean_file: "/home/Jack-Cui/caffe-master/my-caffe-project/mean.binaryproto"
}
data_param {
source: "/home/Jack-Cui/caffe-master/my-caffe-project/img_train.lmdb"
batch_size: 64
backend: LMDB
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
convolution_param {
num_output: 20
kernel_size: 5
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
4.类似的继续添加池化层、全连层、dropout层、softmax层等。
# -*- coding: UTF-8 -*-
import caffe #导入caffe包
caffe_root = "/home/Jack-Cui/caffe-master/my-caffe-project/" #my-caffe-project目录
train_lmdb = caffe_root + "img_train.lmdb" #train.lmdb文件的位置
mean_file = caffe_root + "mean.binaryproto" #均值文件的位置
#网络规范
net = caffe.NetSpec()
#第一层Data层
net.data, net.label = caffe.layers.Data(source = train_lmdb, backend = caffe.params.Data.LMDB, batch_size = 64, ntop=2,
transform_param = dict(crop_size = 40,mean_file = mean_file,mirror = True))
#第二层Convolution视觉层
net.conv1 = caffe.layers.Convolution(net.data, num_output=20, kernel_size=5,weight_filler={"type": "xavier"},
bias_filler={"type": "constant"})
#第三层ReLU激活层
net.relu1 = caffe.layers.ReLU(net.conv1, in_place=True)
#第四层Pooling池化层
net.pool1 = caffe.layers.Pooling(net.relu1, pool=caffe.params.Pooling.MAX, kernel_size=3, stride=2)
net.conv2 = caffe.layers.Convolution(net.pool1, kernel_size=3, stride=1,num_output=32, pad=1,weight_filler=dict(type='xavier'))
net.relu2 = caffe.layers.ReLU(net.conv2, in_place=True)
net.pool2 = caffe.layers.Pooling(net.relu2, pool=caffe.params.Pooling.MAX, kernel_size=3, stride=2)
#全连层
net.fc3 = caffe.layers.InnerProduct(net.pool2, num_output=1024,weight_filler=dict(type='xavier'))
net.relu3 = caffe.layers.ReLU(net.fc3, in_place=True)
#创建一个dropout层
net.drop3 = caffe.layers.Dropout(net.relu3, in_place=True)
net.fc4 = caffe.layers.InnerProduct(net.drop3, num_output=10,weight_filler=dict(type='xavier'))
#创建一个softmax层
net.loss = caffe.layers.SoftmaxWithLoss(net.fc4, net.label)
print str(net.to_proto())
运行结果：
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
transform_param {
mirror: true
crop_size: 40
mean_file: "/home/Jack-Cui/caffe-master/my-caffe-project/mean.binaryproto"
}
data_param {
source: "/home/Jack-Cui/caffe-master/my-caffe-project/img_train.lmdb"
batch_size: 64
backend: LMDB
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
convolution_param {
num_output: 20
kernel_size: 5
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
convolution_param {
num_output: 32
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc3"
type: "InnerProduct"
bottom: "pool2"
top: "fc3"
inner_product_param {
num_output: 1024
weight_filler {
type: "xavier"
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "fc3"
top: "fc3"
}
layer {
name: "drop3"
type: "Dropout"
bottom: "fc3"
top: "fc3"
}
layer {
name: "fc4"
type: "InnerProduct"
bottom: "fc3"
top: "fc4"
inner_product_param {
num_output: 10
weight_filler {
type: "xavier"
}
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc4"
bottom: "label"
top: "loss"
}
三、生成并保存训练需要使用的train.prototxt和test.protxt文件
1.编写代码如下：
# -*- coding: UTF-8 -*-
import caffe #导入caffe包
def create_net(lmdb, mean_file, batch_size, include_acc=False):
#网络规范
net = caffe.NetSpec()
#第一层Data层
net.data, net.label = caffe.layers.Data(source=lmdb, backend=caffe.params.Data.LMDB, batch_size=batch_size, ntop=2,
transform_param = dict(crop_size = 40, mean_file=mean_file, mirror=True))
#第二层Convolution视觉层
net.conv1 = caffe.layers.Convolution(net.data, num_output=20, kernel_size=5,weight_filler={"type": "xavier"},
bias_filler={"type": "constant"})
#第三层ReLU激活层
net.relu1 = caffe.layers.ReLU(net.conv1, in_place=True)
#第四层Pooling池化层
net.pool1 = caffe.layers.Pooling(net.relu1, pool=caffe.params.Pooling.MAX, kernel_size=3, stride=2)
net.conv2 = caffe.layers.Convolution(net.pool1, kernel_size=3, stride=1,num_output=32, pad=1,weight_filler=dict(type='xavier'))
net.relu2 = caffe.layers.ReLU(net.conv2, in_place=True)
net.pool2 = caffe.layers.Pooling(net.relu2, pool=caffe.params.Pooling.MAX, kernel_size=3, stride=2)
#全连层
net.fc3 = caffe.layers.InnerProduct(net.pool2, num_output=1024,weight_filler=dict(type='xavier'))
net.relu3 = caffe.layers.ReLU(net.fc3, in_place=True)
#创建一个dropout层
net.drop3 = caffe.layers.Dropout(net.relu3, in_place=True)
net.fc4 = caffe.layers.InnerProduct(net.drop3, num_output=10,weight_filler=dict(type='xavier'))
#创建一个softmax层
net.loss = caffe.layers.SoftmaxWithLoss(net.fc4, net.label)
#训练的prototxt文件不包括Accuracy层,测试的时候需要。
if include_acc:
net.acc = caffe.layers.Accuracy(net.fc4, net.label)
return str(net.to_proto())
return str(net.to_proto())
def write_net():
caffe_root = "/home/Jack-Cui/caffe-master/my-caffe-project/" #my-caffe-project目录
train_lmdb = caffe_root + "train.lmdb" #train.lmdb文件的位置
test_lmdb = caffe_root + "test.lmdb" #test.lmdb文件的位置
mean_file = caffe_root + "mean.binaryproto" #均值文件的位置
train_proto = caffe_root + "train.prototxt" #保存train_prototxt文件的位置
test_proto = caffe_root + "test.prototxt" #保存test_prototxt文件的位置
#写入prototxt文件
with open(train_proto, 'w') as f:
f.write(str(create_net(train_lmdb, mean_file, batch_size=64)))
#写入prototxt文件
with open(test_proto, 'w') as f:
f.write(str(create_net(test_lmdb, mean_file, batch_size=32, include_acc=True)))
if __name__ == '__main__':
write_net()
2.运行结果：
3.总结
现在已经学会了如何生成训练使用的train.prototxt、test.prototxt文件。后续将将继续讲解如何生成solver.prototxt文件。