hans

hans

【Python】【Caffe】一、生成prototxt文件《python调用caffe模块》


GitHub 代码地址: https://github.com/HansRen1024/Use-Python-to-call-Caffe-module

前言#

写这一系列博文前真的想了好久,有种无从下手的感觉。还是功力太浅,越是这样越要硬着头皮写。加油!

我先将将各个函数单独放出来,最后在放出完整代码。各个函数中单独用到的模块,我在函数中单独加载,这样方便将代码独立出来单独运行。

import caffe 是全局通用模块,我就不在每个函数中单独加载了。

一、加载 caffe 模块#

为了以后方便使用,把 caffe 模块放到 python 默认路径下,这样在任意目录下就都能加载 caffe 模块了。

caffe 编译通过后运行:

make pycaffe
sudo cp -r python/caffe/ /usr/local/lib/python/dist-packages #有些朋友路径是site-packages,这个因人而异。

这个时候运行 python,import caffe,会提示找不到 caffe 的动态库。

可以将 $CAFFE_ROOT/.build_release/lib/ 加到环境变量中去,

也可以将该动态库复制到 /usr/lib/ 或者 /usr/local/lib 目录下。

此时,应该就可以在任意目录下运行 python,import caffe 了。

二、生成训练和测试 prototxt 文件#

生成网络结构文件我找到了两种方法,下面这种通过定义一个 NetSpec () 实例 n 的方法是比较好的,所以我先写的这个方法。这种方法生成的文件内,各个层的名字和输出 blob 的名字就是等号前面定义的 n 的方法。

def lenet(lmdb, batch_size, include_acc=False):
    from caffe import layers as L
    from caffe import params as P
    n = caffe.NetSpec()
    # 具体每个层内的参数,可以对照现有的prototxt文件。我这里写的并不全。
    n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb,
                             transform_param=dict(scale=1./255), ntop=2)              # ntop表示两个输出
    n.conv1 = L.Convolution(n.data, kernel_size=5, num_output=20, weight_filler=dict(type='xavier'))
    n.pool1 = L.Pooling(n.conv1, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    n.conv2 = L.Convolution(n.pool1, kernel_size=5, num_output=50, weight_filler=dict(type='xavier'))
    n.pool2 = L.Pooling(n.conv2, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    n.ip1 = L.InnerProduct(n.pool2, num_output=500, weight_filler=dict(type='xavier'))
    n.relu1 = L.ReLU(n.ip1, in_place=True)
    n.ip2 = L.InnerProduct(n.relu1, num_output=10, weight_filler=dict(type='xavier'))
    n.loss = L.SoftmaxWithLoss(n.ip2, n.label)
    if include_acc: # 生成测试文件时,需要有计算准确率的层。
        n.acc = L.Accuracy(n.ip2, n.label)
    return n.to_proto() # 注意这里的to_proto()不用带参数。

def write_lenet():
    with open('./doc/train_lenet.prototxt','w') as f:
        f.write(str(lenet('./doc/mnist_train_lmdb', 64)))
    
    with open('./doc/test_lenet.prototxt', 'w') as f:
        f.write(str(lenet('./doc/mnist_test_lmdb', 100, True)))

三、生成 deploy 文件#

这里我放出生成网络结构文件的第二种方法,虽然我并不推荐使用这个方法。其实 deploy 直接拿上面生成好的文件改就行,很简单。

def deploy():
    from caffe import layers as L
    from caffe import params as P
    from caffe import to_proto
    # deploy文件没有数据层
    conv1 = L.Convolution(bottom='data', kernel_size=5, num_output=20, weight_filler=dict(type='xavier'))
    pool1 = L.Pooling(conv1, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    conv2 = L.Convolution(pool1, kernel_size=5, num_output=50, weight_filler=dict(type='xavier'))
    pool2 = L.Pooling(conv2, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    ip1 = L.InnerProduct(pool2, num_output=500, weight_filler=dict(type='xavier'))
    relu1 = L.ReLU(ip1, in_place=True)
    ip2 = L.InnerProduct(relu1, num_output=10, weight_filler=dict(type='xavier')) 
    prob = L.Softmax(ip2) # 最后一层不用计算loss,输出概率。
    return to_proto(prob) # 这里需要带参数

def write_deploy():
    with open('doc/deploy_lenet.prototxt', 'w') as f:
        f.write('name: "Lenet"\n')
        f.write('input: "data"\n')
        f.write('input_dim: 1\n')
        f.write('input_dim: 3\n')
        f.write('input_dim: 28\n')
        f.write('input_dim: 28\n')
        f.write(str(deploy()))

四、生成 solver 文件#

方法一是用字典生成:

def solver_dict():
    solver_file='doc/solver_lenet.prototxt'
    sp={}
    sp['train_net']='"doc/train_lenet.prototxt"'
    sp['test_net']='"doc/test_lenet.prototxt"'
    sp['test_iter']='100'
    sp['test_interval']='500'
    sp['display']='100'
    sp['max_iter']='10000'
    sp['base_lr']='0.01'
    sp['lr_policy']='"inv"'
    sp['gamma']='0.0001'
    sp['power']='0.75'
    sp['momentum']='0.9'
    sp['weight_decay']='0.0005'
    sp['snapshot']='5000'
    sp['snapshot_prefix']='"models/lenet"'
    sp['solver_mode']='GPU'
    sp['solver_type']='SGD'
    sp['device_id']='0'
    
    with open(solver_file, 'w') as f:
        for key, value in sp.items():
            if not(type(value) is str):
                raise TypeError('All solver parameters must be string')
            f.write('%s: %s\n' %(key, value))

方法二是调用 caffe 模块生成,这种方法生成的文件内,小数部分会有很小的损失。处女座强迫症犯了!

def solver_caffe():
    from caffe.proto import caffe_pb2
    s = caffe_pb2.SolverParameter()
    solver_file='doc/solver_lenet.prototxt'
    
    s.train_net = 'doc/train_lenet.prototxt'
    s.test_net.append('doc/test_lenet.prototxt')
    s.test_interval = 500
    s.test_iter.append(100)
    s.display = 100
    s.max_iter = 10000
    s.base_lr = 0.01
    s.lr_policy = "inv"
    s.gamma = 0.0001
    s.power = 0.75
    s.momentum = 0.9
    s.weight_decay = 0.0005
    s.snapshot = 5000
    s.snapshot_prefix = "models/lenet"
    s.type = "SGD"
    s.solver_mode = caffe_pb2.SolverParameter.GPU
    
    with open(solver_file, 'w') as f:
        f.write(str(s))

五、完整代码:#

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Sat Jul 29 11:16:29 2017

@author: hans
"""

import caffe

def lenet(lmdb, batch_size, include_acc=False):
    from caffe import layers as L
    from caffe import params as P

    n = caffe.NetSpec()
    n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb,
                             transform_param=dict(scale=1./255), ntop=2)
    n.conv1 = L.Convolution(n.data, kernel_size=5, num_output=20, weight_filler=dict(type='xavier'))
    n.pool1 = L.Pooling(n.conv1, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    n.conv2 = L.Convolution(n.pool1, kernel_size=5, num_output=50, weight_filler=dict(type='xavier'))
    n.pool2 = L.Pooling(n.conv2, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    n.ip1 = L.InnerProduct(n.pool2, num_output=500, weight_filler=dict(type='xavier'))
    n.relu1 = L.ReLU(n.ip1, in_place=True)
    n.ip2 = L.InnerProduct(n.relu1, num_output=10, weight_filler=dict(type='xavier'))
    n.loss = L.SoftmaxWithLoss(n.ip2, n.label)
    if include_acc:
        n.acc = L.Accuracy(n.ip2, n.label)
    return n.to_proto()

def write_lenet():
    with open('./doc/train_lenet.prototxt','w') as f:
        f.write(str(lenet('./doc/mnist_train_lmdb', 64)))
    
    with open('./doc/test_lenet.prototxt', 'w') as f:
        f.write(str(lenet('./doc/mnist_test_lmdb', 100, True)))

def deploy():
    from caffe import layers as L
    from caffe import params as P
    from caffe import to_proto

    conv1 = L.Convolution(bottom='data', kernel_size=5, num_output=20, weight_filler=dict(type='xavier'))
    pool1 = L.Pooling(conv1, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    conv2 = L.Convolution(pool1, kernel_size=5, num_output=50, weight_filler=dict(type='xavier'))
    pool2 = L.Pooling(conv2, kernel_size=2, stride=2, pool=P.Pooling.MAX)
    ip1 = L.InnerProduct(pool2, num_output=500, weight_filler=dict(type='xavier'))
    relu1 = L.ReLU(ip1, in_place=True)
    ip2 = L.InnerProduct(relu1, num_output=10, weight_filler=dict(type='xavier'))
    prob = L.Softmax(ip2)
    return to_proto(prob)

def write_deploy():
    with open('doc/deploy_lenet.prototxt', 'w') as f:
        f.write('name: "Lenet"\n')
        f.write('input: "data"\n')
        f.write('input_dim: 1\n')
        f.write('input_dim: 3\n')
        f.write('input_dim: 28\n')
        f.write('input_dim: 28\n')
        f.write(str(deploy()))
    
def solver_dict():
    solver_file='doc/solver_lenet.prototxt'
    sp={}
    sp['train_net']='"doc/train_lenet.prototxt"'
    sp['test_net']='"doc/test_lenet.prototxt"'
    sp['test_iter']='100'
    sp['test_interval']='500'
    sp['display']='100'
    sp['max_iter']='10000'
    sp['base_lr']='0.01'
    sp['lr_policy']='"inv"'
    sp['gamma']='0.0001'
    sp['power']='0.75'
    sp['momentum']='0.9'
    sp['weight_decay']='0.0005'
    sp['snapshot']='5000'
    sp['snapshot_prefix']='"models/lenet"'
    sp['solver_mode']='GPU'
    sp['solver_type']='SGD'
    sp['device_id']='0'
    
    with open(solver_file, 'w') as f:
        for key, value in sp.items():
            if not(type(value) is str):
                raise TypeError('All solver parameters must be string')
            f.write('%s: %s\n' %(key, value))
            
def solver_caffe():
    from caffe.proto import caffe_pb2

    s = caffe_pb2.SolverParameter()
    solver_file='doc/solver_lenet.prototxt'
    
    s.train_net = 'doc/train_lenet.prototxt'
    s.test_net.append('doc/test_lenet.prototxt')
    s.test_interval = 500
    s.test_iter.append(100)
    s.display = 100
    s.max_iter = 10000
    s.base_lr = 0.01
    s.lr_policy = "inv"
    s.gamma = 0.0001
    s.power = 0.75
    s.momentum = 0.9
    s.weight_decay = 0.0005
    s.snapshot = 5000
    s.snapshot_prefix = "models/lenet"
    s.type = "SGD"
    s.solver_mode = caffe_pb2.SolverParameter.GPU
    
    with open(solver_file, 'w') as f:
        f.write(str(s))

def train():
    caffe.set_device(0)
    caffe.set_mode_gpu()
    solver = caffe.SGDSolver('doc/solver_lenet.prototxt')
    solver.solve()

if __name__ == '__main__':
    write_lenet()
#    write_deploy()
#    solver_dict()
#    solver_caffe()
#    train()
加载中...
此文章数据所有权由区块链加密技术和智能合约保障仅归创作者所有。