GitHub 代碼地址： https://github.com/HansRen1024/Use-Python-to-call-Caffe-module
前言#
寫這一系列博文前真的想了好久，有種無從下手的感覺。還是功力太淺，越是這樣越要硬著頭皮寫。加油！
我先將各個函數單獨放出來，最後再放出完整代碼。各個函數中單獨用到的模塊，我在函數中單獨加載，這樣方便將代碼獨立出來單獨運行。
import caffe 是全局通用模塊，我就不在每個函數中單獨加載了。
一、加載 caffe 模塊#
為了以後方便使用，把 caffe 模塊放到 python 默認路徑下，這樣在任意目錄下就都能加載 caffe 模塊了。
caffe 編譯通過後運行：
make pycaffe
sudo cp -r python/caffe/ /usr/local/lib/python/dist-packages #有些朋友路徑是site-packages,這個因人而異。
這個時候運行 python，import caffe，會提示找不到 caffe 的動態庫。
可以將 $CAFFE_ROOT/.build_release/lib/ 加到環境變量中去，
也可以將該動態庫複製到 /usr/lib/ 或者 /usr/local/lib 目錄下。
此時，應該就可以在任意目錄下運行 python，import caffe 了。
二、生成訓練和測試 prototxt 文件#
生成網絡結構文件我找到了兩種方法，下面這種通過定義一個 NetSpec () 實例 n 的方法是比較好的，所以我先寫的這個方法。這種方法生成的文件內，各個層的名字和輸出 blob 的名字就是等號前面定義的 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()
# 具體每個層內的參數，可以對照現有的prototxt文件。我這裡寫的並不全。
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表示兩個輸出
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: # 生成測試文件時，需要有計算準確率的層。
n.acc = L.Accuracy(n.ip2, n.label)
return n.to_proto() # 注意這裡的to_proto()不用帶參數。
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#
這裡我放出生成網絡結構文件的第二種方法，雖然我並不推薦使用這個方法。其實 deploy 直接拿上面生成好的文件改就行，很簡單。
def deploy():
from caffe import layers as L
from caffe import params as P
from caffe import to_proto
# deploy文件沒有數據層
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) # 最後一層不用計算loss，輸出概率。
return to_proto(prob) # 這裡需要帶參數
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))
方法二是調用 caffe 模塊生成，這種方法生成的文件內，小數部分會有很小的損失。處女座強迫症犯了！
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、完整代碼：#
#!/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()