caffe下python网络创建

１）　载入模块

import matplotlib.pyplot as plt
from pylab import *
# %matplotlib inline
caffe_root = '/home/cc/caffe-master/examples/'  # this file should be run from {caffe_root}/examples (otherwise change this line)

import sys
# sys.path.insert(0, caffe_root + 'python')
# sys.path.insert(0, caffe_root + 'examples')
# sys.path.insert(0, caffe_root)
import caffe

#  网络结构:需要两个文件：
# lenet.prototxt:定义结构，指明训练,测试数据的维度
# solver.prototxt:定义参数
from caffe import layers as L, params as P

2) 定义网络

def lenet(lmdb, batch_size):
    # our version of LeNet: a series of linear and simple nonlinear transformations
    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.fc1 = L.InnerProduct(n.pool2, num_output=500, weight_filler=dict(type='xavier'))
    n.relu1 = L.ReLU(n.fc1, in_place=True)
    n.score = L.InnerProduct(n.relu1, num_output=10, weight_filler=dict(type='xavier'))
    n.loss = L.SoftmaxWithLoss(n.score, n.label)

    return n.to_proto()

with open(caffe_root+'mnist/lenet_auto_train.prototxt', 'w') as f:
    f.write(str(lenet(caffe_root+'mnist/mnist_train_lmdb', 64)))

with open(caffe_root+'mnist/lenet_auto_test.prototxt', 'w') as f:
    f.write(str(lenet(caffe_root+'mnist/mnist_test_lmdb', 100)))

３) 定义求解器

# caffe.set_device(0)
# caffe.set_mode_gpu()
caffe.set_mode_cpu()

### load the solver and create train and test nets
solver = None  # ignore this workaround for lmdb data (can't instantiate two solvers on the same data)
solver = caffe.SGDSolver(caffe_root+'mnist/lenet_auto_solver.prototxt')　　#默认SGD方法

４）　中间结果输出

# each output is (batch size, feature dim, spatial dim)
# [(k, v.data.shape) for k, v in solver.net.blobs.items()]

for k, v in solver.net.blobs.items():
    print k, v.data.shape

# just print the weight sizes (we'll omit the biases)
for k, v in solver.net.params.items():
    print '(k,v)', (k, v[0].data.shape)

solver.net.forward()  # train net
solver.test_nets[0].forward()  # test net (there can be more than one)　＃输出最后一层loss
# {'loss': array(2.3258860111236572, dtype=float32)}
# we use a little trick to tile the first eight images
# reshape按照行排列：[1 2 3 5]-->[[1 2],[3, 5]], 将图片(28,28,8)个按照一行排列(28,8*28)
plt.imshow(solver.net.blobs['data'].data[:8, 0].transpose(1, 0, 2).reshape(28, 8*28), cmap='gray'); axis('off')
# plt.show()
print 'train labels:', solver.net.blobs['label'].data[:8]


imshow(solver.test_nets[0].blobs['data'].data[:8, 0].transpose(1, 0, 2).reshape(28, 8*28), cmap='gray'); axis('off')
plt.show()
print 'test labels:', solver.test_nets[0].blobs['label'].data[:8]

# take one step of SGD
solver.step(1)
# 将２０张图片按照４行５列排列
plt.imshow(solver.net.params['conv1'][0].diff[:, 0].reshape(4, 5, 5, 5)
       .transpose(0, 2, 1, 3).reshape(4*5, 5*5), cmap='gray'); axis('off')
plt.show()

５）定义迭代次数，选取结果输出

#% % time
niter = 200
test_interval = 25
# losses will also be stored in the log
train_loss = zeros(niter)
test_acc = zeros(int(np.ceil(niter / test_interval)))　＃每隔多少次测试一次
output = zeros((niter, 8, 10))　＃保存８个样本输出结果

# the main solver loop
for it in range(niter):
    solver.step(1)  # SGD by Caffe

    # store the train loss
    train_loss[it] = solver.net.blobs['loss'].data

    # store the output on the first test batch
    # (start the forward pass at conv1 to avoid loading new data)
    solver.test_nets[0].forward(start='conv1')  #
    output[it] = solver.test_nets[0].blobs['score'].data[:8]#提取前８个输出(8,10)　#(64,10)

    # run a full test every so often
    # (Caffe can also do this for us and write to a log, but we show here
    #  how to do it directly in Python, where more complicated things are easier.)
    if it % test_interval == 0:
        print 'Iteration', it, 'testing...'
        correct = 0
        for test_it in range(100):
            solver.test_nets[0].forward()
            correct += sum(solver.test_nets[0].blobs['score'].data.argmax(1)
                           == solver.test_nets[0].blobs['label'].data)
        test_acc[it // test_interval] = correct / 1e4



# plot the train loss and test accuracy
plt.figure()
ax1 = subplot()
ax2 = ax1.twinx()
ax1.plot(arange(niter), train_loss)
ax2.plot(test_interval * arange(len(test_acc)), test_acc, 'r')
ax1.set_xlabel('iteration')
ax1.set_ylabel('train loss')
ax2.set_ylabel('test accuracy')
ax2.set_title('Test Accuracy: {:.2f}'.format(test_acc[-1]))
plt.show()


for i in range(8):
    figure(figsize=(2, 2))
    plt.imshow(solver.test_nets[0].blobs['data'].data[i, 0], cmap='gray')
    figure(figsize=(10, 2))
    plt.imshow(output[:50, i].T, interpolation='nearest', cmap='gray')
    plt.show()
    xlabel('iteration')
    ylabel('label')



for i in range(8):
    figure(figsize=(2, 2))
    imshow(solver.test_nets[0].blobs['data'].data[i, 0], cmap='gray')
    figure(figsize=(10, 2))
    imshow(exp(output[:50, i].T) / exp(output[:50, i].T).sum(0), interpolation='nearest', cmap='gray')
    plt.show()
    xlabel('iteration')
    ylabel('label')

６）按照上文创建自己的网络：

path_examples = '/home/cc/caffe-master/examples/'
train_net_path = path_examples + 'mnist/custom_auto_train.prototxt'
test_net_path = path_examples + 'mnist/custom_auto_test.prototxt'
solver_config_path = path_examples + 'mnist/custom_auto_solver.prototxt'
### define net
def custom_net(lmdb, batch_size):
    # define your own net!
    n = caffe.NetSpec()
    # keep this data layer for all networks
    n.data1, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb,
                             transform_param=dict(scale=1. / 255), ntop=2)

　　# 结果输出：
　　　layer {
  name: "data"
  type: "Data"
  top: "data1"
  top: "label"
  transform_param {
    scale: 0.00392156885937
  }
  data_param {
    source: "/home/cc/caffe-master/examples/mnist/mnist_train_lmdb"
    batch_size: 64
    backend: LMDB
  }
 　　#　n.data定义了name和top,    L.Data定义了layer和type, data_param, ntop数目：n.data, n.label
    # EDIT HERE to try different networks
    # this single layer defines a simple linear classifier
    # (in particular this defines a multiway logistic regression)
    # n.score = L.InnerProduct(n.data1, num_output=10, weight_filler=dict(type='xavier'))
    # n.score定义了name和top, L.InnerProduct定义了type和inner_product_param. n.data输入数定义了bottom的数目

 # EDIT HERE this is the LeNet variant we have already tried
    n.conv1 = L.Convolution(n.data1, 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.fc1 =   L.InnerProduct(n.pool2, num_output=500, weight_filler=dict(type='xavier'))
    # EDIT HERE consider L.ELU or L.Sigmoid for the nonlinearity
    n.relu1 = L.ReLU(n.fc1, in_place=True)
    n.score =   L.InnerProduct(n.fc1, num_output=10, weight_filler=dict(type='xavier'))
    #
    # # keep this loss layer for all networks
    n.loss = L.SoftmaxWithLoss(n.score, n.label)

    return n.to_proto()
    #调用函数进行初始化


with open(train_net_path, 'w') as f:
    f.write(str(custom_net(path_examples + 'mnist/mnist_train_lmdb', 64)))
with open(test_net_path, 'w') as f:
    f.write(str(custom_net(path_examples + 'mnist/mnist_test_lmdb', 100)))

### define solver
from caffe.proto import caffe_pb2

s = caffe_pb2.SolverParameter()

# Set a seed for reproducible experiments:
# this controls for randomization in training.
s.random_seed = 0xCAFFE

# Specify locations of the train and (maybe) test networks.
s.train_net = train_net_path #定义训练.prototxt文件所在路径
s.test_net.append(test_net_path)
s.test_interval = 500  # Test after every 500 training iterations.
s.test_iter.append(100)  # Test on 100 batches each time we test.　每次100个样本测试

s.max_iter = 10000  # no. of times to update the net (training iterations)

# EDIT HERE to try different solvers
# solver types include "SGD", "Adam", and "Nesterov" among others.
s.type = "SGD"

# Set the initial learning rate for SGD.
s.base_lr = 0.01  # EDIT HERE to try different learning rates
# Set momentum to accelerate learning by
# taking weighted average of current and previous updates.
s.momentum = 0.9
# Set weight decay to regularize and prevent overfitting
s.weight_decay = 5e-4

# Set `lr_policy` to define how the learning rate changes during training.
# This is the same policy as our default LeNet.
s.lr_policy = 'inv'
s.gamma = 0.0001
s.power = 0.75
# EDIT HERE to try the fixed rate (and compare with adaptive solvers)
# `fixed` is the simplest policy that keeps the learning rate constant.
# s.lr_policy = 'fixed'

# Display the current training loss and accuracy every 1000 iterations.
s.display = 1000

# Snapshots are files used to store networks we've trained.
# We'll snapshot every 5K iterations -- twice during training.
s.snapshot = 5000
s.snapshot_prefix = path_examples + 'mnist/custom_net'  #快照保存文件名和地址

# Train on the GPU
# s.solver_mode = caffe_pb2.SolverParameter.GPU
s.solver_mode = caffe_pb2.SolverParameter.CPU
# Write the solver to a temporary file and return its filename.
with open(solver_config_path, 'w') as f:
    f.write(str(s))

### load the solver and create train and test nets
solver = None  # ignore this workaround for lmdb data (can't instantiate two solvers on the same data)
solver = caffe.get_solver(solver_config_path)# load the solver in python
# 也可以采用solver = caffe.SGDSolver('solver.prototxt')#但它只用SGD算法,不管文件里设置什么
### solve
niter = 250  # EDIT HERE increase to train for longer
test_interval = niter / 10
# losses will also be stored in the log
train_loss = zeros(niter)
test_acc = zeros(int(np.ceil(niter / test_interval)))

# the main solver loop
for it in range(niter):
    solver.step(1)  # SGD by Caffe
    #只进行一步前向,反向和梯度更新.　solver.step()会执行所有的步数
    #solver.step()：可以采用如下命令代替：
    # solver.net.forward()#train net solver.test_nets[0].forward()#test net
    # solver.net.backward()

    # store the train loss
    train_loss[it] = solver.net.blobs['loss'].data

    # run a full test every so often
    # (Caffe can also do this for us and write to a log, but we show here
    #  how to do it directly in Python, where more complicated things are easier.)
    if it % test_interval == 0:
        print 'Iteration', it, 'testing...'
        correct = 0
        for test_it in range(100):
            solver.test_nets[0].forward()
            correct += sum(solver.test_nets[0].blobs['score'].data.argmax(1)
                           == solver.test_nets[0].blobs['label'].data)
        test_acc[it // test_interval] = correct / 1e4

ax1 = subplot()
ax2 = ax1.twinx()
ax1.plot(arange(niter), train_loss)
ax2.plot(test_interval * arange(len(test_acc)), test_acc, 'r')
plt.show()
ax1.set_xlabel('iteration')
ax1.set_ylabel('train loss')
ax2.set_ylabel('test accuracy')
ax2.set_title('Custom Test Accuracy: {:.2f}'.format(test_acc[-1]))