caffe学习笔记8:使用python建立Caffe网络入门

使用python建立Caffe网络入门

---

在这个例子中，我们将探索caffe的python版本使用，使用Solver接口，建立和修改Lenet网络。

---

1.建立python环境

---

from pylab import *
%matplotlib inline

导入pyhon，讲python环境假如到sys.path中

caffe_root = '../'  # this file should be run from {caffe_root}/examples (otherwise change this line)
import sys
sys.path.insert(0, caffe_root + 'python')
import caffe

我们将使用Lenet的例子数据和网络，确认你下载了数据和创建了数据集，像下面一样

# run scripts from caffe root
import os
os.chdir(caffe_root)
# Download data
!data/mnist/get_mnist.sh
# Prepare data
!examples/mnist/create_mnist.sh
# back to examples
os.chdir('examples')

Downloading…
Creating lmdb…
Done.

---

2.创建网络

现在创建一个lenet的变种，这个网络1989年就有了
我们需要两个额外的文件

the net prototxt, defining the architecture and pointing to the train/test data
the solver prototxt, defining the learning parameters

我们将从创建网络开始，我们要以protobuf的形式编写模型
网络读取文件通过预先生成的LMDB网络，同样可以通过内存读取ndarray形式的数据

from caffe import layers as L, params as P

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

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

网络以google的protobuf库的形式被写入硬盘。你可以直接读写修改这个文件，让我们看看训练网络的样子。

!cat mnist/lenet_auto_train.prototxt

显示的文件内容

layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  transform_param {
    scale: 0.00392156862745
  }
  data_param {
    source: "mnist/mnist_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"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  convolution_param {
    num_output: 50
    kernel_size: 5
    weight_filler {
      type: "xavier"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "fc1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "fc1"
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "fc1"
  top: "fc1"
}
layer {
  name: "score"
  type: "InnerProduct"
  bottom: "fc1"
  top: "score"
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "score"
  bottom: "label"
  top: "loss"
}

现在让我们看看学习过程的参数，也是写在一个prototext文件制作，已经在硬盘上准备好了。我们使用带动量的SGD优化函数，权重衰减，一个特定的学习滤改变计划。

!cat mnist/lenet_auto_solver.prototxt

显示内容

# The train/test net protocol buffer definition
train_net: "mnist/lenet_auto_train.prototxt"
test_net: "mnist/lenet_auto_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: "mnist/lenet"

3.下载检测solver

---

让我们指定一个GPU和下载solver，我们将使用SGD（含动量），其他的优化函数也是可以使用的

caffe.set_device(0)
caffe.set_mode_gpu()
### 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('mnist/lenet_auto_solver.prototxt')

为了检测网络结构，我们可以参考中间特性(blob)和参数的维度（以后这些维多在吹数据的时候也很有用）

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

[(‘data’, (64, 1, 28, 28)),
(‘label’, (64,)),
(‘conv1’, (64, 20, 24, 24)),
(‘pool1’, (64, 20, 12, 12)),
(‘conv2’, (64, 50, 8, 8)),
(‘pool2’, (64, 50, 4, 4)),
(‘fc1’, (64, 500)),
(‘score’, (64, 10)),
(‘loss’, ())]

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

在我们训练模型之前，看看是不是每件事都是按照我们的期望导入的，我们将允许一次前向传播过程，测试网络检测它是否包含我们需要的数据

solver.net.forward()  # train net
solver.test_nets[0].forward()  # test net (there can be more than one)

输出
{‘loss’: array(2.365971088409424, dtype=float32)}

# we use a little trick to tile the first eight images
imshow(solver.net.blobs['data'].data[:8, 0].transpose(1, 0, 2).reshape(28, 8*28), cmap='gray'); axis('off')
print 'train labels:', solver.net.blobs['label'].data[:8]

train labels: [ 5. 0. 4. 1. 9. 2. 1. 3.]

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

test labels: [ 7. 2. 1. 0. 4. 1. 4. 9.]

4.一步一步运行solver

---

看来训练和test网络都导入了数据，有正确的标签，
现在我们运行一步（使用SGD）看会发生什么

solver.step(1)

我们的梯度是否在filter上面传播了呢，现在看更新后的第一层权重，用4*5的网格显示5*5大小的filters

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')

(-0.5, 24.5, 19.5, -0.5)

5.写一个通用的训练循环

---

上述过程中午网络之中发生了一些事，让我们运行一会这个网络，随时跟踪一些事情，注意这个过程和使用caffe二进制文件进行训练是一样的，尤其是
1.会记录日志
2.以指定的步数间隔保存模型(在这里是5000次迭代)
3.测试过程会以指定的间隔进行
由于我们已经控制了Python中的循环，我们可以水洗所欲计算更多东西，入一下所示，我们可以做其他事，例如
1.写一个自定义的停止标准
2.通过更新循环中的网络来改变求解器的过程

%%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)))
output = zeros((niter, 8, 10))

# 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]

    # 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

输出

Iteration 0 testing...
Iteration 25 testing...
Iteration 50 testing...
Iteration 75 testing...
Iteration 100 testing...
Iteration 125 testing...
Iteration 150 testing...
Iteration 175 testing...
CPU times: user 12.6 s, sys: 2.4 s, total: 15 s
Wall time: 14.4 s

让我们画出训练的loss曲线和测试精度

_, ax1 = subplots()
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]))

输出

看来loss下降的很快并且收敛了，同时精度上升，万岁！
由于我们将结果保存在第一批测试中，我们可以看看我们的预测成绩，以时间为x轴，y轴为可能的标签,越亮表示置信度越高

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(output[:50, i].T, interpolation='nearest', cmap='gray')
    xlabel('iteration')
    ylabel('label')

我们的网络一开始对数字没有分辨能力，训练结束的时候已经能正确分类了，
如果你一直在看，你就会发现，倾斜的9和4最容易混淆

注意，这是输出的原始的输出分数而不是softma计算的概率向量
后者如下图所示，这让我们更容易看到网络的置信但是更难看到分数

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')
    xlabel('iteration')
    ylabel('label')

6.实验结构和优化器

---

现在我们定义训练 测试了Lenet，接下来还有很多可以做的事情
定义新的网络结构作为比较
改变基础学习率或者训练更久
改变SGD算法至AdaDelta或者Adam
你可以做这些来改变网络

1.Switch the nonlinearity from ReLU to ELU or a saturing nonlinearity like Sigmoid
2.Stack more fully connected and nonlinear layers
3.Search over learning rate 10x at a time (trying 0.1 and 0.001)
4.Switch the solver type to Adam (this adaptive solver type should be less sensitive to hyperparameters, but no guarantees…)
5.Solve for longer by setting niter higher (to 500 or 1,000 for instance) to better show training differences

train_net_path = 'mnist/custom_auto_train.prototxt'
test_net_path = 'mnist/custom_auto_test.prototxt'
solver_config_path = '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.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb,
                             transform_param=dict(scale=1./255), ntop=2)

    # 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.data, num_output=10, weight_filler=dict(type='xavier'))

    # EDIT HERE this is the LeNet variant we have already tried
    # 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'))
    # 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()

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

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 = 'mnist/custom_net'

# Train on the GPU
s.solver_mode = caffe_pb2.SolverParameter.GPU

# 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)

### 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

    # 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 = subplots()
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('Custom Test Accuracy: {:.2f}'.format(test_acc[-1]))

Iteration 0 testing…
Iteration 25 testing…
Iteration 50 testing…
Iteration 75 testing…
Iteration 100 testing…
Iteration 125 testing…
Iteration 150 testing…
Iteration 175 testing…
Iteration 200 testing…
Iteration 225 testing…

7.参考资料

---

http://nbviewer.jupyter.org/github/BVLC/caffe/blob/master/examples/01-learning-lenet.ipynb