caffe学习笔记８-- Python solving with LeNet

这是caffe官方文档Notebook Examples中的第二个例子，链接地址：http://nbviewer.jupyter.org/github/BVLC/caffe/blob/master/examples/01-learning-lenet.ipynb

这个例子使用LeNet对手写数字分类。LeNet的结构可以参考：http://blog.csdn.net/thystar/article/details/50470325

１. 改变工作目录：

import os
caffe_root = '/home/sindyz/caffe-master/'
os.chdir(caffe_root)

2. 导入相应的包

import sys
sys.path.insert(0, './python')
import caffe

from pylab import *
%matplotlib inline

3. 获取数据

如果已经下载过，这步可以不要

# Download and prepare data
!data/mnist/get_mnist.sh
!examples/mnist/create_mnist.sh

4. 写LeNet网络结构，分别命名为lenet_auto_train.prototxt和lenet_auto_test.prototxt

from caffe import layers as L
from caffe import 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.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)
    return n.to_proto()

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

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

5. 查看网络结构

!cat examples/mnist/lenet_auto_train.prototxt

输出：

layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  transform_param {
    scale: 0.00392156862745
  }
  data_param {
    source: "examples/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: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}

6.  查看参数文件，同样是prototxt文件，用带动量的SGD（随机梯度下降），权重衰减，以及特定的学习率：

!cat examples/mnist/lenet_auto_solver.prototxt

输出：

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

7. 使用GPU，载入solver，这里用SGD，Adagrad和Nesterov加速梯度也是可行的：

这里需要说明一下，caffe的优化函数是非凸的，没有解析解，需要通过优化方法来求解，

caffe封装了三种优化方法：

• Stochastic Gradient Descent (SGD), 随机梯度下降
  
• AdaptiveGradient (ADAGRAD), 自适应梯度下降
  
• Nesterov’s Accelerated Gradient (NAG)。Nesterov加速梯度下降法

caffe.set_device(0)
caffe.set_mode_gpu()
solver = caffe.SGDSolver(caffe_root+'/examples/mnist/lenet_auto_solver.prototxt')

8. 查看中间特征（blobs）和参数（params）的维数：

[(k,v.data.shape) for k,v in solver.net.blobs.items()]

输出

[('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)),
 ('ip1', (64, 500)),
 ('ip2', (64, 10)),
 ('loss', ())]

[(k,v[0].data.shape) for k,v in solver.net.params.items()]

输出：

[('conv1', (20, 1, 5, 5)),
 ('conv2', (50, 20, 5, 5)),
 ('ip1', (500, 800)),
 ('ip2', (10, 500))]

9. 在测试集和训练集上执行一个前向的过程

solver.net.forward()
solver.test_nets[0].forward()

输出：

{'loss': array(2.2941734790802, dtype=float32)}

10. 显示训练集８个数据的图像和他们的标签，

imshow(solver.net.blobs['data'].data[:8, 0].transpose(1, 0, 2).reshape(28, 8*28), cmap='gray')
print solver.net.blobs['label'].data[:8]

[ 5.  0.  4.  1.  9.  2.  1.  3.]

11. 显示测试集中的8个图像和他们的标签

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

[ 7.  2.  1.  0.  4.  1.  4.  9.]

11. 执行无误，则执行一步SGB, 查看权值的变化:

第一层权值的变化如下图：20个5x5规模的滤波器

 solver.step(1)
 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')

运行网络，这个过程和通过caffe的binary训练是一样的，

12. 控制循环

因为可以控制python中的循环，因此可以做一些其他的事情，例如自定义停止的标准，通过循环更新网络来改变求解过程：

%%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['ip2'].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['ip2'].data.argmax(1)
                            == solver.test_nets[0].blobs['label'].data)
         test_acc[it // test_interval] = correct / 1e4

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 19 s, sys: 6.2 s, total: 25.2 s
Wall time: 24.4 s

13. 画出训练样本损失和测试样本正确率

_, 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')

14. 画出分类结果：

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')

图像省略，在网站上有的

15. 使用softmax分类

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')

参考网站：

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