python 神经网络 多进程_用Caffe Python实现一个两层神经网络

1. 首先准备一下原始数据

# *-* coding: utf-8 *-*

import pickle

import numpy as np

# 划分类别的边界

def cos_curve(x):

return 0.25*np.sin(2*x*np.pi+0.5*np.pi) + 0.5

# samples保存二维点的坐标，labels标明类别

np.random.seed(123)

samples = []

labels = []

# 单位空间内平均样本数为50

sample_density = 50

for i in range(sample_density):

x1, x2 = np.random.random(2)

# 计算当前x1对应的分类边界

bound = cos_curve(x1)

# 为了方便可视化，舍弃太靠近边界的样本

if bound - 0.1 < x2 <= bound + 0.1:

continue

else:

samples.append((x1, x2))

# 打标签，上半部分为1，下半部分为2

if x2 > bound:

labels.append(1)

else:

labels.append(0)

# 将生成的样本和标签保存

with open('data.pkl', 'wb') as f:

pickle.dump((samples, labels), f)

# 进行数据可视化

import matplotlib.pyplot as plt

for i, sample in enumerate(samples):

plt.plot(sample[0], sample[1], 'o' if labels[i] else '^', mec='r' if labels[i] else 'b', mfc='none', markersize=10)

x1 = np.linspace(0, 1)

plt.plot(x1, cos_curve(x1), 'k--')

plt.show()

2. 用HDF5准备坐标数据和对应标签。

# *-* coding: utf-8 *-*

import pickle

import numpy as np

import h5py

# 读取先前保存好的数据

with open('data.pkl', 'rb') as f:

samples, labels = pickle.load(f)

sample_size = len(labels)

# 按照HDF5格式要求制作数据

samples = np.array(samples).reshape((sample_size, 2))

labels = np.array(labels).reshape((sample_size, 1))

# 生成HDF5格式数据

h5_filename = 'data.h5'

with h5py.File(h5_filename, 'w') as h:

h.create_dataset('data', data=samples)

h.create_dataset('label', data=labels)

# 生成HDF5数据列表

with open('data_h5.txt', 'w') as f:

f.write(h5_filename)

这部分结束之后，生成data.h5和data_h5.txt。

3.做训练网络以及train.prototxt

name: "SimpleMLP"

input: "data"

input_shape {

dim: 1

dim: 2

}

layer {

name: "fc1"

type: "InnerProduct"

bottom: "data"

top: "fc1"

inner_product_param {

num_output: 2

}

}

layer {

name: "sigmoid1"

type: "Sigmoid"

bottom: "fc1"

top: "sigmoid1"

}

layer {

name: "fc2"

type: "InnerProduct"

bottom: "sigmoid1"

top: "fc2"

inner_product_param {

num_output: 2

}

}

layer {

name: "softmax"

type: "Softmax"

bottom: "fc2"

top: "prob"

}

就这样完成了一个两层神经网络的设计。

接下来将这个网络进行可视化，利用caffe提供的draw_net.py实现，需要安装graphviz和pydot。

遇到的问题在我的另一篇文章用draw_net.py绘制网络图时的小问题中有给出解决方法。

如果你在使用pycharm编辑器的话，需要在run之前给出一些需要设置的参数，第一个参数为train.prototxt，第二个为生成图像的位置，第三个–randir为生成layers的排列顺序，默认为横向，BT为竖直生成。

这样运行之后，就生成了一张网络图：

4.进行训练

# *-* coding: utf-8 *-*

import sys

import numpy as np

import caffe

# caffe的python入口

sys.path.append('D:/new_caffe/caffe/python')

# 初始化一个SGDSolver

solver = caffe.SGDSolver('solver.prototxt')

# 开始训练

solver.solve()

# 获取训练好的网络

net = solver.net

# 制定一个输入数据，比如取值范围平面的中心

net.blobs['data'] = np.array([[0.5, 0.5]])

# 执行前向计算

output = net.forward()

# 输出结果

print output

训练过程：

并且生成了相应的权重文件：

5.写test.prototxt

name: "SimpleMLP"

input: "data"

input_shape {

dim: 1

dim: 2

}

layer {

name: "fc1"

type: "InnerProduct"

bottom: "data"

top: "fc1"

inner_product_param {

num_output: 2

}

}

layer {

name: "sigmoid1"

type: "Sigmoid"

bottom: "fc1"

top: "sigmoid1"

}

layer {

name: "fc2"

type: "InnerProduct"

bottom: "sigmoid1"

top: "fc2"

inner_product_param {

num_output: 2

}

}

layer {

name: "softmax"

type: "Softmax"

bottom: "fc2"

top: "prob"

}

用于使用训练好的模型进行test。

6.来test模型，并且生成可视化的结果

# *-* coding:utf-8 *-*

import sys

import pickle

import numpy as np

import matplotlib.pyplot as plt

from mpl_toolkits.mplot3d import Axes3D

sys.path.append('D:/new_caffe/caffe/python')

import caffe

# 构建一个网络用语Inference

# 网络结构是test.prototxt，权重从训练好的simple_mlp_iter_2000.caffemodel中获取

net = caffe.Net('test.prototxt', "simple_mlp_iter_2000.caffemodel", caffe.TEST)

# 读取二维样本及标签

with open('data.pkl', 'rb') as f:

samples, labels = pickle.load(f)

samples = np.array(samples)

labels = np.array(labels)

# 进行可视化

# 第一步可视化概率值平面

X = np.arange(0, 1.05, 0.05)

Y = np.arange(0, 1.05, 0.05)

X, Y = np.meshgrid(X, Y)

grids = np.array([[X[i][j], Y[i][j]] for i in range(X.shape[0]) for j in range(X.shape[1])])

grid_probs = []

for grid in grids:

net.blobs['data'].data[...] = grid.reshape((1, 2))[...]

output = net.forward()

grid_probs.append(output['prob'][0][1])

grid_probs = np.array(grid_probs).reshape(X.shape)

fig = plt.figure('Sample Surface')

ax = fig.gca(projection='3d')

ax.plot_surface(X, Y, grid_probs, alpha=0.15, color='k', rstride=2, cstride=2, lw=0.5)

# 对所有样本及对应概率进行可视化

samples0 = samples[labels == 0]

samples0_probs = []

for sample in samples0:

net.blobs['data'].data[...] = sample.reshape((1, 2))[...]

output = net.forward()

samples0_probs.append(output['prob'][0][1])

samples1 = samples[labels == 1]

samples1_probs = []

for sample in samples1:

net.blobs['data'].data[...] = sample.reshape((1, 2))[...]

output = net.forward()

samples1_probs.append(output['prob'][0][1])

ax.scatter(samples0[:, 0], samples0[:, 1], samples0_probs, c='b', marker='^', s=50)

ax.scatter(samples1[:, 0], samples1[:, 1], samples1_probs, c='r', marker='o', s=50)

plt.show()

test过程：

生成结果：

参考资料：《深度学习与计算机视觉 》 叶韵 编著