CNN卷积神经网络应用于人脸识别-带详细流程+代码实现

# -*-coding:utf8-*-# """ 本程序基于python+numpy+theano+PIL开发，采用类似LeNet5的CNN模型，应用于olivettifaces人脸数据库， 实现人脸识别的功能，模型的误差降到了5%以下。 本程序只是个人学习过程的一个toy implement，模型可能存在overfitting，因为样本小，这一点也无从验证。 但是，本程序意在理清程序开发CNN模型的具体步骤，特别是针对图像识别，从拿到图像数据库，到实现一个针对这个图像数据库的CNN模型， 我觉得本程序对这些流程的实现具有参考意义。 @author:wepon(http://2hwp.com) 讲解这份代码的文章：http://blog.csdn.net/u012162613/article/details/43277187 """ import os import sys import time import numpy from PIL import Image import theano import theano.tensor as T from theano.tensor.signal import downsample from theano.tensor.nnet import conv """ 加载图像数据的函数,dataset_path即图像olivettifaces的路径 加载olivettifaces后，划分为train_data,valid_data,test_data三个数据集 函数返回train_data,valid_data,test_data以及对应的label """ def load_data(dataset_path): img = Image.open(dataset_path) img_ndarray = numpy.asarray(img, dtype='float64')/256 faces=numpy.empty((400,2679)) for row in range(20): for column in range(20): faces[row*20+column]=numpy.ndarray.flatten(img_ndarray [row*57:(row+1)*57,column*47:(column+1)*47]) label=numpy.empty(400) for i in range(40): label[i*10:i*10+10]=i label=label.astype(numpy.int) #分成训练集、验证集、测试集，大小如下 train_data=numpy.empty((320,2679)) train_label=numpy.empty(320) valid_data=numpy.empty((40,2679)) valid_label=numpy.empty(40) test_data=numpy.empty((40,2679)) test_label=numpy.empty(40) for i in range(40): train_data[i*8:i*8+8]=faces[i*10:i*10+8] train_label[i*8:i*8+8]=label[i*10:i*10+8] valid_data[i]=faces[i*10+8] valid_label[i]=label[i*10+8] test_data[i]=faces[i*10+9] test_label[i]=label[i*10+9] #将数据集定义成shared类型，才能将数据复制进GPU，利用GPU加速程序。 def shared_dataset(data_x, data_y, borrow=True): shared_x = theano.shared(numpy.asarray(data_x, dtype=theano.config.floatX), borrow=borrow) shared_y = theano.shared(numpy.asarray(data_y, dtype=theano.config.floatX), borrow=borrow) return shared_x, T.cast(shared_y, 'int32') train_set_x, train_set_y = shared_dataset(train_data,train_label) valid_set_x, valid_set_y = shared_dataset(valid_data,valid_label) test_set_x, test_set_y = shared_dataset(test_data,test_label) rval = [(train_set_x, train_set_y), (valid_set_x, valid_set_y), (test_set_x, test_set_y)] return rval #分类器，即CNN最后一层，采用逻辑回归（softmax） class LogisticRegression(object): def __init__(self, input, n_in, n_out): self.W = theano.shared( value=numpy.zeros( (n_in, n_out), dtype=theano.config.floatX ), name='W', borrow=True ) self.b = theano.shared( value=numpy.zeros( (n_out,), dtype=theano.config.floatX ), name='b', borrow=True ) self.p_y_given_x = T.nnet.softmax(T.dot(input, self.W) + self.b) self.y_pred = T.argmax(self.p_y_given_x, axis=1) self.params = [self.W, self.b] def negative_log_likelihood(self, y): return -T.mean(T.log(self.p_y_given_x)[T.arange(y.shape[0]), y]) def errors(self, y): if y.ndim != self.y_pred.ndim: raise TypeError( 'y should have the same shape as self.y_pred', ('y', y.type, 'y_pred', self.y_pred.type) ) if y.dtype.startswith('int'): return T.mean(T.neq(self.y_pred, y)) else: raise NotImplementedError() #全连接层，分类器前一层 class HiddenLayer(object): def __init__(self, rng, input, n_in, n_out, W=None, b=None, activation=T.tanh): self.input = input if W is None: W_values = numpy.asarray( rng.uniform( low=-numpy.sqrt(6. / (n_in + n_out)), high=numpy.sqrt(6. / (n_in + n_out)), size=(n_in, n_out) ), dtype=theano.config.floatX ) if activation == theano.tensor.nnet.sigmoid: W_values *= 4 W = theano.shared(value=W_values, name='W', borrow=True) if b is None: b_values = numpy.zeros((n_out,), dtype=theano.config.floatX) b = theano.shared(value=b_values, name='b', borrow=True) self.W = W self.b = b lin_output = T.dot(input, self.W) + self.b self.output = ( lin_output if activation is None else activation(lin_output) ) # parameters of the model self.params = [self.W, self.b] #卷积+采样层（conv+maxpooling） class LeNetConvPoolLayer(object): def __init__(self, rng, input, filter_shape, image_shape, poolsize=(2, 2)): assert image_shape[1] == filter_shape[1] self.input = input fan_in = numpy.prod(filter_shape[1:]) fan_out = (filter_shape[0] * numpy.prod(filter_shape[2:]) / numpy.prod(poolsize)) # initialize weights with random weights W_bound = numpy.sqrt(6. / (fan_in + fan_out)) self.W = theano.shared( numpy.asarray( rng.uniform(low=-W_bound, high=W_bound, size=filter_shape), dtype=theano.config.floatX ), borrow=True ) # the bias is a 1D tensor -- one bias per output feature map b_values = numpy.zeros((filter_shape[0],), dtype=theano.config.floatX) self.b = theano.shared(value=b_values, borrow=True) # 卷积 conv_out = conv.conv2d( input=input, filters=self.W, filter_shape=filter_shape, image_shape=image_shape ) # 子采样 pooled_out = downsample.max_pool_2d( input=conv_out, ds=poolsize, ignore_border=True ) self.output = T.tanh(pooled_out + self.b.dimshuffle('x', 0, 'x', 'x')) # store parameters of this layer self.params = [self.W, self.b] #保存训练参数的函数 def save_params(param1,param2,param3,param4): import cPickle write_file = open('params.pkl', 'wb') cPickle.dump(param1, write_file, -1) cPickle.dump(param2, write_file, -1) cPickle.dump(param3, write_file, -1) cPickle.dump(param4, write_file, -1) write_file.close() """ 上面定义好了CNN的一些基本构件，下面的函数将CNN应用于olivettifaces这个数据集，CNN的模型基于LeNet。 采用的优化算法是批量随机梯度下降算法，minibatch SGD，所以下面很多参数都带有batch_size，比如image_shape=(batch_size, 1, 57, 47) 可以设置的参数有： batch_size,但应注意n_train_batches、n_valid_batches、n_test_batches的计算都依赖于batch_size nkerns=[5, 10]即第一二层的卷积核个数可以设置 全连接层HiddenLayer的输出神经元个数n_out可以设置，要同时更改分类器的输入n_in 另外，还有一个很重要的就是学习速率learning_rate. """ def evaluate_olivettifaces(learning_rate=0.05, n_epochs=200, dataset='olivettifaces.gif', nkerns=[5, 10], batch_size=40): #随机数生成器，用于初始化参数 rng = numpy.random.RandomState(23455)