基于神经网络的手写数字识别代码（计算智能课程设计）

Layer

# coding=utf-8
import numpy as np
import struct
import os
import time

class FullyConnectedLayer(object):
    def __init__(self, num_input, num_output):  # 全连接层初始化
        self.num_input = num_input
        self.num_output = num_output
        print('\tFully connected layer with input %d, output %d.' % (self.num_input, self.num_output))
    def init_param(self, std=0.01):  # 参数初始化
        self.weight = np.random.normal(loc=0.0, scale=std, size=(self.num_input, self.num_output))
        self.bias = np.zeros([1, self.num_output])
    def forward(self, input):  # 前向传播计算
        start_time = time.time()
        self.input = input
        # TODO：全连接层的前向传播，计算输出结果
        self.output = np.matmul(input,self.weight)+self.bias
        return self.output
    def backward(self, top_diff):  # 反向传播的计算
        # TODO：全连接层的反向传播，计算参数梯度和本层损失
        self.d_weight = np.matmul(self.input.T,top_diff)
        self.d_bias = np.sum(top_diff,axis=0)
        bottom_diff = np.matmul(top_diff,self.weight.T)
        return bottom_diff
    def update_param(self, lr):  # 参数更新
        # TODO：对全连接层参数利用参数进行更新
        self.weight = self.weight - lr * self.d_weight
        self.bias = self.bias - lr * self.d_bias
    def load_param(self, weight, bias):  # 参数加载
        assert self.weight.shape == weight.shape
        assert self.bias.shape == bias.shape
        self.weight = weight
        self.bias = bias
    def save_param(self):  # 参数保存
        return self.weight, self.bias

class ReLULayer(object):
    def __init__(self):
        print('\tReLU layer.')
    def forward(self, input):  # 前向传播的计算
        start_time = time.time()
        self.input = input
        # TODO：ReLU层的前向传播，计算输出结果
        output = input.copy()
        output[(input < 0)] = 0
        return output
    def backward(self, top_diff):  # 反向传播的计算
        # TODO：ReLU层的反向传播，计算本层损失
        bottom_diff = top_diff
        bottom_diff[self.input<0] = 0
        return bottom_diff

class SoftmaxLossLayer(object):
    def __init__(self):
        print('\tSoftmax loss layer.')
    def forward(self, input):  # 前向传播的计算
        # TODO：softmax 损失层的前向传播，计算输出结果
        input_max = np.max(input, axis=1, keepdims=True)
        input_exp = np.exp(input - input_max)
        self.prob = input_exp / np.sum(input_exp, axis=1, keepdims=True)
        return self.prob
    def get_loss(self, label):   # 计算损失
        self.batch_size = self.prob.shape[0]
        self.label_onehot = np.zeros_like(self.prob)
        self.label_onehot[np.arange(self.batch_size), label] = 1.0
        loss = -np.sum(np.log(self.prob) * self.label_onehot) / self.batch_size
        return loss
    def backward(self):  # 反向传播的计算
        # TODO：softmax 损失层的反向传播，计算本层损失
        bottom_diff = (self.prob - self.label_onehot) / self.batch_size
        return bottom_diff

cpu

# coding=utf-8
import numpy as np
import struct
import os
import time

from layers_1 import FullyConnectedLayer, ReLULayer, SoftmaxLossLayer

MNIST_DIR = "./mnist_data"
TRAIN_DATA = "train-images-idx3-ubyte"
TRAIN_LABEL = "train-labels-idx1-ubyte"
TEST_DATA = "t10k-images-idx3-ubyte"
TEST_LABEL = "t10k-labels-idx1-ubyte"

def show_matrix(mat, name):
    #print(name + str(mat.shape) + ' mean %f, std %f' % (mat.mean(), mat.std()))
    pass

class MNIST_MLP(object):
    def __init__(self, batch_size=100, input_size=784, hidden1=32, hidden2=16, hidden3=8, out_classes=10, lr=0.01, max_epoch=2, print_iter=100):
        #  神经网络初始化
        self.batch_size = batch_size
        self.input_size = input_size
        self.hidden1 = hidden1
        self.hidden2 = hidden2
        self.hidden3 = hidden3
        self.out_classes = out_classes
        self.lr = lr
        self.max_epoch = max_epoch
        self.print_iter = print_iter

    def load_mnist(self, file_dir, is_images = 'True'):
        # Read binary data
        bin_file = open(file_dir, 'rb')
        bin_data = bin_file.read()
        bin_file.close()
        # Analysis file header
        if is_images:
            # Read images
            fmt_header = '>iiii'
            # struct.unpack_from(fmt, buffer, offset=0)
            # 按照指定的格式fmt，从偏移位置offset开始解包,
            # 返回数据格式是一个元组(v1, v2...)
            magic, num_images, num_rows, num_cols = struct.unpack_from(fmt_header, bin_data, 0)
        else:
            # Read labels
            fmt_header = '>ii'
            magic, num_images = struct.unpack_from(fmt_header, bin_data, 0)
            num_rows, num_cols = 1, 1
        data_size = num_images * num_rows * num_cols
        mat_data = struct.unpack_from('>' + str(data_size) + 'B', bin_data, struct.calcsize(fmt_header))
        mat_data = np.reshape(mat_data, [num_images, num_rows * num_cols])
        print('Load images from %s, number: %d, data shape: %s' % (file_dir, num_images, str(mat_data.shape)))
        return mat_data

    def load_data(self):
        # TODO: 调用函数 load_mnist 读取和预处理 MNIST 中训练数据和测试数据的图像和标记
        print('Loading MNIST data from files...')
        train_images = self.load_mnist(os.path.join(MNIST_DIR, TRAIN_DATA), True)
        train_labels = self.load_mnist(os.path.join(MNIST_DIR, TRAIN_LABEL), False)
        test_images = self.load_mnist(os.path.join(MNIST_DIR, TEST_DATA), True)
        test_labels = self.load_mnist(os.path.join(MNIST_DIR, TEST_LABEL), False)
        self.train_data = np.append(train_images, train_labels, axis=1)
        self.test_data = np.append(test_images, test_labels, axis=1)
        # print("train1", self.train_data.shape, 'train2', train_labels.shape)
        # print("test1", self.test_data.shape, 'test2', test_images.shape)
        # exit(0)
        # self.test_data = np.concatenate((self.train_data, self.test_data), axis=0)

    def shuffle_data(self):
        print('Randomly shuffle MNIST data...')
        np.random.shuffle(self.train_data)

    def build_model(self):  # 建立网络结构
        # TODO：建立三层神经网络结构
        print('Building multi-layer perception model...')
        self.fc1 = FullyConnectedLayer(self.input_size, self.hidden1)
        self.relu1 = ReLULayer()
        self.fc2 = FullyConnectedLayer(self.hidden1, self.hidden2)
        self.relu2 = ReLULayer()
        self.fc3 = FullyConnectedLayer(self.hidden2, self.hidden3)
        self.relu3 = ReLULayer()
        self.fc4 = FullyConnectedLayer(self.hidden3, self.out_classes)
        self.softmax = SoftmaxLossLayer()
        self.update_layer_list = [self.fc1, self.fc2, self.fc3, self.fc4]

    def init_model(self):
        print('Initializing parameters of each layer in MLP...')
        for layer in self.update_layer_list:
            layer.init_param()

    def load_model(self, param_dir): # 加载神经网络权值
        print('Loading parameters from file ' + param_dir)
        params = np.load(param_dir, allow_pickle=True).item()
        self.fc1.load_param(params['w1'], params['b1'])
        self.fc2.load_param(params['w2'], params['b2'])
        self.fc3.load_param(params['w3'], params['b3'])
        self.fc3.load_param(params['w4'], params['b4'])

    def save_model(self, param_dir):
        print('Saving parameters to file ' + param_dir)
        params = {}
        params['w1'], params['b1'] = self.fc1.save_param()
        params['w2'], params['b2'] = self.fc2.save_param()
        params['w3'], params['b3'] = self.fc3.save_param()
        params['w4'], params['b4'] = self.fc3.save_param()
        np.save(param_dir, params)

    def forward(self, input):  # 神经网络的前向传播
        # TODO：神经网络的前向传播
        h1 = self.fc1.forward(input)
        h1 = self.relu1.forward(h1)
        h2 = self.fc2.forward(h1)
        h2 = self.relu2.forward(h2)
        h3 = self.fc3.forward(h2)
        h3 = self.relu3.forward(h3)
        h4 = self.fc4.forward(h3)
        prob = self.softmax.forward(h4)
        return prob

    def backward(self):  # 神经网络的反向传播
        # TODO：神经网络的反向传播
        dloss = self.softmax.backward()
        dh4 = self.fc4.backward(dloss)
        dh3 = self.relu3.backward(dh4)
        dh3 = self.fc3.backward(dh3)
        dh2 = self.relu2.backward(dh3)
        dh2 = self.fc2.backward(dh2)
        dh1 = self.relu1.backward(dh2)
        dh1 = self.fc1.backward(dh1)

    def update(self, lr):   # 神经网络的参数更新
        for layer in self.update_layer_list:
            layer.update_param(lr)

    def train(self): # 训练函数
        max_batch = self.train_data.shape[0] // self.batch_size
        # print("train.0",self.train_data.shape[0] )
        # print("self.batch_size",self.batch_size )
        # exit(0)
        print('Start training...')
        for idx_epoch in range(self.max_epoch):
            self.shuffle_data()
            print(idx_epoch)
            for idx_batch in range(max_batch):
                batch_images = self.train_data[idx_batch*self.batch_size:(idx_batch+1)*self.batch_size, :-1]
                batch_labels = self.train_data[idx_batch*self.batch_size:(idx_batch+1)*self.batch_size, -1]
                prob = self.forward(batch_images)
                loss = self.softmax.get_loss(batch_labels)
                self.backward()
                self.update(self.lr)
                if idx_batch % self.print_iter == 0:
                    print('Epoch %d, iter %d, loss: %.6f' % (idx_epoch, idx_batch, loss))

    def evaluate(self): #推断函数
        pred_results = np.zeros([self.test_data.shape[0]])
        start_time = time.time()
        for idx in range(self.test_data.shape[0]//self.batch_size):
            batch_images = self.test_data[idx*self.batch_size:(idx+1)*self.batch_size, :-1]
            prob = self.forward(batch_images)
            end = time.time()
            pred_labels = np.argmax(prob, axis=1)
            pred_results[idx*self.batch_size:(idx+1)*self.batch_size] = pred_labels
        print("All evaluate time: %f"%(time.time()-start_time))
        accuracy = np.mean(pred_results == self.test_data[:,-1])
        print('Accuracy in test set: %f' % accuracy)


if __name__ == '__main__':
    h1, h2,h3, e = 64, 32, 16, 10


    # def __init__(self, batch_size=100, input_size=784,
    # hidden1=32, hidden2=16, out_classes=10,
    # lr=0.01, max_epoch=2,
    #              print_iter=100):


    mlp = MNIST_MLP(hidden1=h1, hidden2=h2,hidden3=h3, max_epoch=e)
    mlp.load_data()
    mlp.build_model()
    mlp.init_model()
    start_time = time.time()
    mlp.train()
    print("All train time: %f"%(time.time()-start_time))
    mlp.save_model('mlp-%d-%d-%depoch.npy' % (h1, h2, e))
    mlp.load_model('mlp-%d-%d-%depoch.npy' % (h1, h2, e))
    mlp.evaluate()