knn实现手写数字识别c++

对于手写数字识别，K最近邻（K-Nearest Neighbors, KNN）是一种简单而有效的算法。下面是一个用C语言实现KNN手写数字识别的示例代码：

#include <stdio.h>
#include <stdlib.h>
#include <math.h>

#define K 3 // 设置K值

typedef struct {
    int label;
    double features[64];
} Sample;

double euclidean_distance(double *a, double *b, int n) {
    double sum = 0.0;
    for (int i = 0; i < n; i++) {
        sum += pow(a[i] - b[i], 2);
    }
    return sqrt(sum);
}

int knn_predict(Sample *train_set, Sample test_sample, int train_size) {
    double distances[train_size];
    int labels[K];

    // 计算测试样本与所有训练样本之间的距离
    for (int i = 0; i < train_size; i++) {
        distances[i] = euclidean_distance(train_set[i].features, test_sample.features, 64);
    }

    // 根据距离排序，获取K个最近邻样本的标签
    for (int i = 0; i < K; i++) {
        int min_index = 0;
        for (int j = 1; j < train_size; j++) {
            if (distances[j] < distances[min_index]) {
                min_index = j;
            }
        }
        labels[i] = train_set[min_index].label;
        distances[min_index] = INFINITY; // 将已选择的样本距离设为无穷大，避免再次选择
    }

    // 统计最近邻样本中出现次数最多的标签
    int counts[10] = {0};
    for (int i = 0; i < K; i++) {
        counts[labels[i]]++;
    }

    int max_count = 0;
    int predicted_label = 0;
    for (int i = 0; i < 10; i++) {
        if (counts[i] > max_count) {
            max_count = counts[i];
            predicted_label = i;
        }
    }

    return predicted_label;
}

int main() {
    // 读取训练数据和测试数据

    FILE *train_file = fopen("train.txt", "r");
    if (train_file == NULL) {
        printf("无法打开训练文件\n");
        return 1;
    }

    int train_size;
    fscanf(train_file, "%d", &train_size);

    Sample *train_set = (Sample *)malloc(train_size * sizeof(Sample));
    for (int i = 0; i < train_size; i++) {
        fscanf(train_file, "%d", &train_set[i].label);
        for (int j = 0; j < 64; j++) {
            fscanf(train_file, "%lf", &train_set[i].features[j]);
        }
    }

    fclose(train_file);

    FILE *test_file = fopen("test.txt", "r");
    if (test_file == NULL) {
        printf("无法打开测试文件\n");
        return 1;
    }

    int test_size;
    fscanf(test_file, "%d", &test_size);

    Sample *test_set = (Sample *)malloc(test_size * sizeof(Sample));
    for (int i = 0; i < test_size; i++) {
        fscanf(test_file, "%d", &test_set[i].label);
        for (int j = 0; j < 64; j++) {
            fscanf(test_file, "%lf", &test_set[i].features[j]);
        }
    }

    fclose(test_file);

    // 预测并计算准确率
    int correct_count = 0;
    for (int i = 0; i < test_size; i++) {
        int predicted_label = knn_predict(train_set, test_set[i], train_size);
        if (predicted_label == test_set[i].label) {
            correct_count++;
        }
    }

    double accuracy = (double)correct_count / test_size * 100;
    printf("准确率：%lf%%\n", accuracy);

    free(train_set);
    free(test_set);

    return 0;
}

以上代码是一个简单的KNN手写数字识别的实现。你需要准备训练数据和测试数据，将其分别保存在"train.txt"和"test.txt"的文本文件中。训练数据和测试数据的格式如下：

2000   // 样本数量
5      // 标签
0.1 0.2 ... 0.3   // 特征
...

你可以根据实际情况调整K值和特征维度等参数来提高识别精度。希望能对你有所帮助！