这里有一个模板来帮你做这件事:

template<typename T>
void removeDuplicates(std::vector<T>& vec)
{
    std::sort(vec.begin(), vec.end());
    vec.erase(std::unique(vec.begin(), vec.end()), vec.end());
}

这样称呼它:

removeDuplicates<int>(vectorname);

取决于用例。如果你期望有少于100个正整数的唯一值，并且你有一个cpu能够处理avx512f指令集，那么你可以以每个元素15个时钟周期或每秒3 -5亿个插入的速度插入元素，通过与一个小型查找表进行简单的比较。

接下来的实现使用CPU寄存器对~50个惟一值进行值查找，并对~1000个惟一值进行L1缓存。对于L1缓存版本，每次插入大约需要160个时钟周期，这相当于大约每秒25M个插入，并且比使用std::set慢。对于只有4个唯一值，它以每个元素5.8个周期的速率插入，高于500M/s。

//g++  7.4.0
// time measurement taken from another answer
// valid C99 and C++

#include <stdint.h>  // <cstdint> is preferred in C++, but stdint.h works.

#ifdef _MSC_VER
# include <intrin.h>
#else
# include <x86intrin.h>
#endif

// optional wrapper if you don't want to just use __rdtsc() everywhere
inline
uint64_t readTSC() {
     _mm_lfence();  // optionally wait for earlier insns to retire before reading the clock
    uint64_t tsc = __rdtsc();
     _mm_lfence();  // optionally block later instructions until rdtsc retires
    return tsc;
}

// requires a Nehalem or newer CPU.  Not Core2 or earlier.  IDK when AMD added it.
inline
uint64_t readTSCp() {
    unsigned dummy;
    return __rdtscp(&dummy);  // waits for earlier insns to retire, but allows later to start
}



#include <iostream>

template<int n>
struct FastUnique
{
    public:
    FastUnique()
    {
         it=0;
         for(int i=0;i<n;i++)
             dict[i]=-1;
    }

    void insert(const int val)
    {
        if(!test(dict,val))
            dict[it++]=val;
    }

    const int get(const int index)
    {
        return dict[index];
    }

    const int size()
    {
        return it;
    }

    private:
    int dict[n];
    int it;
    bool test(const int * dict, const int val)
    {
        int c=0;
        for(int i=0;i<n;i++)
            c+=(dict[i]==val);
        return c>0;
    }
};

int main()
{
    std::cout << "Hello, world!\n";
    const int n=500000000;

    FastUnique<64> fastSet;

    auto t= readTSC();

    for(int i=0;i<n;i++)
        fastSet.insert(i&63);

    auto t2=readTSC();

    std::cout<<(t2-t)/(double)n<<"cycles per iteration"<<std::endl;
   
    for(int i=0;i<fastSet.size();i++)
        std::cout<<fastSet.get(i)<<std::endl;
    
    return 0;
}

更多可理解的代码来自:https://en.cppreference.com/w/cpp/algorithm/unique

#include <iostream>
#include <algorithm>
#include <vector>
#include <string>
#include <cctype>

int main() 
{
    // remove duplicate elements
    std::vector<int> v{1,2,3,1,2,3,3,4,5,4,5,6,7};
    std::sort(v.begin(), v.end()); // 1 1 2 2 3 3 3 4 4 5 5 6 7 
    auto last = std::unique(v.begin(), v.end());
    // v now holds {1 2 3 4 5 6 7 x x x x x x}, where 'x' is indeterminate
    v.erase(last, v.end()); 
    for (int i : v)
      std::cout << i << " ";
    std::cout << "\n";
}

增长:

1 2 3 4 5 6 7

下面是使用std::unique()出现重复删除问题的示例。在LINUX机器上，程序崩溃。详情请阅读评论。

// Main10.cpp
//
// Illustration of duplicate delete and memory leak in a vector<int*> after calling std::unique.
// On a LINUX machine, it crashes the progam because of the duplicate delete.
//
// INPUT : {1, 2, 2, 3}
// OUTPUT: {1, 2, 3, 3}
//
// The two 3's are actually pointers to the same 3 integer in the HEAP, which is BAD
// because if you delete both int* pointers, you are deleting the same memory
// location twice.
//
//
// Never mind the fact that we ignore the "dupPosition" returned by std::unique(),
// but in any sensible program that "cleans up after istelf" you want to call deletex
// on all int* poitners to avoid memory leaks.
//
//
// NOW IF you replace std::unique() with ptgi::unique(), all of the the problems disappear.
// Why? Because ptgi:unique merely reshuffles the data:
// OUTPUT: {1, 2, 3, 2}
// The ptgi:unique has swapped the last two elements, so all of the original elements in
// the INPUT are STILL in the OUTPUT.
//
// 130215   dbednar@ptgi.com
//============================================================================

#include <iostream>
#include <vector>
#include <algorithm>
#include <functional>

#include "ptgi_unique.hpp"

// functor used by std::unique to remove adjacent elts from vector<int*>
struct EqualToVectorOfIntegerStar: public std::equal_to<int *>
{
    bool operator() (const int* arg1, const int* arg2) const
    {
        return (*arg1 == *arg2);
    }
};

void printVector( const std::string& msg, const std::vector<int*>& vnums);

int main()
{
    int inums [] = { 1, 2, 2, 3 };
    std::vector<int*> vnums;

    // convert C array into vector of pointers to integers
    for (size_t inx = 0; inx < 4; ++ inx)
        vnums.push_back( new int(inums[inx]) );

    printVector("BEFORE UNIQ", vnums);

    // INPUT : 1, 2A, 2B, 3
    std::unique( vnums.begin(), vnums.end(), EqualToVectorOfIntegerStar() );
    // OUTPUT: 1, 2A, 3, 3 }
    printVector("AFTER  UNIQ", vnums);

    // now we delete 3 twice, and we have a memory leak because 2B is not deleted.
    for (size_t inx = 0; inx < vnums.size(); ++inx)
    {
        delete(vnums[inx]);
    }
}

// print a line of the form "msg: 1,2,3,..,5,6,7\n", where 1..7 are the numbers in vnums vector
// PS: you may pass "hello world" (const char *) because of implicit (automatic) conversion
// from "const char *" to std::string conversion.

void printVector( const std::string& msg, const std::vector<int*>& vnums)
{
    std::cout << msg << ": ";

    for (size_t inx = 0; inx < vnums.size(); ++inx)
    {
        // insert comma separator before current elt, but ONLY after first elt
        if (inx > 0)
            std::cout << ",";
        std::cout << *vnums[inx];

    }
    std::cout << "\n";
}

假设a是一个向量，使用

a.erase(独特(a.begin (), a.end ()), a.end ());运行时间为O(n)。

我重做了内特·科尔的侧写得到了不同的结果。对于我的测试用例，直接对向量排序总是比使用集合更有效。我添加了一个新的更有效的方法，使用unordered_set。

请记住，unordered_set方法仅适用于您需要唯一和排序的类型的良好哈希函数。对于int型，这很简单!(标准库提供了一个默认的哈希，它只是标识函数。)另外，不要忘记在最后排序，因为unordered_set是无序的:)

我深入研究了set和unordered_set实现，发现构造函数实际上为每个元素构造了一个新节点，然后检查其值以确定是否应该实际插入(至少在Visual Studio实现中是这样)。

以下是5种方法:

f1:只是使用向量，sort + unique

sort( vec.begin(), vec.end() );
vec.erase( unique( vec.begin(), vec.end() ), vec.end() );

f2:转换为set(使用构造函数)

set<int> s( vec.begin(), vec.end() );
vec.assign( s.begin(), s.end() );

f3:转换为set(手动)

set<int> s;
for (int i : vec)
    s.insert(i);
vec.assign( s.begin(), s.end() );

f4:转换为unordered_set(使用构造函数)

unordered_set<int> s( vec.begin(), vec.end() );
vec.assign( s.begin(), s.end() );
sort( vec.begin(), vec.end() );

f5:转换为unordered_set(手动)

unordered_set<int> s;
for (int i : vec)
    s.insert(i);
vec.assign( s.begin(), s.end() );
sort( vec.begin(), vec.end() );

我在[1,10]，[1,1000]和[1,100000]的范围内随机选择了100,000,000 int的向量进行测试

结果(以秒为单位，越小越好):

range         f1       f2       f3       f4      f5
[1,10]      1.6821   7.6804   2.8232   6.2634  0.7980
[1,1000]    5.0773  13.3658   8.2235   7.6884  1.9861
[1,100000]  8.7955  32.1148  26.5485  13.3278  3.9822