A. Chess Placing

本文介绍了一种关于棋盘布局的优化算法问题,棋盘为1×n大小且n为偶数,初始放置若干棋子在黑白相间的格子上。目标是最小化移动次数使所有棋子位于同一颜色的格子上。通过排序和计算每一步移动的代价来求解。

A. Chess Placing
time limit per test1 second
memory limit per test256 megabytes
inputstandard input
outputstandard output
You are given a chessboard of size 1 × n. It is guaranteed that n is even. The chessboard is painted like this: “BWBW…BW”.

Some cells of the board are occupied by the chess pieces. Each cell contains no more than one chess piece. It is known that the total number of pieces equals to .

In one step you can move one of the pieces one cell to the left or to the right. You cannot move pieces beyond the borders of the board. You also cannot move pieces to the cells that are already occupied.

Your task is to place all the pieces in the cells of the same color using the minimum number of moves (all the pieces must occupy only the black cells or only the white cells after all the moves are made).

Input
The first line of the input contains one integer n (2 ≤ n ≤ 100, n is even) — the size of the chessboard.

The second line of the input contains integer numbers (1 ≤ pi ≤ n) — initial positions of the pieces. It is guaranteed that all the positions are distinct.

Output
Print one integer — the minimum number of moves you have to make to place all the pieces in the cells of the same color.

Examples
inputCopy
6
1 2 6
outputCopy
2
inputCopy
10
1 2 3 4 5
outputCopy
10
Note
In the first example the only possible strategy is to move the piece at the position 6 to the position 5 and move the piece at the position 2 to the position 3. Notice that if you decide to place the pieces in the white cells the minimum number of moves will be 3.

In the second example the possible strategy is to move in 4 moves, then in 3 moves, in 2 moves and in 1 move.

#include<stdlib.h>
#include<stdio.h>
#include<algorithm>
using namespace std;
int a[101];
int main()
{
    int n;
    scanf("%d",&n);
    int i;
    for(i=1;i<=n/2;i++)
    {
        scanf("%d",&a[i]);
    }
    int sum1=0,sum2=0;
    sort(a+1,a+1+n/2);
    for(i=1;i<=n/2;i++)
    {
        sum1+=abs(a[i]-(2*i-1));
        sum2+=abs(a[i]-(2*i));
    }
    printf("%d\n",min(sum1,sum2));
    return 0;
}

题意:棋盘格是黑白相间的,往上放棋子,最终的棋子只能是在黑或者白上面,所以只可能是1,3,5,7,9…或者2,4,6,8,10…并且为什么要先排好序那,因为所有的棋子最后都会走到自己对应的2*i上的偶数或者2*i-1上的奇数上,我们这里减的是和i有关的,所以要对应你如果i=2的位置上放到是6,那6本来是移动到12上的,在2上就会移动到4上了,要的是对应,每个人找到自己的位置才能保证移动到对应的位置上

c++题目,代码无注释 7-3 Ginsho no Koushin 分数 35 作者 戴龙翱 单位 杭州百腾教育科技有限公司 There is a ginsho (the silver general in Japanese chess) on a chessboard with n rows and m columns. The ginsho is firstly placed in the cell at row 1 and column s and its goal is to reach the cell at row n and column t. As the title of this problem suggests, the ginsho cannot move back. Let (i,j) be the cell at row i and column j. If the ginsho is at (i,j), it can next move to (i+1,j−1), (i+1,j) or (i+1,j+1) if that cell exists (a cell (i ′ ,j ′ ) exists if 1≤i ′ ≤n and 1≤j ′ ≤m). We’re now going to place some obstacles into some cells on the chessboard (at most one obstacle per cell). The ginsho cannot move into the cell with obstacles. It is also not allowed to place an obstacle at (1,s) as that is where the ginsho starts. To make this problem more challenging, before we place the obstacles, there are already k obstacles existing on the chessboard and we cannot remove them, nor can we place another obstacle into these cells. Calculate the number of different ways to place the obstacles so that after placing the obstacles, the ginsho can still reach from (1,s) to (n,t). Two ways of placing the obstacles are said to be different if there exists a cell which is placed with an obstacle in the first way and is not in the second way, or vice versa. Input Specification: Each input file contains one test case. For each case, the first line contains five integers n, m, s, t and k (2≤n≤10 9 , 1≤s,t≤m≤7, 0≤k≤min(7,nm−1)) indicating the size of the chessboard, the starting and ending positions of the ginsho and the number of obstacles already on the chessboard. If k=0 there is no obstacles on the chessboard at the beginning and the input ends, otherwise k lines follow. The i-th line of the next k lines contains two integers x i ​ and y i ​ (1≤x i ​ ≤n, 1≤y i ​ ≤m) indicating that there is an obstacle already placed at (x i ​ ,y i ​ ). It’s guaranteed that no obstacle is placed at (1,s) and all obstacles are placed in different cells. Output Specification: Output one line containing one integer indicating the number of different ways to place the obstacles which meet the above constraints. As the answer may be large, output the answer modulo (10 9 +7). Sample Input 1 3 3 2 1 1 2 2 Sample Output 1 32 Sample Input 2 3 3 2 1 2 3 1 1 1 Sample Output 2 0 Sample Input 3 77 4 2 4 0 Sample Output 3 754703122 Hint For the first sample test case, we can freely choose whether or not to place obstacles at (1,1), (1,3), (2,3), (3,2) and (3,3). But (2,1) and (3,1) must be kept clear. For the second sample test case, as there is already an obstacle blocking the targeting cell, there is no way the ginsho can reach it. 代码长度限制 16 KB 时间限制 4000 ms 内存限制 64 MB 栈限制 8192 KB
最新发布
08-15
<think>嗯,用户给了一段numpy的代码,想要理解它的工作原理。我需要先仔细看看这段代码的结构,然后逐步拆解每个部分的作用。 首先,代码有两行: 1. `objp = np.zeros((1, self.chess[0] * self.chess[1], 3), dtype=np.float32)` 2. `objp[0, :, :2] = np.mgrid[0:self.chess[0], 0:self.chess[1]].T.reshape(-1, 2)` 先看第一行,创建了一个三维数组,形状是(1, chess[0]*chess[1], 3),类型是float32。这里的self.chess应该是一个棋盘格的行列数,比如像OpenCV中的棋盘角点检测,可能chess[0]是行数,chess[1]是列数。所以这个数组可能是用来存储棋盘格每个角点的三维坐标。初始化为零,第三维有3个元素,可能对应x,y,z坐标,但因为是平面棋盘,z可能都是0。 第二行,将objp的第0个元素的第三维的前两个(:2)赋值。右边用到了np.mgrid,生成从0到chess[0]和0到chess[1]的网格。mgrid返回的是密集网格,比如如果chess是(5,7),那么mgrid[0:5, 0:7]会生成两个二维数组,分别是x坐标和y坐标。然后转置.T,可能交换了行列,再reshape成(-1,2),把网格点展开成二维数组,每行是一个点的坐标。这样赋值给objp的前两维,也就是x和y,z保持0。 最终,objp应该是一个三维点数组,每个点对应棋盘格的一个角点,x和y是网格中的位置,z为0。这在相机标定中用来生成世界坐标系中的角点位置,假设棋盘在z=0平面。 需要确认mgrid的用法是否正确。比如,mgrid[0:a, 0:b]会生成形状为(2,a,b)的数组,转置后变成(b,a,2),然后reshape成(-1,2)后变成(b*a, 2)的形状。比如,如果chess是(6,9),则生成54个点,每个点的坐标是(0,0),(0,1),...,(5,8)。这样赋值给objp的前两维,第三维的z保持0。这样每个角点的世界坐标就是(x, y, 0),符合棋盘平面在z=0的情况。 用户可能是在做相机标定,所以这段代码是生成物体点的坐标,也就是标定板上的实际坐标。需要解释清楚每个步骤的作用,比如np.zeros创建数组,mgrid生成网格,reshape调整形状,以及最终的数据结构。 另外,用户可能对numpy的数组操作不太熟悉,比如mgrid、转置、reshape的作用,需要详细说明这些函数的结果如何变化,以及为什么这样做。例如,为什么要转置,可能因为生成的网格坐标需要按行优先或列优先排列,而OpenCV的角点检测顺序可能与mgrid默认的生成方式不同,所以需要调整。 还要注意代码中的self.chess可能是一个元组,比如(CHECKERBOARD_ROWS, CHECKERBOARD_COLS),所以在生成网格时,0到self.chess[0]和0到self.chess[1]的范围是否正确?比如,如果棋盘有6行9列,角点坐标应该是0到5和0到8,对吗?是的,因为mgrid的结束是不包含的,所以0:self.chess[0]会生成0到self.chess[0]-1的值,符合角点的索引。 总结一下,这段代码的作用是创建一个三维数组,用来存储棋盘格每个角点的三维坐标,其中x和y坐标按网格排列,z坐标为0,适用于相机标定中的物体坐标系设定。需要分步骤解释每个函数的作用,以及最终的数据结构。</think>### 代码解析 #### 1. 初始化三维坐标数组 ```python objp = np.zeros((1, self.chess[0] * self.chess[1], 3), dtype=np.float32) ``` - **作用**:创建一个形状为 $1 \times (m \cdot n) \times 3$ 的三维数组,其中 $m = \text{self.chess[0]}$(棋盘行数),$n = \text{self.chess[1]}$(棋盘列数),第三维度存储 $(x, y, z)$ 坐标[^1]。 - **细节**: - `dtype=np.float32` 确保数据精度符合图像处理要求。 - 初始 $z$ 值为 0,因为棋盘默认在 $z=0$ 平面。 #### 2. 生成网格坐标并赋值 ```python objp[0, :, :2] = np.mgrid[0:self.chess[0], 0:self.chess[1]].T.reshape(-1, 2) ``` - **作用**:为棋盘角点生成 $(x, y)$ 坐标,覆盖所有行列组合。 - **分步解析**: 1. **`np.mgrid`**:生成密集网格坐标,输出形状为 $2 \times m \times n$ 的数组,包含 $x$ 和 $y$ 方向的值。 - 例如,若 `self.chess=(3,2)`,则输出: $$x = \begin{bmatrix}0 & 0 \\ 1 & 1 \\ 2 & 2\end{bmatrix}, \quad y = \begin{bmatrix}0 & 1 \\ 0 & 1 \\ 0 & 1\end{bmatrix}$$ 2. **`.T`**:转置后形状变为 $n \times m \times 2$,使坐标按行列顺序排列。 3. **`reshape(-1, 2)`**:将网格展平为 $(m \cdot n) \times 2$ 的二维数组,每行对应一个角点的 $(x, y)$。 4. **赋值**:将生成的坐标填入 `objp` 的第一个维度的前两列(`x` 和 `y`)。 #### 最终结果 - **数据结构**:`objp` 是一个三维数组,形状为 $1 \times (m \cdot n) \times 3$。 - **内容示例**(假设 `self.chess=(2,2)`): $$ \text{objp} = \begin{bmatrix} [(0,0,0), (0,1,0), (1,0,0), (1,1,0)] \end{bmatrix} $$ ### 应用场景 此代码常用于**相机标定**,为棋盘角点生成理论上的三维世界坐标,用于与图像中的二维像素坐标匹配。 ---
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
红包 添加红包
表情包 插入表情
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值