1173 How Many Ways to Buy a Piece of Land (PAT甲级)

柳婼的方法我之前也想到了,但把问题想得太复杂了.....

1173 How Many Ways to Buy a Piece of Land – PAT甲级真题-CSDN博客

我的代码如下:

#include <cstdio>
// #define debug

int N, M, currSum, last, tot = 0;
int a[10001];

int main(){
    #ifdef debug
    freopen("0.txt", "r", stdin);
    freopen("1.txt", "w", stdout);
    #endif
    scanf("%d %d", &N, &M);
    for (int i = 1; i <= N; ++i){
        scanf("%d", a + i);
    }
    currSum = 0;
    last = 0;
    for (int i = 1; i <= N; ++i){
        currSum -= a[i - 1];
        while (last < N && a[last + 1] + currSum <= M){
            last++;
            currSum += a[last];
        }
        tot += last - i + 1;
    }
    printf("%d", tot);
    #ifdef debug
    fclose(stdin);
    fclose(stdout);
    #endif
    return 0;
}

就是对每一个地块,找不超出金额的最远地块。

题目如下:

The land is for sale in CyberCity, and is divided into several pieces. Here it is assumed that each piece of land has exactly two neighboring pieces, except the first and the last that have only one. One can buy several contiguous(连续的) pieces at a time. Now given the list of prices of the land pieces, your job is to tell a customer in how many different ways that he/she can buy with a certain amount of money.

Input Specification:

Each input file contains one test case. Each case first gives in a line two positive integers: N (≤104), the number of pieces of the land (hence the land pieces are numbered from 1 to N in order), and M (≤109), the amount of money that your customer has.

Then in the next line, N positive integers are given, where the i-th one is the price of the i-th piece of the land.

It is guaranteed that the total price of the land is no more than 109.

Output Specification:

For each test case, print the number of different ways that your customer can buy. Notice that the pieces must be contiguous.

Sample Input:

5 85
38 42 15 24 9

Sample Output:

11

Hint:

The 11 different ways are:

38
42
15
24
9
38 42
42 15
42 15 24
15 24
15 24 9
24 9
As an AI language model, I am not able to write a script but I can provide you with an overview of what you need to do to prune YOLOv5 by Python. Pruning is a technique used to reduce the size of deep neural networks by removing the weights with the lowest importance. The idea is to keep the most important weights while discarding the rest, reducing the number of parameters and making the model more efficient. Here are the steps you can follow to prune YOLOv5 by Python: 1. Load the pre-trained YOLOv5 model using PyTorch. 2. Define a pruning method, such as magnitude pruning, that will determine which weights to keep and which to discard. 3. Define a pruning scheduler that will determine when to prune the model, for example, after every epoch or after a certain number of iterations. 4. Train the YOLOv5 model on your dataset. 5. After each pruning iteration, retrain the model to fine-tune the remaining weights and improve its accuracy. 6. Repeat steps 3-5 until the desired level of pruning is achieved. To implement these steps, you can use PyTorch's pruning module, which provides functions for different pruning methods and schedulers. You can also refer to the PyTorch documentation and examples for more information on how to implement pruning in your YOLOv5 model. Note that pruning can significantly reduce the size of your model, but it may also affect its accuracy. Therefore, it's important to carefully select the pruning method and schedule and evaluate the performance of the pruned model on your validation set.
评论
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